Search

Sihan Yan,1,2,* Dan Du,1,2,* Xu Liu,1,2 Yingying Dai,1,2 Min-Kyu Kim,1,2 Xinyu Zhou,3 Lian Wang,1,2 Lu Zhang,1,2 Xian Jiang1,2 1Department of Dermatology, West China Hospital, Sichuan University, Chengdu, People’s Republic of China; 2Laboratory of Dermatology, Clinical Institute of Inflammation and Immunology, Frontiers Science Center for Disease-Related Molecular Network, West China Hospital, Sichuan University, Chengdu, People’s Republic of China; 3Department of Dermatology, Nanbu County People’s Hospital, Nanbu County, Nanchong, Sichuan, People’s Republic of China*These authors contributed equally to this workCorrespondence: Xian Jiang; Lu Zhang, Email jiangxian@scu.edu.cn; zhangluhx@scu.edu.cnObjective: Artificial intelligence chatbot, particularly ChatGPT (Chat Generative Pre-trained Transformer), is capable of analyzing human input and generating human-like responses, which shows its potential application in healthcare. People with rosacea often have questions about alleviating symptoms and daily skin-care, which is suitable for ChatGPT to response. This study aims to assess the reliability and clinical applicability of ChatGPT 3.5 in responding to patients’ common queries about rosacea and to evaluate the extent of ChatGPT’s coverage in dermatology resources.Methods: Based on a qualitative analysis of the literature on the queries from rosacea patients, we have extracted 20 questions of patients’ greatest concerns, covering four main categories: treatment, triggers and diet, skincare, and special manifestations of rosacea. Each question was inputted into ChatGPT separately for three rounds of question-and-answer conversations. The generated answers will be evaluated by three experienced dermatologists with postgraduate degrees and over five years of clinical experience in dermatology, to assess their reliability and applicability for clinical practice.Results: The analysis results indicate that the reviewers unanimously a

Xu Zeng,1,2 Xianjie Zhang,2 Wencai Jiang,2,&ast; Xinyu Zhou1,&ast; 1Department of Anaesthesiology, Chengdu Medical College, Chengdu, People’s Republic of China; 2Department of Anesthesiology, People’s Hospital of Deyang City, Deyang, People’s Republic of China&ast;These authors contributed equally to this workCorrespondence: Xianjie Zhang, Department of Anesthesiology, People’s Hospital of Deyang City, Deyang, People’s Republic of China, Email zxianjiemazui@163.comPurpose: Investigating the efficacy of intraoperative fractionated intravenous esketamine in the prevention of rebound pain after cessation of thoracic paravertebral nerve blockade.Methods: One hundred and twenty patients who underwent elective thoracoscopic lobectomy were selected for the study and were randomly divided into two groups, the esketamine group was given 0.5 mg/kg and 0.3 mg/kg of esketamine at the induction of anaesthesia and 30 minutes before the end of the operation, respectively, and the control group was given an equal amount of saline. The incidence of rebound pain (RP) 7 days after surgery and postoperative recovery were compared between the two groups.Results: The NRS pain scores at 24 and 48 hours postoperatively in the esketamine group were significantly lower than those in the control group (P < 0.05). The incidence of postoperative rebound pain was significantly lower in the esketamine group than in the control group (P < 0.05). The consumption of sufentanil was less in the esketamine group in the postoperative 48 hours (P < 0.05). Postoperative recovery was compared between the two groups and the difference was not statistically significant.Conclusion: Intravenous esketamine reduces postoperative pain scores, decreases the incidence of rebound pain after cessation of thoracic paravertebral block, and reduces opioid consumption.Keywords: esketamine, rebound pain, paravertebral nerve block, postoperative pain

Crowd navigation has received significant research attention in recent years, especially DRL-based methods. While single-robot crowd scenarios have dominated research, they offer limited applicability to real-world complexities. The heterogeneity of interaction among multiple agent categories, like in decentralized multi-robot pedestrian scenarios, are frequently disregarded. This "interaction blind spot" hinders generalizability and restricts progress towards robust navigation algorithms. In this paper, we propose a heterogeneous relational deep reinforcement learning(HeR-DRL), based on customised heterogeneous GNN, in order to improve navigation strategies in decentralized multi-robot crowd navigation. Firstly, we devised a method for constructing robot-crowd heterogenous relation graph that effectively simulates the heterogeneous pair-wise interaction relationships. We proposed a new heterogeneous graph neural network for transferring and aggregating the heterogeneous state information. Finally, we incorporate the encoded information into deep reinforcement learning to explore the optimal policy. HeR-DRL are rigorously evaluated through comparing it to state-of-the-art algorithms in both single-robot and multi-robot circle crowssing scenario. The experimental results demonstrate that HeR-DRL surpasses the state-of-the-art approaches in overall performance, particularly excelling in safety and comfort metrics. This underscores the significance of interaction heterogeneity for crowd navigation. The source code will be publicly released in https://github.com/Zhouxy-Debugging-Den/HeR-DRL.

Visual object tracking aims to localize the target object of each frame based on its initial appearance in the first frame. Depending on the input modility, tracking tasks can be divided into RGB tracking and RGB+X (e.g. RGB+N, and RGB+D) tracking. Despite the different input modalities, the core aspect of tracking is the temporal matching. Based on this common ground, we present a general framework to unify various tracking tasks, termed as OneTracker. OneTracker first performs a large-scale pre-training on a RGB tracker called Foundation Tracker. This pretraining phase equips the Foundation Tracker with a stable ability to estimate the location of the target object. Then we regard other modality information as prompt and build Prompt Tracker upon Foundation Tracker. Through freezing the Foundation Tracker and only adjusting some additional trainable parameters, Prompt Tracker inhibits the strong localization ability from Foundation Tracker and achieves parameter-efficient finetuning on downstream RGB+X tracking tasks. To evaluate the effectiveness of our general framework OneTracker, which is consisted of Foundation Tracker and Prompt Tracker, we conduct extensive experiments on 6 popular tracking tasks across 11 benchmarks and our OneTracker outperforms other models and achieves state-of-the-art performance., Comment: Accepted to CVPR 2024

Contemporary Video Object Segmentation (VOS) approaches typically consist stages of feature extraction, matching, memory management, and multiple objects aggregation. Recent advanced models either employ a discrete modeling for these components in a sequential manner, or optimize a combined pipeline through substructure aggregation. However, these existing explicit staged approaches prevent the VOS framework from being optimized as a unified whole, leading to the limited capacity and suboptimal performance in tackling complex videos. In this paper, we propose OneVOS, a novel framework that unifies the core components of VOS with All-in-One Transformer. Specifically, to unify all aforementioned modules into a vision transformer, we model all the features of frames, masks and memory for multiple objects as transformer tokens, and integrally accomplish feature extraction, matching and memory management of multiple objects through the flexible attention mechanism. Furthermore, a Unidirectional Hybrid Attention is proposed through a double decoupling of the original attention operation, to rectify semantic errors and ambiguities of stored tokens in OneVOS framework. Finally, to alleviate the storage burden and expedite inference, we propose the Dynamic Token Selector, which unveils the working mechanism of OneVOS and naturally leads to a more efficient version of OneVOS. Extensive experiments demonstrate the superiority of OneVOS, achieving state-of-the-art performance across 7 datasets, particularly excelling in complex LVOS and MOSE datasets with 70.1% and 66.4% $J \& F$ scores, surpassing previous state-of-the-art methods by 4.2% and 7.0%, respectively. And our code will be available for reproducibility and further research., Comment: 19 pages, 7 figures

