Search

With the expanding application of Large Language Models (LLMs) in various domains, it becomes imperative to comprehensively investigate their unforeseen behaviors and consequent outcomes. In this study, we introduce and systematically explore the phenomenon of “glitch tokens”, which are anomalous tokens produced by established tokenizers and could potentially compromise the models’ quality of response. Specifically, we experiment on seven top popular LLMs utilizing three distinct tokenizers and involving a totally of 182,517 tokens. We present categorizations of the identified glitch tokens and symptoms exhibited by LLMs when interacting with glitch tokens. Based on our observation that glitch tokens tend to cluster in the embedding space, we propose GlitchHunter, a novel iterative clustering-based technique, for efficient glitch token detection. The evaluation shows that our approach notably outperforms three baseline methods on eight open-source LLMs. To the best of our knowledge, we present the first comprehensive study on glitch tokens. Our new detection further provides valuable insights into mitigating tokenization-related errors in LLMs.

Generalized category discovery (GCD) aims at addressing a more realistic and challenging setting of semi-supervised learning, where only part of the category labels are assigned to certain training samples. Previous methods generally employ naive contrastive learning or unsupervised clustering scheme for all the samples. Nevertheless, they usually ignore the inherent critical information within the historical predictions of the model being trained. Specifically, we empirically reveal that a significant number of salient unlabeled samples yield consistent historical predictions corresponding to their ground truth category. From this observation, we propose a Memory Consistency guided Divide-and-conquer Learning framework (MCDL). In this framework, we introduce two memory banks to record historical prediction of unlabeled data, which are exploited to measure the credibility of each sample in terms of its prediction consistency. With the guidance of credibility, we can design a divide-and-conquer learning strategy to fully utilize the discriminative information of unlabeled data while alleviating the negative influence of noisy labels. Extensive experimental results on multiple benchmarks demonstrate the generality and superiority of our method, where our method outperforms state-of-the-art models by a large margin on both seen and unseen classes of the generic image recognition and challenging semantic shift settings (i.e.,with +8.4% gain on CUB and +8.1% on Standford Cars).

Industrial anomaly detection is generally addressed as an unsupervised task that aims at locating defects with only normal training samples. Recently, numerous 2D anomaly detection methods have been proposed and have achieved promising results, however, using only the 2D RGB data as input is not sufficient to identify imperceptible geometric surface anomalies. Hence, in this work, we focus on multi-modal anomaly detection. Specifically, we investigate early multi-modal approaches that attempted to utilize models pre-trained on large-scale visual datasets, i.e., ImageNet, to construct feature databases. And we empirically find that directly using these pre-trained models is not optimal, it can either fail to detect subtle defects or mistake abnormal features as normal ones. This may be attributed to the domain gap between target industrial data and source data.Towards this problem, we propose a Local-to-global Self-supervised Feature Adaptation (LSFA) method to finetune the adaptors and learn task-oriented representation toward anomaly detection.Both intra-modal adaptation and cross-modal alignment are optimized from a local-to-global perspective in LSFA to ensure the representation quality and consistency in the inference stage.Extensive experiments demonstrate that our method not only brings a significant performance boost to feature embedding based approaches, but also outperforms previous State-of-The-Art (SoTA) methods prominently on both MVTec-3D AD and Eyecandies datasets, e.g., LSFA achieves 97.1% I-AUROC on MVTec-3D, surpass previous SoTA by +3.4%.

Image retrieval aims to identify visually similar images within a database using a given query image. Traditional methods typically employ both global and local features extracted from images for matching, and may also apply re-ranking techniques to enhance accuracy. However, these methods often fail to account for the noise present in query images, which can stem from natural or human-induced factors, thereby negatively impacting retrieval performance. To mitigate this issue, we introduce a novel setting for low-quality image retrieval, and propose an Adaptive Noise-Based Network (AdapNet) to learn robust abstract representations. Specifically, we devise a quality compensation block trained to compensate for various low-quality factors in input images. Besides, we introduce an innovative adaptive noise-based loss function, which dynamically adjusts its focus on the gradient in accordance with image quality, thereby augmenting the learning of unknown noisy samples during training and enhancing intra-class compactness. To assess the performance, we construct two datasets with low-quality queries, which is built by applying various types of noise on clean query images on the standard Revisited Oxford and Revisited Paris datasets. Comprehensive experimental results illustrate that AdapNet surpasses state-of-the-art methods on the Noise Revisited Oxford and Noise Revisited Paris benchmarks, while maintaining competitive performance on high-quality datasets. The code and constructed datasets will be made available.

Large language models (LLMs) have transformed the field of natural language processing, but they remain susceptible to jailbreaking attacks that exploit their capabilities to generate unintended and potentially harmful content. Existing token-level jailbreaking techniques, while effective, face scalability and efficiency challenges, especially as models undergo frequent updates and incorporate advanced defensive measures. In this paper, we introduce JailMine, an innovative token-level manipulation approach that addresses these limitations effectively. JailMine employs an automated "mining" process to elicit malicious responses from LLMs by strategically selecting affirmative outputs and iteratively reducing the likelihood of rejection. Through rigorous testing across multiple well-known LLMs and datasets, we demonstrate JailMine's effectiveness and efficiency, achieving a significant average reduction of 86% in time consumed while maintaining high success rates averaging 95%, even in the face of evolving defensive strategies. Our work contributes to the ongoing effort to assess and mitigate the vulnerability of LLMs to jailbreaking attacks, underscoring the importance of continued vigilance and proactive measures to enhance the security and reliability of these powerful language models.

With the expanding application of Large Language Models (LLMs) in various domains, it becomes imperative to comprehensively investigate their unforeseen behaviors and consequent outcomes. In this study, we introduce and systematically explore the phenomenon of "glitch tokens", which are anomalous tokens produced by established tokenizers and could potentially compromise the models' quality of response. Specifically, we experiment on seven top popular LLMs utilizing three distinct tokenizers and involving a totally of 182,517 tokens. We present categorizations of the identified glitch tokens and symptoms exhibited by LLMs when interacting with glitch tokens. Based on our observation that glitch tokens tend to cluster in the embedding space, we propose GlitchHunter, a novel iterative clustering-based technique, for efficient glitch token detection. The evaluation shows that our approach notably outperforms three baseline methods on eight open-source LLMs. To the best of our knowledge, we present the first comprehensive study on glitch tokens. Our new detection further provides valuable insights into mitigating tokenization-related errors in LLMs.

Magnetars are neutron stars with extremely strong magnetic fields, frequently powering high-energy activity in X-rays. Pulsed radio emission following some X-ray outbursts have been detected, albeit its physical origin is unclear. It has long been speculated that the origin of magnetars' radio signals is different from those from canonical pulsars, although convincing evidence is still lacking. Five months after magnetar SGR 1935+2154's X-ray outburst and its associated Fast Radio Burst (FRB) 20200428, a radio pulsar phase was discovered. Here we report the discovery of X-ray spectral hardening associated with the emergence of periodic radio pulsations from SGR 1935+2154 and a detailed analysis of the properties of the radio pulses. The complex radio pulse morphology, which contains both narrow-band emission and frequency drifts, has not been seen before in other magnetars, but is similar to those of repeating FRBs - even though the luminosities are many orders of magnitude different. The observations suggest that radio emission originates from the outer magnetosphere of the magnetar, and the surface heating due to the bombardment of inward-going particles from the radio emission region is responsible for the observed X-ray spectral hardening., Comment: 47 pages, 11 figures

Collecting large-scale datasets is crucial for training deep models, annotating the data, however, inevitably yields noisy labels, which poses challenges to deep learning algorithms. Previous efforts tend to mitigate this problem via identifying and removing noisy samples or correcting their labels according to the statistical properties (e.g., loss values) among training samples. In this paper, we aim to tackle this problem from a new perspective, delving into the deep feature maps, we empirically find that models trained with clean and mislabeled samples manifest distinguishable activation feature distributions. From this observation, a novel robust training approach termed adversarial noisy masking is proposed. The idea is to regularize deep features with a label quality guided masking scheme, which adaptively modulates the input data and label simultaneously, preventing the model to overfit noisy samples. Further, an auxiliary task is designed to reconstruct input data, it naturally provides noise-free self-supervised signals to reinforce the generalization ability of deep models. The proposed method is simple and flexible, it is tested on both synthetic and real-world noisy datasets, where significant improvements are achieved over previous state-of-the-art methods.

Robust autonomous driving requires agents to accurately identify unexpected areas (anomalies) in urban scenes. To this end, some critical issues remain open: how to design advisable metric to measure anomalies, and how to properly generate training samples of anomaly data? Classical effort in anomaly detection usually resorts to pixel-wise uncertainty or sample synthesis, which ignores the contextual information and sometimes requires auxiliary data with fine-grained annotations. On the contrary, in this paper, we exploit the strong context-dependent nature of the segmentation task and design an energy-guided self-supervised framework for anomaly segmentation, which optimizes an anomaly head by maximizing the likelihood of self-generated anomaly pixels. For this purpose, we design two estimators to model anomaly likelihood, one is a task-agnostic binary estimator and the other depicts the likelihood as residual of task-oriented joint energy. Based on the proposed estimators, we devise an adaptive self-supervised training framework, which exploits the contextual reliance and estimated likelihood to refine mask annotations in anomaly areas. We conduct extensive experiments on challenging Fishyscapes and Road Anomaly benchmarks, demonstrating that without any auxiliary data or synthetic models, our method can still achieve comparable performance to supervised competitors. Code is available at https://github.com/yuanpengtu/SLEEG..

Training deep neural networks(DNN) with noisy labels is challenging since DNN can easily memorize inaccurate labels, leading to poor generalization ability. Recently, the meta-learning based label correction strategy is widely adopted to tackle this problem via identifying and correcting potential noisy labels with the help of a small set of clean validation data. Although training with purified labels can effectively improve performance, solving the meta-learning problem inevitably involves a nested loop of bi-level optimization between model weights and hyper-parameters (i.e., label distribution). As compromise, previous methods resort to a coupled learning process with alternating update. In this paper, we empirically find such simultaneous optimization over both model weights and label distribution can not achieve an optimal routine, consequently limiting the representation ability of backbone and accuracy of corrected labels. From this observation, a novel multi-stage label purifier named DMLP is proposed. DMLP decouples the label correction process into label-free representation learning and a simple meta label purifier. In this way, DMLP can focus on extracting discriminative feature and label correction in two distinctive stages. DMLP is a plug-and-play label purifier, the purified labels can be directly reused in naive end-to-end network retraining or other robust learning methods, where state-of-the-art results are obtained on several synthetic and real-world noisy datasets, especially under high noise levels.

Change detection is a widely adopted technique in remote sense imagery (RSI) analysis in the discovery of long-term geomorphic evolution. To highlight the areas of semantic changes, previous effort mostly pays attention to learning representative feature descriptors of a single image, while the difference information is either modeled with simple difference operations or implicitly embedded via feature interactions. Nevertheless, such difference modeling can be noisy since it suffers from non-semantic changes and lacks explicit guidance from image content or context. In this paper, we revisit the importance of feature difference for change detection in RSI, and propose a series of operations to fully exploit the difference information: Alignment, Perturbation and Decoupling (APD). Firstly, alignment leverages contextual similarity to compensate for the non-semantic difference in feature space. Next, a difference module trained with semantic-wise perturbation is adopted to learn more generalized change estimators, which reversely bootstraps feature extraction and prediction. Finally, a decoupled dual-decoder structure is designed to predict semantic changes in both content-aware and content-agnostic manners. Extensive experiments are conducted on benchmarks of LEVIR-CD, WHU-CD and DSIFN-CD, demonstrating our proposed operations bring significant improvement and achieve competitive results under similar comparative conditions. Code is available at https://github.com/wangsp1999/CD-Research/tree/main/openAPD, Comment: To appear in IJCAI 2023

Audio-Visual Segmentation (AVS) is a challenging task, which aims to segment sounding objects in video frames by exploring audio signals. Generally AVS faces two key challenges: (1) Audio signals inherently exhibit a high degree of information density, as sounds produced by multiple objects are entangled within the same audio stream; (2) Objects of the same category tend to produce similar audio signals, making it difficult to distinguish between them and thus leading to unclear segmentation results. Toward this end, we propose TransAVS, the first Transformer-based end-to-end framework for AVS task. Specifically, TransAVS disentangles the audio stream as audio queries, which will interact with images and decode into segmentation masks with full transformer architectures. This scheme not only promotes comprehensive audio-image communication but also explicitly excavates instance cues encapsulated in the scene. Meanwhile, to encourage these audio queries to capture distinctive sounding objects instead of degrading to be homogeneous, we devise two self-supervised loss functions at both query and mask levels, allowing the model to capture distinctive features within similar audio data and achieve more precise segmentation. Our experiments demonstrate that TransAVS achieves state-of-the-art results on the AVSBench dataset, highlighting its effectiveness in bridging the gap between audio and visual modalities., Comment: 4 pages, 3 figures

Current few-shot action recognition involves two primary sources of information for classification:(1) intra-video information, determined by frame content within a single video clip, and (2) inter-video information, measured by relationships (e.g., feature similarity) among videos. However, existing methods inadequately exploit these two information sources. In terms of intra-video information, current sampling operations for input videos may omit critical action information, reducing the utilization efficiency of video data. For the inter-video information, the action misalignment among videos makes it challenging to calculate precise relationships. Moreover, how to jointly consider both inter- and intra-video information remains under-explored for few-shot action recognition. To this end, we propose a novel framework, Video Information Maximization (VIM), for few-shot video action recognition. VIM is equipped with an adaptive spatial-temporal video sampler and a spatiotemporal action alignment model to maximize intra- and inter-video information, respectively. The video sampler adaptively selects important frames and amplifies critical spatial regions for each input video based on the task at hand. This preserves and emphasizes informative parts of video clips while eliminating interference at the data level. The alignment model performs temporal and spatial action alignment sequentially at the feature level, leading to more precise measurements of inter-video similarity. Finally, These goals are facilitated by incorporating additional loss terms based on mutual information measurement. Consequently, VIM acts to maximize the distinctiveness of video information from limited video data. Extensive experimental results on public datasets for few-shot action recognition demonstrate the effectiveness and benefits of our framework., Comment: arXiv admin note: text overlap with arXiv:2207.09759

Video Correlation Learning (VCL), which aims to analyze the relationships between videos, has been widely studied and applied in various general video tasks. However, applying VCL to instructional videos is still quite challenging due to their intrinsic procedural temporal structure. Specifically, procedural knowledge is critical for accurate correlation analyses on instructional videos. Nevertheless, current procedure-learning methods heavily rely on step-level annotations, which are costly and not scalable. To address this problem, we introduce a weakly supervised framework called Collaborative Procedure Alignment (CPA) for procedure-aware correlation learning on instructional videos. Our framework comprises two core modules: collaborative step mining and frame-to-step alignment. The collaborative step mining module enables simultaneous and consistent step segmentation for paired videos, leveraging the semantic and temporal similarity between frames. Based on the identified steps, the frame-to-step alignment module performs alignment between the frames and steps across videos. The alignment result serves as a measurement of the correlation distance between two videos. We instantiate our framework in two distinct instructional video tasks: sequence verification and action quality assessment. Extensive experiments validate the effectiveness of our approach in providing accurate and interpretable correlation analyses for instructional videos., Comment: has been accepted by AAAI 24