Reliable hand mesh reconstruction (HMR) from commonly-used color and depth sensors is challenging especially under scenarios with varied illuminations and fast motions. Event camera is a highly promising alternative for its high dynamic range and dense temporal resolution properties, but it lacks key texture appearance for hand mesh reconstruction. In this paper, we propose EvRGBHand -- the first approach for 3D hand mesh reconstruction with an event camera and an RGB camera compensating for each other. By fusing two modalities of data across time, space, and information dimensions,EvRGBHand can tackle overexposure and motion blur issues in RGB-based HMR and foreground scarcity and background overflow issues in event-based HMR. We further propose EvRGBDegrader, which allows our model to generalize effectively in challenging scenes, even when trained solely on standard scenes, thus reducing data acquisition costs. Experiments on real-world data demonstrate that EvRGBHand can effectively solve the challenging issues when using either type of camera alone via retaining the merits of both, and shows the potential of generalization to outdoor scenes and another type of event camera.

Video Object Segmentation (VOS) task aims to segment objects in videos. However, previous settings either require time-consuming manual masks of target objects at the first frame during inference or lack the flexibility to specify arbitrary objects of interest. To address these limitations, we propose the setting named Click Video Object Segmentation (ClickVOS) which segments objects of interest across the whole video according to a single click per object in the first frame. And we provide the extended datasets DAVIS-P and YouTubeVOSP that with point annotations to support this task. ClickVOS is of significant practical applications and research implications due to its only 1-2 seconds interaction time for indicating an object, comparing annotating the mask of an object needs several minutes. However, ClickVOS also presents increased challenges. To address this task, we propose an end-to-end baseline approach named called Attention Before Segmentation (ABS), motivated by the attention process of humans. ABS utilizes the given point in the first frame to perceive the target object through a concise yet effective segmentation attention. Although the initial object mask is possibly inaccurate, in our ABS, as the video goes on, the initially imprecise object mask can self-heal instead of deteriorating due to error accumulation, which is attributed to our designed improvement memory that continuously records stable global object memory and updates detailed dense memory. In addition, we conduct various baseline explorations utilizing off-the-shelf algorithms from related fields, which could provide insights for the further exploration of ClickVOS. The experimental results demonstrate the superiority of the proposed ABS approach. Extended datasets and codes will be available at https://github.com/PinxueGuo/ClickVOS.

A polarization camera can capture four polarized images with different polarizer angles in a single shot, which is useful in polarization-based vision applications since the degree of polarization (DoP) and the angle of polarization (AoP) can be directly computed from the captured polarized images. However, since the on-chip micro-polarizers block part of the light so that the sensor often requires a longer exposure time, the captured polarized images are prone to motion blur caused by camera shakes, leading to noticeable degradation in the computed DoP and AoP. Deblurring methods for conventional images often show degenerated performance when handling the polarized images since they only focus on deblurring without considering the polarization constrains. In this paper, we propose a polarized image deblurring pipeline to solve the problem in a polarization-aware manner by adopting a divide-and-conquer strategy to explicitly decompose the problem into two less ill-posed sub-problems, and design a two-stage neural network to handle the two sub-problems respectively. Experimental results show that our method achieves state-of-the-art performance on both synthetic and real-world images, and can improve the performance of polarization-based vision applications such as image dehazing and reflection removal.

We initiate a systematic study of worst-group risk minimization under $(\epsilon, \delta)$-differential privacy (DP). The goal is to privately find a model that approximately minimizes the maximal risk across $p$ sub-populations (groups) with different distributions, where each group distribution is accessed via a sample oracle. We first present a new algorithm that achieves excess worst-group population risk of $\tilde{O}(\frac{p\sqrt{d}}{K\epsilon} + \sqrt{\frac{p}{K}})$, where $K$ is the total number of samples drawn from all groups and $d$ is the problem dimension. Our rate is nearly optimal when each distribution is observed via a fixed-size dataset of size $K/p$. Our result is based on a new stability-based analysis for the generalization error. In particular, we show that $\Delta$-uniform argument stability implies $\tilde{O}(\Delta + \frac{1}{\sqrt{n}})$ generalization error w.r.t. the worst-group risk, where $n$ is the number of samples drawn from each sample oracle. Next, we propose an algorithmic framework for worst-group population risk minimization using any DP online convex optimization algorithm as a subroutine. Hence, we give another excess risk bound of $\tilde{O}\left( \sqrt{\frac{d^{1/2}}{\epsilon K}} +\sqrt{\frac{p}{K\epsilon^2}} \right)$. Assuming the typical setting of $\epsilon=\Theta(1)$, this bound is more favorable than our first bound in a certain range of $p$ as a function of $K$ and $d$. Finally, we study differentially private worst-group empirical risk minimization in the offline setting, where each group distribution is observed by a fixed-size dataset. We present a new algorithm with nearly optimal excess risk of $\tilde{O}(\frac{p\sqrt{d}}{K\epsilon})$.

Reference features from a template or historical frames are crucial for visual object tracking. Prior works utilize all features from a fixed template or memory for visual object tracking. However, due to the dynamic nature of videos, the required reference historical information for different search regions at different time steps is also inconsistent. Therefore, using all features in the template and memory can lead to redundancy and impair tracking performance. To alleviate this issue, we propose a novel tracking paradigm, consisting of a relevance attention mechanism and a global representation memory, which can adaptively assist the search region in selecting the most relevant historical information from reference features. Specifically, the proposed relevance attention mechanism in this work differs from previous approaches in that it can dynamically choose and build the optimal global representation memory for the current frame by accessing cross-frame information globally. Moreover, it can flexibly read the relevant historical information from the constructed memory to reduce redundancy and counteract the negative effects of harmful information. Extensive experiments validate the effectiveness of the proposed method, achieving competitive performance on five challenging datasets with 71 FPS., Comment: 9pages,5 figures, accepted by the Thirty-seventh Conference on Neural Information Processing Systems(Neurips 2023)