We present projective parallel single-pixel imaging (pPSI), a 3D photography method that provides a robust and efficient way to analyze the light transport behavior and enables separation of light effect due to global illumination, thereby achieving 3D structured light scanning under global illumination. The light transport behavior is described by the light transport coefficients (LTC), which contain complete information for a projector camera pair, and is a 4D data set. However, the capture of LTC is generally time consuming. The 4D LTC in pPSI are reduced to projection functions, thereby enabling a highly efficient data capture process. We introduce the local maximum constraint, which provides constraint for the location of candidate correspondence matching points when projections are captured. Local slice extension (LSE) method is introduced to accelerate the capture of projection functions. Optimization is conducted for pPSI under several situations. The number of projection functions required for pPSI is optimized and the influence of capture ratio in LSE on the accuracy of the correspondence matching points is investigated. Discussions and experiments include two typical kinds of global illuminations: inter-reflections and subsurface scattering. The proposed method is validated with several challenging scenarios, and outperforms the state-of-the-art methods., Comment: 21 pages,13 figures

Active domain adaptation has emerged as a solution to balance the expensive annotation cost and the performance of trained models in semantic segmentation. However, existing works usually ignore the correlation between selected samples and its local context in feature space, which leads to inferior usage of annotation budgets. In this work, we revisit the theoretical bound of the classical Core-set method and identify that the performance is closely related to the local sample distribution around selected samples. To estimate the density of local samples efficiently, we introduce a local proxy estimator with Dynamic Masked Convolution and develop a Density-aware Greedy algorithm to optimize the bound. Extensive experiments demonstrate the superiority of our approach. Moreover, with very few labels, our scheme achieves comparable performance to the fully supervised counterpart.

Colorless crystals of the new hydroxometalates Ba[RE(OH)5] with the rare-earth elements RE=Tb, Dy, Ho were synthesized under ultra-alkaline conditions in a KOH hydroflux at 200 °C. Single-crystal X-ray diffraction revealed that the three compounds crystallize isostructural in the monoclinic space group P21/n (no. 14). In the crystal structure, the rare-earth cations are coordinated by the oxygen atoms of seven hydroxide anions, which define a distorted pentagonal bipyramid. These polyhedra share edges of their basal ring forming infinite chains that run parallel to the [010] direction. Hydrogen bonds connect the chains into layers parallel to the (101) plane. The Ba2+ cations are located between these layers and surrounded by nine oxygen atoms. Ba[Dy(OH)5] is paramagnetic and shows no luminescence under UV light. When heated in synthetic air or argon, water is released in well-defined steps. Ba[Dy(OH)5] decomposes via DyOOH to Dy2O3, which then reacts with the remaining Ba(OH)2 to form BaDy2O4. Thus, the hydroxometalates can be used as carbon-free precursors for oxides.

Pure samples of colorless, air-stable Ba(BO2OH) crystals were obtained from Ba(NO3)2 and H3BO3 under the ultra-alkaline conditions of a KOH hydroflux at about 250 °C. The product formation depends on the water-base molar ratio and the molar ratio of the starting materials. B(OH)3 acts as a proton donor (Brønsted acid) rather than a hydroxide acceptor (Lewis acid). Ba(BO2OH) crystallizes in the non-centrosymmetric orthorhombic space group P212121. Hydrogen bonds connect the almost planar (BO2OH)2− anions, which are isostructural to HCO3−, into a syndiotactic chain. IR and Raman spectroscopy confirm the presence of hydroxide groups, which are involved in weak hydrogen bonds. Upon heating in air to about 450 °C, Ba(BO2OH) dehydrates to Ba2B2O5. Moreover, the non-centrosymmetric structure of Ba(BO2OH) crystals was verified with power-dependent confocal Second Harmonic Generation (SHG) microscopy indicating large conversion efficiencies in ambient atmosphere.

With the outbreak of coronavirus disease-2019 (COVID-19) worldwide, developments in the medical field have aroused concerns within society. As science and technology develop, wearable medical sensors have become the main means of medical data acquisition. To analyze the intelligent development status of wearable medical sensors, the current work classifies and prospects the application status and functions of wireless communication wearable medical sensors, based on human physiological data acquisition in the medical field. By understanding its working principles, data acquisition modes and action modes, the work chiefly analyzes the application of wearable medical sensors in vascular infarction, respiratory intensity, body temperature, blood oxygen concentration, and sleep detection, and reflects the key role of wearable medical sensors in human physiological data acquisition. Further exploration and prospecting are made by investigating the improvement of information security performance of wearable medical sensors, the improvement of biological adaptability and biodegradability of new materials, and the integration of wearable medical sensors and intelligence-assisted rehabilitation. The research expects to provide a reference for the intelligent development of wearable medical sensors and real-time monitoring of human health in the follow-up medical field. © 2022 by the authors. Licensee MDPI, Basel, Switzerland., cited By 0

With the outbreak of coronavirus disease-2019 (COVID-19) worldwide, developments in the medical field have aroused concerns within society. As science and technology develop, wearable medical sensors have become the main means of medical data acquisition. To analyze the intelligent development status of wearable medical sensors, the current work classifies and prospects the application status and functions of wireless communication wearable medical sensors, based on human physiological data acquisition in the medical field. By understanding its working principles, data acquisition modes and action modes, the work chiefly analyzes the application of wearable medical sensors in vascular infarction, respiratory intensity, body temperature, blood oxygen concentration, and sleep detection, and reflects the key role of wearable medical sensors in human physiological data acquisition. Further exploration and prospecting are made by investigating the improvement of information security performance of wearable medical sensors, the improvement of biological adaptability and biodegradability of new materials, and the integration of wearable medical sensors and intelligence-assisted rehabilitation. The research expects to provide a reference for the intelligent development of wearable medical sensors and real-time monitoring of human health in the follow-up medical field. © 2022 by the authors. Licensee MDPI, Basel, Switzerland., cited By 0

With the outbreak of coronavirus disease-2019 (COVID-19) worldwide, developments in the medical field have aroused concerns within society. As science and technology develop, wearable medical sensors have become the main means of medical data acquisition. To analyze the intelligent development status of wearable medical sensors, the current work classifies and prospects the application status and functions of wireless communication wearable medical sensors, based on human physiological data acquisition in the medical field. By understanding its working principles, data acquisition modes and action modes, the work chiefly analyzes the application of wearable medical sensors in vascular infarction, respiratory intensity, body temperature, blood oxygen concentration, and sleep detection, and reflects the key role of wearable medical sensors in human physiological data acquisition. Further exploration and prospecting are made by investigating the improvement of information security performance of wearable medical sensors, the improvement of biological adaptability and biodegradability of new materials, and the integration of wearable medical sensors and intelligence-assisted rehabilitation. The research expects to provide a reference for the intelligent development of wearable medical sensors and real-time monitoring of human health in the follow-up medical field. © 2022 by the authors. Licensee MDPI, Basel, Switzerland., cited By 0

With the outbreak of coronavirus disease-2019 (COVID-19) worldwide, developments in the medical field have aroused concerns within society. As science and technology develop, wearable medical sensors have become the main means of medical data acquisition. To analyze the intelligent development status of wearable medical sensors, the current work classifies and prospects the application status and functions of wireless communication wearable medical sensors, based on human physiological data acquisition in the medical field. By understanding its working principles, data acquisition modes and action modes, the work chiefly analyzes the application of wearable medical sensors in vascular infarction, respiratory intensity, body temperature, blood oxygen concentration, and sleep detection, and reflects the key role of wearable medical sensors in human physiological data acquisition. Further exploration and prospecting are made by investigating the improvement of information security performance of wearable medical sensors, the improvement of biological adaptability and biodegradability of new materials, and the integration of wearable medical sensors and intelligence-assisted rehabilitation. The research expects to provide a reference for the intelligent development of wearable medical sensors and real-time monitoring of human health in the follow-up medical field. © 2022 by the authors. Licensee MDPI, Basel, Switzerland., cited By 0

Colorless crystals of the new hydroxometalates Ba[RE(OH)5] with the rare-earth elements RE=Tb, Dy, Ho were synthesized under ultra-alkaline conditions in a KOH hydroflux at 200 °C. Single-crystal X-ray diffraction revealed that the three compounds crystallize isostructural in the monoclinic space group P21/n (no. 14). In the crystal structure, the rare-earth cations are coordinated by the oxygen atoms of seven hydroxide anions, which define a distorted pentagonal bipyramid. These polyhedra share edges of their basal ring forming infinite chains that run parallel to the [010] direction. Hydrogen bonds connect the chains into layers parallel to the (101) plane. The Ba2+ cations are located between these layers and surrounded by nine oxygen atoms. Ba[Dy(OH)5] is paramagnetic and shows no luminescence under UV light. When heated in synthetic air or argon, water is released in well-defined steps. Ba[Dy(OH)5] decomposes via DyOOH to Dy2O3, which then reacts with the remaining Ba(OH)2 to form BaDy2O4. Thus, the hydroxometalates can be used as carbon-free precursors for oxides.

Few-shot learning problem focuses on recognizing unseen classes given a few labeled images. In recent effort, more attention is paid to fine-grained feature embedding, ignoring the relationship among different distance metrics. In this paper, for the first time, we investigate the contributions of different distance metrics, and propose an adaptive fusion scheme, bringing significant improvements in few-shot classification. We start from a naive baseline of confidence summation and demonstrate the necessity of exploiting the complementary property of different distance metrics. By finding the competition problem among them, built upon the baseline, we propose an Adaptive Metrics Module (AMM) to decouple metrics fusion into metric-prediction fusion and metric-losses fusion. The former encourages mutual complementary, while the latter alleviates metric competition via multi-task collaborative learning. Based on AMM, we design a few-shot classification framework AMTNet, including the AMM and the Global Adaptive Loss (GAL), to jointly optimize the few-shot task and auxiliary self-supervised task, making the embedding features more robust. In the experiment, the proposed AMM achieves 2% higher performance than the naive metrics fusion module, and our AMTNet outperforms the state-of-the-arts on multiple benchmark datasets.

Training deep neural network (DNN) with noisy labels is practically challenging since inaccurate labels severely degrade the generalization ability of DNN. Previous efforts tend to handle part or full data in a unified denoising flow via identifying noisy data with a coarse small-loss criterion to mitigate the interference from noisy labels, ignoring the fact that the difficulties of noisy samples are different, thus a rigid and unified data selection pipeline cannot tackle this problem well. In this paper, we first propose a coarse-to-fine robust learning method called CREMA, to handle noisy data in a divide-and-conquer manner. In coarse-level, clean and noisy sets are firstly separated in terms of credibility in a statistical sense. Since it is practically impossible to categorize all noisy samples correctly, we further process them in a fine-grained manner via modeling the credibility of each sample. Specifically, for the clean set, we deliberately design a memory-based modulation scheme to dynamically adjust the contribution of each sample in terms of its historical credibility sequence during training, thus alleviating the effect from noisy samples incorrectly grouped into the clean set. Meanwhile, for samples categorized into the noisy set, a selective label update strategy is proposed to correct noisy labels while mitigating the problem of correction error. Extensive experiments are conducted on benchmarks of different modalities, including image classification (CIFAR, Clothing1M etc) and text recognition (IMDB), with either synthetic or natural semantic noises, demonstrating the superiority and generality of CREMA., Comment: ECCV 2022: L2ID Workshop

Unsupervised Domain Adaptation (UDA) aims to adapt the model trained on the labeled source domain to an unlabeled target domain. In this paper, we present Prototypical Contrast Adaptation (ProCA), a simple and efficient contrastive learning method for unsupervised domain adaptive semantic segmentation. Previous domain adaptation methods merely consider the alignment of the intra-class representational distributions across various domains, while the inter-class structural relationship is insufficiently explored, resulting in the aligned representations on the target domain might not be as easily discriminated as done on the source domain anymore. Instead, ProCA incorporates inter-class information into class-wise prototypes, and adopts the class-centered distribution alignment for adaptation. By considering the same class prototypes as positives and other class prototypes as negatives to achieve class-centered distribution alignment, ProCA achieves state-of-the-art performance on classical domain adaptation tasks, {\em i.e., GTA5 $\to$ Cityscapes \text{and} SYNTHIA $\to$ Cityscapes}. Code is available at \href{https://github.com/jiangzhengkai/ProCA}{ProCA}

Deficit irrigation (DI) was acknowledged as an effective technique to improve water use efficiency (WUE) without significant yield reduction. In this study, a 3-year field experiment was conducted in Northeast China during 2017–2019 to investigate the combined effects of 3-week DI from 3-leaf stage and N fertilization on maize seedling growth and determine the resulting impacts on silking growth and yield formation, N use efficiency (NUE) and WUE. Results showed that seedling-stage DI decreased leaf area and photosynthesis, thus significantly limited shoot and root dry biomass for maize seedling, compared to well-watered (WW) plants. In 2017 and 2019, seedling-stage DI positively improved seedling growth with higher root: shoot ratio and enhanced drought tolerance, under higher initial soil water contents (SWC) with sufficient precipitation before DI. The DI-primed plants showed similar or better performances on reproductive growth, grain yield, WUE and NUE compared to WW plants, even experiencing heavy rainfall or drought stresses around the silking stage. However, the contrasting results were observed in 2018 with negative DI effects on seedling and silking growth and final yield, probably due to less rainfall and lower SWC before DI. In all 3 years, N fertilization had significant compensatory effects on limited seedling growth under DI, and its effect was much less in 2018 than other years due to adverse early climate. The principal component and correlation analysis revealed maize silking growth, grain yield, NUE and WUE were strongly related to the seedling growth as affected by water and N managements under various climatic conditions. In conclusion, a short-term and moderate DI regime—adopted at the seedling stage under higher initial SWC and coupled with an appropriate N fertilization—is beneficial to control redundant vegetative growth while optimizing root development, therefore effectively improving drought tolerance for maize plants and achieving higher, Deficit irrigation (DI) was acknowledged as an effective technique to improve water use efficiency (WUE) without significant yield reduction. In this study, a 3-year field experiment was conducted in Northeast China during 2017–2019 to investigate the combined effects of 3-week DI from 3-leaf stage and N fertilization on maize seedling growth and determine the resulting impacts on silking growth and yield formation, N use efficiency (NUE) and WUE. Results showed that seedling-stage DI decreased leaf area and photosynthesis, thus significantly limited shoot and root dry biomass for maize seedling, compared to well-watered (WW) plants. In 2017 and 2019, seedling-stage DI positively improved seedling growth with higher root: shoot ratio and enhanced drought tolerance, under higher initial soil water contents (SWC) with sufficient precipitation before DI. The DI-primed plants showed similar or better performances on reproductive growth, grain yield, WUE and NUE compared to WW plants, even experiencing heavy rainfall or drought stresses around the silking stage. However, the contrasting results were observed in 2018 with negative DI effects on seedling and silking growth and final yield, probably due to less rainfall and lower SWC before DI. In all 3 years, N fertilization had significant compensatory effects on limited seedling growth under DI, and its effect was much less in 2018 than other years due to adverse early climate. The principal component and correlation analysis revealed maize silking growth, grain yield, NUE and WUE were strongly related to the seedling growth as affected by water and N managements under various climatic conditions. In conclusion, a short-term and moderate DI regime—adopted at the seedling stage under higher initial SWC and coupled with an appropriate N fertilization—is beneficial to control redundant vegetative growth while optimizing root development, therefore effectively improving drought tolerance for maize plants and achieving higher