Recent advancements in large language models (LLMs) such as ChatGPT and LLaMA have hinted at their potential to revolutionize medical applications, yet their application in clinical settings often reveals limitations due to a lack of specialized training on medical-specific data. In response to this challenge, this study introduces Me-LLaMA, a novel medical LLM family that includes foundation models - Me-LLaMA 13/70B, along with their chat-enhanced versions - Me-LLaMA 13/70B-chat, developed through continual pre-training and instruction tuning of LLaMA2 using large medical datasets. Our methodology leverages a comprehensive domain-specific data suite, including a large-scale, continual pre-training dataset with 129B tokens, an instruction tuning dataset with 214k samples, and a new medical evaluation benchmark (MIBE) across six critical medical tasks with 12 datasets. Our extensive evaluation using the MIBE shows that Me-LLaMA models achieve overall better performance than existing open-source medical LLMs in zero-shot, few-shot and supervised learning abilities. With task-specific instruction tuning, Me-LLaMA models outperform ChatGPT on 7 out of 8 datasets and GPT-4 on 5 out of 8 datasets. In addition, we investigated the catastrophic forgetting problem, and our results show that Me-LLaMA models outperform other open-source medical LLMs in mitigating this issue. Me-LLaMA is one of the largest open-source medical foundation LLMs that use both biomedical and clinical data. It exhibits superior performance across both general and medical tasks compared to other open-source medical LLMs, rendering it an attractive choice for medical AI applications. We release our models, datasets, and evaluation scripts at: https://github.com/BIDS-Xu-Lab/Me-LLaMA., Comment: 21 pages, 3 figures, 8 tables

A good initialization of deep learning models is essential since it can help them converge better and faster. However, pretraining large models is unaffordable for many researchers, which makes a desired prediction for initial parameters more necessary nowadays. Graph HyperNetworks (GHNs), one approach to predicting model parameters, have recently shown strong performance in initializing large vision models. Unfortunately, predicting parameters of very wide networks relies on copying small chunks of parameters multiple times and requires an extremely large number of parameters to support full prediction, which greatly hinders its adoption in practice. To address this limitation, we propose LoGAH (Low-rank GrAph Hypernetworks), a GHN with a low-rank parameter decoder that expands to significantly wider networks without requiring as excessive increase of parameters as in previous attempts. LoGAH allows us to predict the parameters of 774-million large neural networks in a memory-efficient manner. We show that vision and language models (i.e., ViT and GPT-2) initialized with LoGAH achieve better performance than those initialized randomly or using existing hypernetworks. Furthermore, we show promising transfer learning results w.r.t. training LoGAH on small datasets and using the predicted parameters to initialize for larger tasks. We provide the codes in https://github.com/Blackzxy/LoGAH ., Comment: 16 pages

Video object segmentation (VOS) aims to distinguish and track target objects in a video. Despite the excellent performance achieved by off-the-shell VOS models, existing VOS benchmarks mainly focus on short-term videos lasting about 5 seconds, where objects remain visible most of the time. However, these benchmarks poorly represent practical applications, and the absence of long-term datasets restricts further investigation of VOS in realistic scenarios. Thus, we propose a novel benchmark named LVOS, comprising 720 videos with 296,401 frames and 407,945 high-quality annotations. Videos in LVOS last 1.14 minutes on average, approximately 5 times longer than videos in existing datasets. Each video includes various attributes, especially challenges deriving from the wild, such as long-term reappearing and cross-temporal similar objects. Compared to previous benchmarks, our LVOS better reflects VOS models' performance in real scenarios. Based on LVOS, we evaluate 20 existing VOS models under 4 different settings and conduct a comprehensive analysis. On LVOS, these models suffer a large performance drop, highlighting the challenge of achieving precise tracking and segmentation in real-world scenarios. Attribute-based analysis indicates that key factor to accuracy decline is the increased video length, emphasizing LVOS's crucial role. We hope our LVOS can advance development of VOS in real scenes. Data and code are available at https://lingyihongfd.github.io/lvos.github.io/., Comment: LVOS V2

Tumor necrosis factor (TNF)-related apoptosis-inducing ligand (TRAIL) is a promising candidate for cancer treatment due to its tumor specificity. TRAIL binds with death receptor (DR) 4 or 5 to initiate apoptotic signal transduction. In this thesis, we first introduced the protein engineering strategies of TNF ligands to target specific receptors and we reviewed the changes in the biological activity of some key ligands. In the experimental part, we worked with DR4-specific TRAIL variant 4C7 and DR5-specific TRAIL variant DHER to study combination treatments to overcome resistance. Artemisinin is an approved anti-malarial drug extracted from Artemisia annua, which has also been studied as an anti-tumor drug for decades. We showed that artemisinin-type drugs stimulate DR5-specific TRAIL-induced apoptosis by regulating wildtype P53 in colon cancer cells. Then, we investigated the possibility of performing this combination treatment in P53 mutated triple-negative breast cancer (TNBC) cells. The effectiveness of dihydroartemisinin (DHA) was improved by forming adducts with transferrin (TF). These DHA-TF adducts induce apoptosis and ferroptosis in TNBC cells. Meanwhile, they enhance TRAIL-induced apoptosis mainly through DR5 upregulation in a P53-independent and ROS-dependent manner. Based on our findings and literature research, we summarized the effects of artemisinin-type drugs on regulated cell death pathways, the combination strategies with biologics, and the nanocarriers for artemisinin delivery. Finally, the expression pattern of DR4 and DR5 and the influence of ionizing radiation on receptor-specific TRAIL in 2D and 3D spheroids were explored. The whole thesis provided new strategies to enhance receptor-specific TRAIL-induced apoptosis for cancer treatment.

Xu Liu,1,2,&ast; Min-Kyu Kim,1,2,&ast; Dan Du,1,2 Xinyu Zhou,1,2 Lian Wang,1,2 Xian Jiang1,2 1Department of Dermatology, West China Hospital, Sichuan University, Chengdu, People’s Republic of China; 2Laboratory of Dermatology, Clinical Institute of Inflammation and Immunology, Frontiers Science Center for Disease-Related Molecular Network, West China Hospital, Sichuan University, Chengdu, People’s Republic of China&ast;These authors contributed equally to this workCorrespondence: Lian Wang; Xian Jiang, Department of Dermatology, West China Hospital, Sichuan University, &num;37 Guoxue Alley, Wuhou District, Chengdu, Sichuan, 610041, People’s Republic of China, Tel +86-28-85423315, Fax +86-28-85422560, Email wanglian8225@scu.edu.cn; jiangxian@scu.edu.cnObjective: To retrospectively analyze the factors influencing the treatment of rosacea patients with regular follow-up by self-management support in the new media chronic disease management model, to explore the effect of self-management support and to provide an objective basis for clinical application.Methods: Female patients with rosacea who were regularly followed up for more than 6 months at the rosacea follow-up clinic of the Department of Dermatology, West China Hospital, Sichuan University, from March 2022 to June 2023, with erythema and capillary dilation as the main clinical phenotype, met the rosacea diagnostic criteria of the American Rosacea Expert Committee 2017 edition, and received medications recommended by the Chinese Rosacea Treatment Guidelines (2021 edition). A total of 125 patients were treated with combined photobiomodulation therapy (PBMT), and the patients were divided into a standardized group (CEA< 1, IGA< 1) and a non-standardized group (CEA≥ 1, IGA≥ 1) based on significant rosacea efficacy (CEA< 1, IGA< 1) within 6 months. The age, gender, education level, duration of rosacea, treatment regimen, education intensity, CEA, and IGA baseline data were compar

The Metaverse, an emerging digital space, is expected to offer various services mirroring the real world. Wireless communications for mobile Metaverse users should be tailored to meet the following user characteristics: 1) emphasizing application-specific perceptual utility instead of simply the transmission rate, 2) concerned with energy efficiency due to the limited device battery and energy intensiveness of some applications, and 3) caring about security as the applications may involve sensitive personal data. To this end, this paper incorporates application-specific utility, energy efficiency, and physical-layer security (PLS) into the studied optimization in a wireless network for the Metaverse. Specifically, after introducing utility-energy efficiency (UEE) to represent each Metaverse user's application-specific objective under PLS, we formulate an optimization to maximize the network's weighted sum-UEE by deciding users' transmission powers and communication bandwidths. The formulated problem belongs to the sum-of-ratios optimization, for which prior studies have demonstrated its difficulty. Nevertheless, our proposed algorithm 1) obtains the global optimum for the weighted sum-UEE optimization, via a transform to parametric convex optimization problems, 2) applies to any utility function which is concave, increasing, and twice differentiable, and 3) achieves a linear time complexity in the number of users (the optimal complexity in the order sense). Simulations confirm the superiority of our algorithm over other approaches. We explain that our technique for solving the sum-of-ratios optimization is applicable to other optimization problems in wireless networks and mobile computing.

Metaverse has become a buzzword recently. Mobile augmented reality (MAR) is a promising approach to providing users with an immersive experience in the Metaverse. However, due to limitations of bandwidth, latency and computational resources, MAR cannot be applied on a large scale in the Metaverse yet. Moreover, federated learning, with its privacy-preserving characteristics, has emerged as a prospective distributed learning framework in the future Metaverse world. In this paper, we propose a federated learning assisted MAR system via non-orthogonal multiple access for the Metaverse. Additionally, to optimize a weighted sum of energy, latency and model accuracy, a resource allocation algorithm is devised by setting appropriate transmission power, CPU frequency and video frame resolution for each user. Experimental results demonstrate that our proposed algorithm achieves an overall good performance compared to a random algorithm and greedy algorithm., Comment: This paper appears in the Proceedings of IEEE International Conference on Communications (ICC) 2023. Please feel free to contact us for questions or remarks

This paper explores the potential of constructing an AI spoken dialogue system that "thinks how to respond" and "thinks how to speak" simultaneously, which more closely aligns with the human speech production process compared to the current cascade pipeline of independent chatbot and Text-to-Speech (TTS) modules. We hypothesize that Large Language Models (LLMs) with billions of parameters possess significant speech understanding capabilities and can jointly model dialogue responses and linguistic features. We conduct two sets of experiments: 1) Prosodic structure prediction, a typical front-end task in TTS, demonstrating the speech understanding ability of LLMs, and 2) Further integrating dialogue response and a wide array of linguistic features using a unified encoding format. Our results indicate that the LLM-based approach is a promising direction for building unified spoken dialogue systems.

Event cameras and RGB cameras exhibit complementary characteristics in imaging: the former possesses high dynamic range (HDR) and high temporal resolution, while the latter provides rich texture and color information. This makes the integration of event cameras into middle- and high-level RGB-based vision tasks highly promising. However, challenges arise in multi-modal fusion, data annotation, and model architecture design. In this paper, we propose EvPlug, which learns a plug-and-play event and image fusion module from the supervision of the existing RGB-based model. The learned fusion module integrates event streams with image features in the form of a plug-in, endowing the RGB-based model to be robust to HDR and fast motion scenes while enabling high temporal resolution inference. Our method only requires unlabeled event-image pairs (no pixel-wise alignment required) and does not alter the structure or weights of the RGB-based model. We demonstrate the superiority of EvPlug in several vision tasks such as object detection, semantic segmentation, and 3D hand pose estimation

Semantic communication is deemed as a revolution of Shannon's paradigm in the six-generation (6G) wireless networks. It aims at transmitting the extracted information rather than the original data, which receivers will try to recover. Intuitively, the larger extracted information, the longer latency of semantic communication will be. Besides, larger extracted information will result in more accurate reconstructed information, thereby causing a higher utility of the semantic communication system. Shorter latency and higher utility are desirable objectives for the system, so there will be a trade-off between utility and latency. This paper proposes a joint optimization algorithm for total latency and utility. Moreover, security is essential for the semantic communication system. We incorporate the secrecy rate, a physical-layer security method, into the optimization problem. The secrecy rate is the communication rate at which no information is disclosed to an eavesdropper. Experimental results demonstrate that the proposed algorithm obtains the best joint optimization performance compared to the baselines., Comment: This paper appears in IEEE Global Communications Conference (GLOBECOM) 2023

Scene graph generation (SGG) aims to automatically map an image into a semantic structural graph for better scene understanding. It has attracted significant attention for its ability to provide object and relation information, enabling graph reasoning for downstream tasks. However, it faces severe limitations in practice due to the biased data and training method. In this paper, we present a more rational and effective strategy based on causal inference for object relation prediction. To further evaluate the superiority of our strategy, we propose an object enhancement module to conduct ablation studies. Experimental results on the Visual Gnome 150 (VG-150) dataset demonstrate the effectiveness of our proposed method. These contributions can provide great potential for foundation models for decision-making.

This paper explores the potential of constructing an AI spoken dialogue system that "thinks how to respond" and "thinks how to speak" simultaneously, which more closely aligns with the human speech production process compared to the current cascade pipeline of independent chatbot and Text-to-Speech (TTS) modules. We hypothesize that Large Language Models (LLMs) with billions of parameters possess significant speech understanding capabilities and can jointly model dialogue responses and linguistic features. We conduct two sets of experiments: 1) Prosodic structure prediction, a typical front-end task in TTS, demonstrating the speech understanding ability of LLMs, and 2) Further integrating dialogue response and a wide array of linguistic features using a unified encoding format. Our results indicate that the LLM-based approach is a promising direction for building unified spoken dialogue systems.