Deficit irrigation (DI) was acknowledged as an effective technique to improve water use efficiency (WUE) without significant yield reduction. In this study, a 3-year field experiment was conducted in Northeast China during 2017–2019 to investigate the combined effects of 3-week DI from 3-leaf stage and N fertilization on maize seedling growth and determine the resulting impacts on silking growth and yield formation, N use efficiency (NUE) and WUE. Results showed that seedling-stage DI decreased leaf area and photosynthesis, thus significantly limited shoot and root dry biomass for maize seedling, compared to well-watered (WW) plants. In 2017 and 2019, seedling-stage DI positively improved seedling growth with higher root: shoot ratio and enhanced drought tolerance, under higher initial soil water contents (SWC) with sufficient precipitation before DI. The DI-primed plants showed similar or better performances on reproductive growth, grain yield, WUE and NUE compared to WW plants, even experiencing heavy rainfall or drought stresses around the silking stage. However, the contrasting results were observed in 2018 with negative DI effects on seedling and silking growth and final yield, probably due to less rainfall and lower SWC before DI. In all 3 years, N fertilization had significant compensatory effects on limited seedling growth under DI, and its effect was much less in 2018 than other years due to adverse early climate. The principal component and correlation analysis revealed maize silking growth, grain yield, NUE and WUE were strongly related to the seedling growth as affected by water and N managements under various climatic conditions. In conclusion, a short-term and moderate DI regime—adopted at the seedling stage under higher initial SWC and coupled with an appropriate N fertilization—is beneficial to control redundant vegetative growth while optimizing root development, therefore effectively improving drought tolerance for maize plants and achieving higher, Deficit irrigation (DI) was acknowledged as an effective technique to improve water use efficiency (WUE) without significant yield reduction. In this study, a 3-year field experiment was conducted in Northeast China during 2017–2019 to investigate the combined effects of 3-week DI from 3-leaf stage and N fertilization on maize seedling growth and determine the resulting impacts on silking growth and yield formation, N use efficiency (NUE) and WUE. Results showed that seedling-stage DI decreased leaf area and photosynthesis, thus significantly limited shoot and root dry biomass for maize seedling, compared to well-watered (WW) plants. In 2017 and 2019, seedling-stage DI positively improved seedling growth with higher root: shoot ratio and enhanced drought tolerance, under higher initial soil water contents (SWC) with sufficient precipitation before DI. The DI-primed plants showed similar or better performances on reproductive growth, grain yield, WUE and NUE compared to WW plants, even experiencing heavy rainfall or drought stresses around the silking stage. However, the contrasting results were observed in 2018 with negative DI effects on seedling and silking growth and final yield, probably due to less rainfall and lower SWC before DI. In all 3 years, N fertilization had significant compensatory effects on limited seedling growth under DI, and its effect was much less in 2018 than other years due to adverse early climate. The principal component and correlation analysis revealed maize silking growth, grain yield, NUE and WUE were strongly related to the seedling growth as affected by water and N managements under various climatic conditions. In conclusion, a short-term and moderate DI regime—adopted at the seedling stage under higher initial SWC and coupled with an appropriate N fertilization—is beneficial to control redundant vegetative growth while optimizing root development, therefore effectively improving drought tolerance for maize plants and achieving higher

Despite plenty of efforts focusing on improving the domain adaptation ability (DA) under unsupervised or few-shot semi-supervised settings, recently the solution of active learning started to attract more attention due to its suitability in transferring model in a more practical way with limited annotation resource on target data. Nevertheless, most active learning methods are not inherently designed to handle domain gap between data distribution, on the other hand, some active domain adaptation methods (ADA) usually requires complicated query functions, which is vulnerable to overfitting. In this work, we propose a concise but effective ADA method called Select-by-Distinctive-Margin (SDM), which consists of a maximum margin loss and a margin sampling algorithm for data selection. We provide theoretical analysis to show that SDM works like a Support Vector Machine, storing hard examples around decision boundaries and exploiting them to find informative and transferable data. In addition, we propose two variants of our method, one is designed to adaptively adjust the gradient from margin loss, the other boosts the selectivity of margin sampling by taking the gradient direction into account. We benchmark SDM with standard active learning setting, demonstrating our algorithm achieves competitive results with good data scalability. Code is available at https://github.com/TencentYoutuResearch/ActiveLearning-SDM, Comment: To appear in CVPR 2022

This article is a gentle discussion about the field of reinforcement learning in practice, about opportunities and challenges, touching a broad range of topics, with perspectives and without technical details. The article is based on both historical and recent research papers, surveys, tutorials, talks, blogs, books, (panel) discussions, and workshops/conferences. Various groups of readers, like researchers, engineers, students, managers, investors, officers, and people wanting to know more about the field, may find the article interesting. In this article, we first give a brief introduction to reinforcement learning (RL), and its relationship with deep learning, machine learning and AI. Then we discuss opportunities of RL, in particular, products and services, games, bandits, recommender systems, robotics, transportation, finance and economics, healthcare, education, combinatorial optimization, computer systems, and science and engineering. Then we discuss challenges, in particular, 1) foundation, 2) representation, 3) reward, 4) exploration, 5) model, simulation, planning, and benchmarks, 6) off-policy/offline learning, 7) learning to learn a.k.a. meta-learning, 8) explainability and interpretability, 9) constraints, 10) software development and deployment, 11) business perspectives, and 12) more challenges. We conclude with a discussion, attempting to answer: "Why has RL not been widely adopted in practice yet?" and "When is RL helpful?".

With the outbreak of coronavirus disease-2019 (COVID-19) worldwide, developments in the medical field have aroused concerns within society. As science and technology develop, wearable medical sensors have become the main means of medical data acquisition. To analyze the intelligent development status of wearable medical sensors, the current work classifies and prospects the application status and functions of wireless communication wearable medical sensors, based on human physiological data acquisition in the medical field. By understanding its working principles, data acquisition modes and action modes, the work chiefly analyzes the application of wearable medical sensors in vascular infarction, respiratory intensity, body temperature, blood oxygen concentration, and sleep detection, and reflects the key role of wearable medical sensors in human physiological data acquisition. Further exploration and prospecting are made by investigating the improvement of information security performance of wearable medical sensors, the improvement of biological adaptability and biodegradability of new materials, and the integration of wearable medical sensors and intelligence-assisted rehabilitation. The research expects to provide a reference for the intelligent development of wearable medical sensors and real-time monitoring of human health in the follow-up medical field. © 2022 by the authors. Licensee MDPI, Basel, Switzerland., cited By 0