Automatic few-shot font generation (AFFG), aiming at generating new fonts with only a few glyph references, reduces the labor cost of manually designing fonts. However, the traditional AFFG paradigm of style-content disentanglement cannot capture the diverse local details of different fonts. So, many component-based approaches are proposed to tackle this problem. The issue with component-based approaches is that they usually require special pre-defined glyph components, e.g., strokes and radicals, which is infeasible for AFFG of different languages. In this paper, we present a novel font generation approach by aggregating styles from character similarity-guided global features and stylized component-level representations. We calculate the similarity scores of the target character and the referenced samples by measuring the distance along the corresponding channels from the content features, and assigning them as the weights for aggregating the global style features. To better capture the local styles, a cross-attention-based style transfer module is adopted to transfer the styles of reference glyphs to the components, where the components are self-learned discrete latent codes through vector quantization without manual definition. With these designs, our AFFG method could obtain a complete set of component-level style representations, and also control the global glyph characteristics. The experimental results reflect the effectiveness and generalization of the proposed method on different linguistic scripts, and also show its superiority when compared with other state-of-the-art methods. The source code can be found at https://github.com/awei669/VQ-Font., Comment: Accepted by ICCV 2023

Grasping objects is a fundamental yet important capability of robots, and many tasks such as sorting and picking rely on this skill. The prerequisite for stable grasping is the ability to correctly identify suitable grasping positions. However, finding appropriate grasping points is challenging due to the diverse shapes, varying density distributions, and significant differences between the barycenter of various objects. In the past few years, researchers have proposed many methods to address the above-mentioned issues and achieved very good results on publicly available datasets such as the Cornell dataset and the Jacquard dataset. The problem is that the backgrounds of Cornell and Jacquard datasets are relatively simple - typically just a whiteboard, while in real-world operational environments, the background could be complex and noisy. Moreover, in real-world scenarios, robots usually only need to grasp fixed types of objects. To address the aforementioned issues, we proposed a large-scale grasp detection dataset called NBMOD: Noisy Background Multi-Object Dataset for grasp detection, which consists of 31,500 RGB-D images of 20 different types of fruits. Accurate prediction of angles has always been a challenging problem in the detection task of oriented bounding boxes. This paper presents a Rotation Anchor Mechanism (RAM) to address this issue. Considering the high real-time requirement of robotic systems, we propose a series of lightweight architectures called RA-GraspNet (GraspNet with Rotation Anchor): RARA (network with Rotation Anchor and Region Attention), RAST (network with Rotation Anchor and Semi Transformer), and RAGT (network with Rotation Anchor and Global Transformer) to tackle this problem. Among them, the RAGT-3/3 model achieves an accuracy of 99% on the NBMOD dataset. The NBMOD and our code are available at https://github.com/kmittle/Grasp-Detection-NBMOD.

The Metaverse is deemed the next evolution of the Internet and has received much attention recently. Metaverse applications via mobile augmented reality (MAR) require rapid and accurate object detection to mix digital data with the real world. As mobile devices evolve, their computational capabilities are increasing, and thus their computational resources can be leveraged to train machine learning models. In light of the increasing concerns of user privacy and data security, federated learning (FL) has become a promising distributed learning framework for privacy-preserving analytics. In this article, FL and MAR are brought together in the Metaverse. We discuss the necessity and rationality of the combination of FL and MAR. The prospective technologies that support FL and MAR in the Metaverse are also discussed. In addition, existing challenges that prevent the fulfillment of FL and MAR in the Metaverse and several application scenarios are presented. Finally, three case studies of Metaverse FL-MAR systems are demonstrated.

The Metaverse has received much attention recently. Metaverse applications via mobile augmented reality (MAR) require rapid and accurate object detection to mix digital data with the real world. Federated learning (FL) is an intriguing distributed machine learning approach due to its privacy-preserving characteristics. Due to privacy concerns and the limited computation resources on mobile devices, we incorporate FL into MAR systems of the Metaverse to train a model cooperatively. Besides, to balance the trade-off between energy, execution latency and model accuracy, thereby accommodating different demands and application scenarios, we formulate an optimization problem to minimize a weighted combination of total energy consumption, completion time and model accuracy. Through decomposing the non-convex optimization problem into two subproblems, we devise a resource allocation algorithm to determine the bandwidth allocation, transmission power, CPU frequency and video frame resolution for each participating device. We further present the convergence analysis and computational complexity of the proposed algorithm. Numerical results show that our proposed algorithm has better performance (in terms of energy consumption, completion time and model accuracy) under different weight parameters compared to existing benchmarks., Comment: This paper appears in IEEE Transactions on Wireless Communications. DOI: https://doi.org/10.1109/TWC.2023.3326884 It is the journal version of 2022 IEEE 42nd International Conference on Distributed Computing Systems (ICDCS) paper: arXiv:2209.14900; i.e., https://doi.org/10.1109/ICDCS54860.2022.00101

Federated Learning (FL) is an intriguing distributed machine learning approach due to its privacy-preserving characteristics. To balance the trade-off between energy and execution latency, and thus accommodate different demands and application scenarios, we formulate an optimization problem to minimize a weighted sum of total energy consumption and completion time through two weight parameters. The optimization variables include bandwidth, transmission power and CPU frequency of each device in the FL system, where all devices are linked to a base station and train a global model collaboratively. Through decomposing the non-convex optimization problem into two subproblems, we devise a resource allocation algorithm to determine the bandwidth allocation, transmission power, and CPU frequency for each participating device. We further present the convergence analysis and computational complexity of the proposed algorithm. Numerical results show that our proposed algorithm not only has better performance at different weight parameters (i.e., different demands) but also outperforms the state of the art., Comment: This paper appears in the Proceedings of IEEE International Conference on Distributed Computing Systems (ICDCS) 2022. Please feel free to contact us for questions or remarks

Although CLIP-like Visual Language Models provide a functional joint feature space for image and text, due to the limitation of the CILP-like model's image input size (e.g., 224), subtle details are lost in the feature representation if we input high-resolution images (e.g., 2240). In this work, we introduce an efficient framework that can produce a single feature representation for a high-resolution image that injects image details and shares the same semantic space as the original CLIP. In the framework, we train a feature fusing model based on CLIP features extracted from a carefully designed image patch method that can cover objects of any scale, weakly supervised by image-agnostic class prompted queries. We validate our framework by retrieving images from class prompted queries on the real world and synthetic datasets, showing significant performance improvement on these tasks. Furthermore, to fully demonstrate our framework's detail retrieval ability, we construct a CLEVR-like synthetic dataset called CLVER-DS, which is fully annotated and has a controllable object scale.

Tumor necrosis factor (TNF)-related apoptosis-inducing ligand (TRAIL) is a promising candidate for cancer treatment due to its tumor specificity. TRAIL binds with death receptor (DR) 4 or 5 to initiate apoptotic signal transduction. In this thesis, we first introduced the protein engineering strategies of TNF ligands to target specific receptors and we reviewed the changes in the biological activity of some key ligands. In the experimental part, we worked with DR4-specific TRAIL variant 4C7 and DR5-specific TRAIL variant DHER to study combination treatments to overcome resistance. Artemisinin is an approved anti-malarial drug extracted from Artemisia annua, which has also been studied as an anti-tumor drug for decades. We showed that artemisinin-type drugs stimulate DR5-specific TRAIL-induced apoptosis by regulating wildtype P53 in colon cancer cells. Then, we investigated the possibility of performing this combination treatment in P53 mutated triple-negative breast cancer (TNBC) cells. The effectiveness of dihydroartemisinin (DHA) was improved by forming adducts with transferrin (TF). These DHA-TF adducts induce apoptosis and ferroptosis in TNBC cells. Meanwhile, they enhance TRAIL-induced apoptosis mainly through DR5 upregulation in a P53-independent and ROS-dependent manner. Based on our findings and literature research, we summarized the effects of artemisinin-type drugs on regulated cell death pathways, the combination strategies with biologics, and the nanocarriers for artemisinin delivery. Finally, the expression pattern of DR4 and DR5 and the influence of ionizing radiation on receptor-specific TRAIL in 2D and 3D spheroids were explored. The whole thesis provided new strategies to enhance receptor-specific TRAIL-induced apoptosis for cancer treatment.