Jing Zhang,1,&ast; Yuxi Li,2,&ast; Bo Zheng,2 Jianxing Qiu,3 Xiahuan Chen,1 Weiwei Zhou,1 Yan Fan,1 Meilin Liu1 1Department of Geriatrics, Peking University First Hospital, Beijing, 100034, People’s Republic of China; 2Department of Cardiology, Institute of Cardiovascular Disease, Peking University First Hospital, Beijing, 100034, People’s Republic of China; 3Department of Radiology, Peking University First Hospital, Beijing, 100034, People’s Republic of China&ast;These authors contributed equally to this workCorrespondence: Meilin Liu, Department of Geriatrics, Peking University First Hospital, No. 8 Xishiku Street, Xicheng District, Beijing, 100034, People’s Republic of China, Tel +86-010-83572022, Email liumeilin@hotmail.comPurpose: To assess the diagnostic efficiency of a combination of symptoms, residual Syntax score (rSS) and non-invasive tests in elderly post-PCI patients.Patients and Methods: This was a retrospective study that consecutively enrolled patients ≥ 60 years old with chronic coronary syndrome and previous stent implantation without lesions requiring further revascularization between March 2013 and June 2020. The patients were scheduled for exercise ECG, CCTA and invasive coronary angiography within 4 weeks. The study then calculated rSS and the sensitivity, specificity, positive and negative predictive values (PPV and NPV) and accuracy of symptoms, rSS, exercise ECG and CCTA, taking computational pressure-flow dynamics derived fractional flow reserve (caFFR) as the standard reference.Results: A total of 114 patients were enrolled in this study, including 75 patients with caFFR-positive and 39 patients with caFFR-negative. The caFFR-positive group had more patients with typical angina. Furthermore, the rSS in the caFFR-positive group was higher than that in the caFFR-negative category (7.33 ± 6.56 vs 3.34 ± 4.26, p < 0.001). There was no significant difference in exercise ECG results between the two groups. However, the

Pure samples of colorless, air-stable Ba(BO2OH) crystals were obtained from Ba(NO3)2 and H3BO3 under the ultra-alkaline conditions of a KOH hydroflux at about 250 °C. The product formation depends on the water-base molar ratio and the molar ratio of the starting materials. B(OH)3 acts as a proton donor (Brønsted acid) rather than a hydroxide acceptor (Lewis acid). Ba(BO2OH) crystallizes in the non-centrosymmetric orthorhombic space group P212121. Hydrogen bonds connect the almost planar (BO2OH)2− anions, which are isostructural to HCO3−, into a syndiotactic chain. IR and Raman spectroscopy confirm the presence of hydroxide groups, which are involved in weak hydrogen bonds. Upon heating in air to about 450 °C, Ba(BO2OH) dehydrates to Ba2B2O5. Moreover, the non-centrosymmetric structure of Ba(BO2OH) crystals was verified with power-dependent confocal Second Harmonic Generation (SHG) microscopy indicating large conversion efficiencies in ambient atmosphere.

Modern video object segmentation (VOS) algorithms have achieved remarkably high performance in a sequential processing order, while most of currently prevailing pipelines still show some obvious inadequacy like accumulative error, unknown robustness or lack of proper interpretation tools. In this paper, we place the semi-supervised video object segmentation problem into a cyclic workflow and find the defects above can be collectively addressed via the inherent cyclic property of semi-supervised VOS systems. Firstly, a cyclic mechanism incorporated to the standard sequential flow can produce more consistent representations for pixel-wise correspondance. Relying on the accurate reference mask in the starting frame, we show that the error propagation problem can be mitigated. Next, a simple gradient correction module, which naturally extends the offline cyclic pipeline to an online manner, can highlight the high-frequent and detailed part of results to further improve the segmentation quality while keeping feasible computation cost. Meanwhile such correction can protect the network from severe performance degration resulted from interference signals. Finally we develop cycle effective receptive field (cycle-ERF) based on gradient correction process to provide a new perspective into analyzing object-specific regions of interests. We conduct comprehensive comparison and detailed analysis on challenging benchmarks of DAVIS16, DAVIS17 and Youtube-VOS, demonstrating that the cyclic mechanism is helpful to enhance segmentation quality, improve the robustness of VOS systems, and further provide qualitative comparison and interpretation on how different VOS algorithms work. The code of this project can be found at https://github.com/lyxok1/STM-Training, Comment: modified version to appear in IJCV. arXiv admin note: substantial text overlap with arXiv:2010.12176

In this paper, we place the atomic action detection problem into a Long-Short Term Context (LSTC) to analyze how the temporal reliance among video signals affect the action detection results. To do this, we decompose the action recognition pipeline into short-term and long-term reliance, in terms of the hypothesis that the two kinds of context are conditionally independent given the objective action instance. Within our design, a local aggregation branch is utilized to gather dense and informative short-term cues, while a high order long-term inference branch is designed to reason the objective action class from high-order interaction between actor and other person or person pairs. Both branches independently predict the context-specific actions and the results are merged in the end. We demonstrate that both temporal grains are beneficial to atomic action recognition. On the mainstream benchmarks of atomic action detection, our design can bring significant performance gain from the existing state-of-the-art pipeline. The code of this project can be found at [this url](https://github.com/TencentYoutuResearch/ActionDetection-LSTC), Comment: ACM Multimedia 2021

The crux of self-supervised video representation learning is to build general features from unlabeled videos. However, most recent works have mainly focused on high-level semantics and neglected lower-level representations and their temporal relationship which are crucial for general video understanding. To address these challenges, this paper proposes a multi-level feature optimization framework to improve the generalization and temporal modeling ability of learned video representations. Concretely, high-level features obtained from naive and prototypical contrastive learning are utilized to build distribution graphs, guiding the process of low-level and mid-level feature learning. We also devise a simple temporal modeling module from multi-level features to enhance motion pattern learning. Experiments demonstrate that multi-level feature optimization with the graph constraint and temporal modeling can greatly improve the representation ability in video understanding. Code is available at https://github.com/shvdiwnkozbw/Video-Representation-via-Multi-level-Optimization., Comment: ICCV 2021

Few-shot action recognition aims to recognize novel action classes (query) using just a few samples (support). The majority of current approaches follow the metric learning paradigm, which learns to compare the similarity between videos. Recently, it has been observed that directly measuring this similarity is not ideal since different action instances may show distinctive temporal distribution, resulting in severe misalignment issues across query and support videos. In this paper, we arrest this problem from two distinct aspects -- action duration misalignment and action evolution misalignment. We address them sequentially through a Two-stage Action Alignment Network (TA2N). The first stage locates the action by learning a temporal affine transform, which warps each video feature to its action duration while dismissing the action-irrelevant feature (e.g. background). Next, the second stage coordinates query feature to match the spatial-temporal action evolution of support by performing temporally rearrange and spatially offset prediction. Extensive experiments on benchmark datasets show the potential of the proposed method in achieving state-of-the-art performance for few-shot action recognition.The code of this project can be found at https://github.com/R00Kie-Liu/TA2N, Comment: Published in AAAI 2022

Pedestrian detection in a crowd is a challenging task due to a high number of mutually-occluding human instances, which brings ambiguity and optimization difficulties to the current IoU-based ground truth assignment procedure in classical object detection methods. In this paper, we develop a unique perspective of pedestrian detection as a variational inference problem. We formulate a novel and efficient algorithm for pedestrian detection by modeling the dense proposals as a latent variable while proposing a customized Auto Encoding Variational Bayes (AEVB) algorithm. Through the optimization of our proposed algorithm, a classical detector can be fashioned into a variational pedestrian detector. Experiments conducted on CrowdHuman and CityPersons datasets show that the proposed algorithm serves as an efficient solution to handle the dense pedestrian detection problem for the case of single-stage detectors. Our method can also be flexibly applied to two-stage detectors, achieving notable performance enhancement.