Learning using privileged information (LUPI) paradigm, which pioneered teacher-student interaction mechanism, makes the learning models use additional information in training stage. This paper is the first to propose an incremental learning algorithm with LUPI paradigm for stochastic configuration network (SCN), named SCN+. This novel algorithm can leverage privileged information into SCN in the training stage, which provides a new method to train SCN. Moreover, the convergences have been studied in this paper. Finally, experimental results indicate that SCN+ indeed performs favorably.

Although nanorobots have been used as clinical prescriptions for work such as gastroscopy, and even photoacoustic tomography technology has been proposed to control nanorobots to deliver drugs at designated delivery points in real time, and there are cases of eliminating "superbacteria" in blood through nanorobots, most technologies are immature, either with low efficiency or low accuracy, Either it can not be mass produced, so the most effective way to treat cancer diseases at this stage is through chemotherapy and radiotherapy. Patients are suffering and can not be cured. Therefore, this paper proposes an ideal model of a treatment method that can completely cure cancer, a cooperative treatment method based on nano robot queue through team member communication and computer vision image classification (target detection)., Comment: 7pages,2figures

"Pay-per-last-$N$-shares" (PPLNS) is one of the most common payout strategies used by mining pools in Proof-of-Work (PoW) cryptocurrencies. As with any payment scheme, it is imperative to study issues of incentive compatibility of miners within the pool. For PPLNS this question has only been partially answered; we know that reasonably-sized miners within a PPLNS pool prefer following the pool protocol over employing specific deviations. In this paper, we present a novel modification to PPLNS where we randomise the protocol in a natural way. We call our protocol "Randomised pay-per-last-$N$-shares" (RPPLNS), and note that the randomised structure of the protocol greatly simplifies the study of its incentive compatibility. We show that RPPLNS maintains the strengths of PPLNS (i.e., fairness, variance reduction, and resistance to pool hopping), while also being robust against a richer class of strategic mining than what has been shown for PPLNS.

Background: Available evidence on the comparative efficacy and acceptability of psychotherapies for post-traumatic stress disorder (PTSD) in children and adolescents remains uncertain. Objective: We aimed to compare and rank the different types and formats of psychotherapies for PTSD in children and adolescents. Methods: We searched eight databases and other international registers up to 31 December 2020. The pairwise meta-analyses and frequentist network meta-analyses estimated pooled standardised mean differences (SMDs) and ORs with random-effects model. Efficacy at post-treatment and follow-up, acceptability, depressive and anxiety symptoms were measured. Findings: We included 56 randomised controlled trials with 5327 patients comparing 14 different types of psychotherapies and 3 control conditions. For efficacy, cognitive processing therapy (CPT), behavioural therapy (BT), individual trauma-focused cognitive–behavioural therapy (TF-CBT), eye movement desensitisation and reprocessing, and group TF-CBT were significantly superior to all control conditions at post-treatment and follow-up (SMDs between −2.42 and −0.25). Moreover, CPT, BT and individual TF-CBT were more effective than supportive therapy (SMDs between −1.92 and −0.49). Results for depressive and anxiety symptoms were similar to the findings for the primary outcome. Most of the results were rated as ‘moderate’ to ‘very low’ in terms of confidence of evidence. Conclusions: CPT, BT and individual TF-CBT appear to be the best choices of psychotherapy for PTSD in young patients. Other types and different ways of delivering psychological treatment can be alternative options. Clinicians should consider the importance of each outcome and the patients’ preferences in real clinical practice.

Jun Zhou,1 Gonghao Ling,1 Jia Cao,1 Xun Ding,1 Xingnan Liao,1 Meng Wu,2 Xinyu Zhou,3 Haibo Xu,1 QingYun Long1 1Department of Radiology, Zhongnan Hospital of Wuhan University, Wuhan 430071, Hubei, People’s Republic of China; 2Department of Ultrasound, Zhongnan Hospital of Wuhan University, Wuhan 430071, Hubei, People’s Republic of China; 3Department of Radiation and Medical Oncology, Zhongnan Hospital of Wuhan University, Wuhan 430071, Hubei, People’s Republic of ChinaCorrespondence: Haibo Xu; QingYun LongDepartment of Radiology, Zhongnan Hospital of Wuhan University, No. 169 Donghu Road, Wuhan 430071, Hubei, People’s Republic of ChinaTel +86 13545009416; +86 15827339526Email xuhaibo1120@hotmail.com; longqy2005@sina.comBackground: Photothermal therapy (PTT) has great potential application in the treatment of tumors. However, due to the low penetration of near-infrared light (NIR) and the low concentration of nanomaterials in the tumor site, the application of PTT has been limited.Purpose: The objective of this study was to investigate the therapeutic effect of transcatheter intra-arterial infusion of lecithin-modified Bi nanoparticles (Bi-Ln NPs) combined with interventional PTT (IPTT) on hepatocellular carcinoma.Methods: Bi-Ln NPs were prepared by emulsifying the hydrophobic Bi nanoparticles and lecithin, and the photothermal conversion and cytotoxicity of Bi-Ln NPs were then measured by infrared imaging and MTT (3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide) assay, respectively. Twenty-four VX2 hepatic carcinoma rabbits were randomly divided into four groups. Rabbits in group A received Bi-Ln NPs by intra-arterial infusion and NIR laser treatment (IA Bi-Ln NPs + Laser), group B received Bi-Ln NPs by intravenous infusion and NIR laser treatment (IV Bi-Ln NPs + Laser), group C received PBS (phosphate buffer saline) via intra-arterial infusion with NIR laser treatment (IA PBS + Laser), group D received PBS via int

Jun Zhou,1 Gonghao Ling,1 Jia Cao,1 Xun Ding,1 Xingnan Liao,1 Meng Wu,2 Xinyu Zhou,3 Haibo Xu,1 QingYun Long1 1Department of Radiology, Zhongnan Hospital of Wuhan University, Wuhan 430071, Hubei, People’s Republic of China; 2Department of Ultrasound, Zhongnan Hospital of Wuhan University, Wuhan 430071, Hubei, People’s Republic of China; 3Department of Radiation and Medical Oncology, Zhongnan Hospital of Wuhan University, Wuhan 430071, Hubei, People’s Republic of ChinaCorrespondence: Haibo Xu; QingYun LongDepartment of Radiology, Zhongnan Hospital of Wuhan University, No. 169 Donghu Road, Wuhan 430071, Hubei, People’s Republic of ChinaTel +86 13545009416; +86 15827339526Email xuhaibo1120@hotmail.com; longqy2005@sina.comBackground: Photothermal therapy (PTT) has great potential application in the treatment of tumors. However, due to the low penetration of near-infrared light (NIR) and the low concentration of nanomaterials in the tumor site, the application of PTT has been limited.Purpose: The objective of this study was to investigate the therapeutic effect of transcatheter intra-arterial infusion of lecithin-modified Bi nanoparticles (Bi-Ln NPs) combined with interventional PTT (IPTT) on hepatocellular carcinoma.Methods: Bi-Ln NPs were prepared by emulsifying the hydrophobic Bi nanoparticles and lecithin, and the photothermal conversion and cytotoxicity of Bi-Ln NPs were then measured by infrared imaging and MTT (3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide) assay, respectively. Twenty-four VX2 hepatic carcinoma rabbits were randomly divided into four groups. Rabbits in group A received Bi-Ln NPs by intra-arterial infusion and NIR laser treatment (IA Bi-Ln NPs + Laser), group B received Bi-Ln NPs by intravenous infusion and NIR laser treatment (IV Bi-Ln NPs + Laser), group C received PBS (phosphate buffer saline) via intra-arterial infusion with NIR laser treatment (IA PBS + Laser), group D received PBS via int

The pandemic of COVID-19 has caused millions of infections, which has led to a great loss all over the world, socially and economically. Due to the false-negative rate and the time-consuming of the conventional Reverse Transcription Polymerase Chain Reaction (RT-PCR) tests, diagnosing based on X-ray images and Computed Tomography (CT) images has been widely adopted. Therefore, researchers of the computer vision area have developed many automatic diagnosing models based on machine learning or deep learning to assist the radiologists and improve the diagnosing accuracy. In this paper, we present a review of these recently emerging automatic diagnosing models. 70 models proposed from February 14, 2020, to July 21, 2020, are involved. We analyzed the models from the perspective of preprocessing, feature extraction, classification, and evaluation. Based on the limitation of existing models, we pointed out that domain adaption in transfer learning and interpretability promotion would be the possible future directions., Comment: In ICRAI 2020: 2020 6th International Conference on Robotics and Artificial Intelligence

Parameter estimation of mixture regression model using the expectation maximization (EM) algorithm is highly sensitive to outliers. Here we propose a fast and efficient robust mixture regression algorithm, called Component-wise Adaptive Trimming (CAT) method. We consider simultaneous outlier detection and robust parameter estimation to minimize the effect of outlier contamination. Robust mixture regression has many important applications including in human cancer genomics data, where the population often displays strong heterogeneity added by unwanted technological perturbations. Existing robust mixture regression methods suffer from outliers as they either conduct parameter estimation in the presence of outliers, or rely on prior knowledge of the level of outlier contamination. CAT was implemented in the framework of classification expectation maximization, under which a natural definition of outliers could be derived. It implements a least trimmed squares (LTS) approach within each exclusive mixing component, where the robustness issue could be transformed from the mixture case to simple linear regression case. The high breakdown point of the LTS approach allows us to avoid the pre-specification of trimming parameter. Compared with multiple existing algorithms, CAT is the most competitive one that can handle and adaptively trim off outliers as well as heavy tailed noise, in different scenarios of simulated data and real genomic data. CAT has been implemented in an R package `RobMixReg' available in CRAN.

Most graph-network-based meta-learning approaches model instance-level relation of examples. We extend this idea further to explicitly model the distribution-level relation of one example to all other examples in a 1-vs-N manner. We propose a novel approach named distribution propagation graph network (DPGN) for few-shot learning. It conveys both the distribution-level relations and instance-level relations in each few-shot learning task. To combine the distribution-level relations and instance-level relations for all examples, we construct a dual complete graph network which consists of a point graph and a distribution graph with each node standing for an example. Equipped with dual graph architecture, DPGN propagates label information from labeled examples to unlabeled examples within several update generations. In extensive experiments on few-shot learning benchmarks, DPGN outperforms state-of-the-art results by a large margin in 5% $\sim$ 12% under supervised setting and 7% $\sim$ 13% under semi-supervised setting. Code will be released., Comment: Accepted by CVPR 2020

In this paper, we propose a novel method called Residual Steps Network (RSN). RSN aggregates features with the same spatial size (Intra-level features) efficiently to obtain delicate local representations, which retain rich low-level spatial information and result in precise keypoint localization. Additionally, we observe the output features contribute differently to final performance. To tackle this problem, we propose an efficient attention mechanism - Pose Refine Machine (PRM) to make a trade-off between local and global representations in output features and further refine the keypoint locations. Our approach won the 1st place of COCO Keypoint Challenge 2019 and achieves state-of-the-art results on both COCO and MPII benchmarks, without using extra training data and pretrained model. Our single model achieves 78.6 on COCO test-dev, 93.0 on MPII test dataset. Ensembled models achieve 79.2 on COCO test-dev, 77.1 on COCO test-challenge dataset. The source code is publicly available for further research at https://github.com/caiyuanhao1998/RSN, Comment: ECCV2020 Spotlight

Out-of-Distribution (OoD) detection is important for building safe artificial intelligence systems. However, current OoD detection methods still cannot meet the performance requirements for practical deployment. In this paper, we propose a simple yet effective algorithm based on a novel observation: in a trained neural network, OoD samples with bounded norms well concentrate in the feature space. We call the center of OoD features the Feature Space Singularity (FSS), and denote the distance of a sample feature to FSS as FSSD. Then, OoD samples can be identified by taking a threshold on the FSSD. Our analysis of the phenomenon reveals why our algorithm works. We demonstrate that our algorithm achieves state-of-the-art performance on various OoD detection benchmarks. Besides, FSSD also enjoys robustness to slight corruption in test data and can be further enhanced by ensembling. These make FSSD a promising algorithm to be employed in real world. We release our code at \url{https://github.com/megvii-research/FSSD_OoD_Detection}., Comment: 10 pages, 7 figures

In this paper, we devise a framework to infer a smartphone user's location and walking routes in an indoor environment, using only the information from inertial measurement unit (IMU) sensors like gyroscope and accelerometer. To overcome the shortcoming of estimation drift over time in common PDR (pedestrian dead reckoning)-IMU systems, we propose a map-aided system which uses the map elements to help correct the user's position. We generate a map based on the environment parameters and a map matching algorithm is applied to find the most likely location of the user. The reading from the IMU sensors contains amounts of noise when user is walking, therefore we propose an edge detection algorithm based on the PELT model to smooth the piece-wise signals and identify the time frame when the user is making a turn. We evaluate our system when the smartphone is held either in the user's hand or in the backpack, and the system is able to give the correct walking path in both cases.