Luping Yang,1,&ast; Dongling Zhong,2,&ast; Yue Zhang,2 Yuxi Li,2 Tianyu Liu,3 Yaling Zheng,2 Wei Wang,4 Juan Li,2 Li Guan,5 Rongjiang Jin2 1Department of Rehabilitation Technology, Sichuan Nursing Vocational College, Chengdu, 610037, People’s Republic of China; 2Department of Rehabilitation, Chengdu University of Traditional Chinese Medicine, Chengdu, 610037, People’s Republic of China; 3Department of Sport, Chengdu University of Traditional Chinese Medicine, Chengdu, 610037, People’s Republic of China; 4Department of Rehabilitation, Kunming Municipal Hospital of Traditional Chinese Medicine, Kunming, 650000, People’s Republic of China; 5Department of Rehabilitation, People’s Hospital of Fushun County, Zigong, 643000, People’s Republic of China&ast;These authors contributed equally to this workCorrespondence: Li Guan Email 172739721@qq.comRongjiang Jin Email cdzyydxjrj@126.comObjective: Since current systematic reviews (SRs) show that results of effectiveness on Tai Chi for chronic obstructive pulmonary disease (COPD) are inconsistent, the purpose of this study is to find the reasons of the disparity by comprehensively appraising the related SRs.Methods: Six databases were systematically searched from the inception date to April 17, 2021. The methodological quality, the risk of bias, the reporting quality, and the quality of evidence were independently assessed by two reviewers with the AMSTAR 2, ROBIS, PRISMA, and GRADE.Results: A total of 12 studies met the inclusion criteria: 10 SRs were rated critically low quality and two SRs were low quality by AMSTAR 2. By the ROBIS, four out of 12 SRs were rated as “low risk”. According to PRISMA, nine out of 12 SRs were adequately reported over 80%. With the GRADE tool, three out of 12 SRs rated the FEV1 as “Moderate”, one out of 12 SRs (1/12, 9%) rated the FEV1/FVC (%) as “Moderate”, three out of 12 SRs assessed the 6MWD as “Moderate”, three out of 12 SRs evaluated the SGRQ as “Mod

Aims Based on the aortic pressure waveform, a specially designed computational fluid dynamic (CFD) method was proposed to determine coronary angiography-derived diastolic pressure ratio (caDPR) without using invasive pressure wire. The aim of the study is to retrospectively assess diagnostic performance of the caDPR in the catheterization laboratory, based on a previous multicenter trial for online assessment of coronary angiography-derived FFR (caFFR). Methods and Results Patients with diagnosis of stable or unstable angina pectoris were enrolled in six centers. Wire-derived FFR was measured in coronary arteries with 30-90% diameter stenosis. Offline caDPR was assessed in blinded fashion against wire-derived FFR at an independent core laboratory. A total of 330 patients who met the inclusion/exclusion criteria were enrolled from June 26 to December 18, 2018. Offline computed caDPR and wire-derived FFR were compared in 328 interrogated vessels. The caDPR with a cutoff value of 0.89 shows diagnostic accuracy of 87.7%, sensitivity of 89.5%, specificity of 86.8%, and AUC of 0.940 against the wire-derived FFR with a cutoff value of 0.80. Conclusions Using wired-based FFR as the standard reference, there is good diagnostic performance of the novel-CFD-design caDPR. Hence, caDPR could enhance the hemodynamic assessment of coronary lesions.

Aims Based on the aortic pressure waveform, a specially designed computational fluid dynamic (CFD) method was proposed to determine coronary angiography-derived diastolic pressure ratio (caDPR) without using invasive pressure wire. The aim of the study is to retrospectively assess diagnostic performance of the caDPR in the catheterization laboratory, based on a previous multicenter trial for online assessment of coronary angiography-derived FFR (caFFR). Methods and Results Patients with diagnosis of stable or unstable angina pectoris were enrolled in six centers. Wire-derived FFR was measured in coronary arteries with 30-90% diameter stenosis. Offline caDPR was assessed in blinded fashion against wire-derived FFR at an independent core laboratory. A total of 330 patients who met the inclusion/exclusion criteria were enrolled from June 26 to December 18, 2018. Offline computed caDPR and wire-derived FFR were compared in 328 interrogated vessels. The caDPR with a cutoff value of 0.89 shows diagnostic accuracy of 87.7%, sensitivity of 89.5%, specificity of 86.8%, and AUC of 0.940 against the wire-derived FFR with a cutoff value of 0.80. Conclusions Using wired-based FFR as the standard reference, there is good diagnostic performance of the novel-CFD-design caDPR. Hence, caDPR could enhance the hemodynamic assessment of coronary lesions.

Aims Based on the aortic pressure waveform, a specially designed computational fluid dynamic (CFD) method was proposed to determine coronary angiography-derived diastolic pressure ratio (caDPR) without using invasive pressure wire. The aim of the study is to retrospectively assess diagnostic performance of the caDPR in the catheterization laboratory, based on a previous multicenter trial for online assessment of coronary angiography-derived FFR (caFFR). Methods and Results Patients with diagnosis of stable or unstable angina pectoris were enrolled in six centers. Wire-derived FFR was measured in coronary arteries with 30-90% diameter stenosis. Offline caDPR was assessed in blinded fashion against wire-derived FFR at an independent core laboratory. A total of 330 patients who met the inclusion/exclusion criteria were enrolled from June 26 to December 18, 2018. Offline computed caDPR and wire-derived FFR were compared in 328 interrogated vessels. The caDPR with a cutoff value of 0.89 shows diagnostic accuracy of 87.7%, sensitivity of 89.5%, specificity of 86.8%, and AUC of 0.940 against the wire-derived FFR with a cutoff value of 0.80. Conclusions Using wired-based FFR as the standard reference, there is good diagnostic performance of the novel-CFD-design caDPR. Hence, caDPR could enhance the hemodynamic assessment of coronary lesions.

Based on the distribution of tidal deformabilities and component masses of binary neutron star merger GW170817, the parametric equation of states (EOS) are employed to probe the nuclear symmetry energy and the properties of neutron star. To obtain a proper distribution of the parameters of the EOS that is consistent with the observation, Bayesian analysis is used and the constraints of causality and maximum mass are considered. From this analysis, it is found that the symmetry energy at twice the saturation density of nuclear matter can be constrained within $E_{sym}(2{\rho_{0}})$ = $34.5^{+20.5}_{-2.3}$ MeV at 90\% credible level. Moreover, the constraints on the radii and dimensionless tidal deformabilities of canonical neutron stars are also demonstrated through this analysis, and the corresponding constraints are 10.80 km $< R_{1.4} <$ 13.20 km and $133 < \Lambda_{1.4} < 686$ at 90\% credible level, with the most probable value of $\bar{R}_{1.4}$ = 12.60 km and $\bar{\Lambda}_{1.4}$ = 500, respectively. With respect to the prior, our result (posterior result) prefers a softer EOS, corresponding to a lower expected value of symmetry energy, a smaller radius and a smaller tidal deformability., Comment: 15 pages, 15 figures

Aims Based on the aortic pressure waveform, a specially designed computational fluid dynamic (CFD) method was proposed to determine coronary angiography-derived diastolic pressure ratio (caDPR) without using invasive pressure wire. The aim of the study is to retrospectively assess diagnostic performance of the caDPR in the catheterization laboratory, based on a previous multicenter trial for online assessment of coronary angiography-derived FFR (caFFR). Methods and Results Patients with diagnosis of stable or unstable angina pectoris were enrolled in six centers. Wire-derived FFR was measured in coronary arteries with 30-90% diameter stenosis. Offline caDPR was assessed in blinded fashion against wire-derived FFR at an independent core laboratory. A total of 330 patients who met the inclusion/exclusion criteria were enrolled from June 26 to December 18, 2018. Offline computed caDPR and wire-derived FFR were compared in 328 interrogated vessels. The caDPR with a cutoff value of 0.89 shows diagnostic accuracy of 87.7%, sensitivity of 89.5%, specificity of 86.8%, and AUC of 0.940 against the wire-derived FFR with a cutoff value of 0.80. Conclusions Using wired-based FFR as the standard reference, there is good diagnostic performance of the novel-CFD-design caDPR. Hence, caDPR could enhance the hemodynamic assessment of coronary lesions.

Along with the development of modern smart cities, human-centric video analysis has been encountering the challenge of analyzing diverse and complex events in real scenes. A complex event relates to dense crowds, anomalous individuals, or collective behaviors. However, limited by the scale and coverage of existing video datasets, few human analysis approaches have reported their performances on such complex events. To this end, we present a new large-scale dataset with comprehensive annotations, named Human-in-Events or HiEve (Human-centric video analysis in complex Events), for the understanding of human motions, poses, and actions in a variety of realistic events, especially in crowd & complex events. It contains a record number of poses (>1M), the largest number of action instances (>56k) under complex events, as well as one of the largest numbers of trajectories lasting for longer time (with an average trajectory length of >480 frames). Based on its diverse annotation, we present two simple baselines for action recognition and pose estimation, respectively. They leverage cross-label information during training to enhance the feature learning in corresponding visual tasks. Experiments show that they could boost the performance of existing action recognition and pose estimation pipelines. More importantly, they prove the widely ranged annotations in HiEve can improve various video tasks. Furthermore, we conduct extensive experiments to benchmark recent video analysis approaches together with our baseline methods, demonstrating HiEve is a challenging dataset for human-centric video analysis. We expect that the dataset will advance the development of cutting-edge techniques in human-centric analysis and the understanding of complex events. The dataset is available at http://humaninevents.org, Comment: Dataset for Large-scale Human-centric Video Analysis in Complex Events (http://humaninevents.org), the paper has been published in Int J Comput Vis (2023)

To enable DNNs on edge devices like mobile phones, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attempted to directly approximate a pretrained model by low-rank decomposition; however, small approximation errors in parameters can ripple over a large prediction loss. As a result, performance usually drops significantly and a sophisticated effort on fine-tuning is required to recover accuracy. Apparently, it is not optimal to separate low-rank approximation from training. Unlike previous works, this paper integrates low rank approximation and regularization into the training process. We propose Trained Rank Pruning (TRP), which alternates between low rank approximation and training. TRP maintains the capacity of the original network while imposing low-rank constraints during training. A nuclear regularization optimized by stochastic sub-gradient descent is utilized to further promote low rank in TRP. The TRP trained network inherently has a low-rank structure, and is approximated with negligible performance loss, thus eliminating the fine-tuning process after low rank decomposition. The proposed method is comprehensively evaluated on CIFAR-10 and ImageNet, outperforming previous compression methods using low rank approximation., Comment: Accepted by IJCAI2020, An extension version of arXiv:1812.02402

In this paper, we address several inadequacies of current video object segmentation pipelines. Firstly, a cyclic mechanism is incorporated to the standard semi-supervised process to produce more robust representations. By relying on the accurate reference mask in the starting frame, we show that the error propagation problem can be mitigated. Next, we introduce a simple gradient correction module, which extends the offline pipeline to an online method while maintaining the efficiency of the former. Finally we develop cycle effective receptive field (cycle-ERF) based on gradient correction to provide a new perspective into analyzing object-specific regions of interests. We conduct comprehensive experiments on challenging benchmarks of DAVIS17 and Youtube-VOS, demonstrating that the cyclic mechanism is beneficial to segmentation quality., Comment: 13 pages, 10 figures

The task of spatial-temporal action detection has attracted increasing attention among researchers. Existing dominant methods solve this problem by relying on short-term information and dense serial-wise detection on each individual frames or clips. Despite their effectiveness, these methods showed inadequate use of long-term information and are prone to inefficiency. In this paper, we propose for the first time, an efficient framework that generates action tube proposals from video streams with a single forward pass in a sparse-to-dense manner. There are two key characteristics in this framework: (1) Both long-term and short-term sampled information are explicitly utilized in our spatiotemporal network, (2) A new dynamic feature sampling module (DTS) is designed to effectively approximate the tube output while keeping the system tractable. We evaluate the efficacy of our model on the UCF101-24, JHMDB-21 and UCFSports benchmark datasets, achieving promising results that are competitive to state-of-the-art methods. The proposed sparse-to-dense strategy rendered our framework about 7.6 times more efficient than the nearest competitor., Comment: 5 figures; AAAI 2020

Most current pipelines for spatio-temporal action localization connect frame-wise or clip-wise detection results to generate action proposals, where only local information is exploited and the efficiency is hindered by dense per-frame localization. In this paper, we propose Coarse-to-Fine Action Detector (CFAD),an original end-to-end trainable framework for efficient spatio-temporal action localization. The CFAD introduces a new paradigm that first estimates coarse spatio-temporal action tubes from video streams, and then refines the tubes' location based on key timestamps. This concept is implemented by two key components, the Coarse and Refine Modules in our framework. The parameterized modeling of long temporal information in the Coarse Module helps obtain accurate initial tube estimation, while the Refine Module selectively adjusts the tube location under the guidance of key timestamps. Against other methods, theproposed CFAD achieves competitive results on action detection benchmarks of UCF101-24, UCFSports and JHMDB-21 with inference speed that is 3.3x faster than the nearest competitors., Comment: 7 figures, 3 tables; ECCV2020

Mengyuan Liu,1,2 Fangfang Fan,1,2 Bo Liu,1,2 Jia Jia,1,2 Yimeng Jiang,1,2 Pengfei Sun,1,2 Danmei He,1,2 Jiahui Liu,1,2 Yuxi Li,1,2 Yong Huo,1,2 Jianping Li,1,2 Yan Zhang1,2 1Department of Cardiology, Peking University First Hospital, Beijing, People’s Republic of China; 2Institute of Cardiovascular Disease, Peking University First Hospital, Beijing, People’s Republic of ChinaCorrespondence: Yan Zhang; Jianping Li Tel +86 10 83575262; +86 10 83575728Fax +86 10 66551383Email drzhy1108@163.com; lijianping03455@pkufh.comPurpose: Hyperhomocysteinemia is an independent risk factor for cardio- and cerebrovascular diseases. However, the relationship between plasma homocysteine (Hcy) concentration and peripheral arterial disease (PAD) has not been completely characterized. The aim of the present study was to determine the relationship between plasma Hcy concentration and new-onset PAD and to assess the effects of combinations of Hcy and traditional cardiovascular risk factors.Patients and Methods: We conducted a prospective community-based cohort study of 3119 Chinese participants who did not have PAD at baseline, with a median follow-up period of 2.30 years. We used multivariate logistic regression models to evaluate the relationship between high Hcy (≥ 10μmol/L) and new-onset PAD. The effects of combinations of high Hcy and traditional cardiovascular risk factors were assessed using logistic regression analysis.Results: After adjustment for 14 covariates, high Hcy concentration was significantly associated with new-onset PAD (odds ratio [OR]=2.08, 95% confidence interval [CI]: 1.08– 4.03, P=0.030). Smokers with high Hcy concentration were substantially more likely to have new-onset PAD than non-smokers with normal Hcy concentration (OR=4.44, 95% CI: 1.77– 11.12, P=0.001). The effect of diabetes on PAD became significant when present in combination with high Hcy concentration (OR=3.67, 95% CI: 1.25– 10.80, P=0.