Background: Depressive disorders are common in children and adolescents. Antidepressants, psychotherapies, and their combination are often used in routine clinical practice; however, available evidence on the comparative efficacy and safety of these interventions is inconclusive. Therefore, we sought to compare and rank all available treatment interventions for the acute treatment of depressive disorders in children and adolescents. Methods: We did a systematic review and network meta-analysis. We searched PubMed, Embase, the Cochrane Central Register of Controlled Trials, Web of Science, PsycINFO, ProQuest, CINAHL, LiLACS, international trial registries, and the websites of regulatory agencies for published and unpublished randomised controlled trials from database inception until Jan 1, 2019. We included placebo-controlled and head-to-head trials of 16 antidepressants, seven psychotherapies, and five combinations of antidepressant and psychotherapy that are used for the acute treatment of children and adolescents (≤18 years old and of both sexes) with depressive disorder diagnosed according to standard operationalised criteria. Trials recruiting participants with treatment-resistant depression, bipolar disorder, psychotic depression, treatment duration of less than 4 weeks, or an overall sample size of fewer than ten patients were excluded. We extracted data following a predefined hierarchy of outcome measures, and assessed risk of bias and certainty of evidence using validated methods. Primary outcomes were efficacy (change in depressive symptoms) and acceptability (treatment discontinuation due to any cause). We estimated summary standardised mean differences (SMDs) or odds ratios (ORs) with credible intervals (CrIs) using network meta-analysis with random effects. This study was registered with PROSPERO, number CRD42015020841. Findings: From 20 366 publications, we included 71 trials (9510 participants). Depressive disorders in most studies were moderate to sev

Introduction: Although previous conventional meta-analyses and network meta-analyses have provided some important findings about pharmacological treatments for children and adolescents with depressive disorders in the past decades, several questions still remain unsolved by the aggregate data from those meta-analyses. Individual participant data meta-analysis (IPD-MA) enables exploration of the impacts of individual characteristics on treatment effects, allowing matching of treatments to specific subgroups of patients. We will perform an IPD-MA to assess the efficacy and tolerability of new-generation antidepressants for major depressive disorder in children and adolescents. Methods and analysis: We will systematically search for all double-blind randomised controlled trials (RCTs) that have compared any new-generation antidepressant with placebo for the acute treatment of major depressive disorder in children and adolescents, in the following databases: PubMed, EMBASE, the Cochrane Library, PsycINFO, Web of Science, CINAHL, LILACS and ProQuest Dissertations. We will contact all corresponding authors of included RCTs and ask for their cooperation in this project by providing individual participant data from the original trials. The primary outcomes will include efficacy, measured as the mean change of depression symptoms by Children’s Depression Rating Scale Revised (CDRS-R), and tolerability, measured as the proportion of patients who withdrew from the trials early due to adverse effects. The secondary outcomes will include response rates, remission rates, deterioration rate, all-cause discontinuation, suicidal-related outcomes and global functioning outcome. Using the raw de-identified study data, we will use mixed-effects logistic and linear regression models to perform the IPD-MAs. The risk of bias of included studies will be assessed using the Cochrane risk of bias tool. We will also detect the publication bias and effects of non-participation of eligible studi

INTRODUCTION: Post-traumatic stress disorder (PTSD) is common among children and adolescents who are exposed to trauma, and it is often associated with significant negative impacts on their psychosocial functioning and quality of life. Many types of psychotherapies have been found to be effective for PTSD in children and adolescents. However, due to the lack of direct comparisons between different psychotherapies, the hierarchy of treatment efficacy is still unclear. Therefore, we plan to conduct a systematic review and network meta-analysis to evaluate the efficacy and acceptability of various types of psychotherapies for PTSD in children and adolescents. METHODS AND ANALYSIS: A systematic search will be conducted among eight electronic databases, including PubMed, Cochrane, Embase, Web of Science, PsycINFO, Cumulative Index of Nursing and Allied Health, Published International Literature on Traumatic Stress (PILOTS) and ProQuest Dissertations, from inception to October 2017. Randomised controlled trials, regardless of language, publication year and publication type, comparing any psychotherapies for PTSD to any control condition or alternative treatment in children and adolescents (18 years old or less) diagnosed with full or subclinical PTSD will be included. Study duration and the number of treatment sessions will not be limited. The primary outcome will be PTSD symptom severity at post-treatment as measured by a rating scale reported by the child, parent or a clinician. The secondary outcomes will include: (1) efficacy at follow-up; (2) acceptability (all-cause discontinuation); (3) anxiety symptom severity; (4) depressive symptom severity and (5) quality of life and functional improvement. Bayesian network meta-analyses for all relative outcome measures will be performed. We will conduct subgroup and sensitivity network meta-analyses to determine whether the findings are affected by study characteristics. The quality of the evidence contributing to network est

Cloud model and D-S theory have been widely used in uncertainty reasoning. Meanwhile, modal strain energy and Inner Product Vector are also utilized as damage-sensitive features to detect structural damage. In this paper, a new structural damage identification approach is proposed based on Dempster-Shafer theory and cloud model. Cloud models were created to make uncertainty reasoning in damage structures by modal strain energy and the Inner Product Vector of acceleration. Then the results of the two methods were combined by using the Dempster-Shafer theory. Due to the classical D-S theory involves counter – intuitive behavious when the high conflicting evidences exists, the distance function was introduced to correct the conflict factor K and combine the evidences. Moreover, a model of simple beam was created to verify the feasibility and accuracy for the single-damage and the multiple-damage. The effects of noise on damage detection were investigated simultaneously. The results show that the method has strong anti-noise ability and high accuracy.

Shuai Yuan,1,* Xinyu Zhou,1,2,* Yuqing Zhang,1,3,* Hanpin Zhang,1,3,* Juncai Pu,1,3 Lining Yang,1,3 Lanxiang Liu,1,3 Xiaofeng Jiang,1,3 Peng Xie1,3 1Institute of Neuroscience and the Collaborative Innovation Center for Brain Science, Chongqing Medical University, 2Department of Psychiatry, 3Department of Neurology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China *These authors contributed equally to this work Background: Depression and anxiety are the most common mental disorders in children and adolescents. Bibliotherapy is a treatment using written materials for mental health problems. Its main advantages are ease of use, low cost, low staffing demands, and greater privacy. Yet few meta-analyses have focused on the effect of bibliotherapy on depression and anxiety disorders in children and adolescents. Methods: We included randomized controlled trials comparing bibliotherapy with control conditions for depression and anxiety in children and adolescents (aged ≤18 years). Five electronic databases (PubMed, Embase, Cochrane, Web of Science, and PsycINFO) were searched from inception to January 2017. Efficacy was defined as mean change scores in depression and anxiety symptoms. Acceptability was defined as the proportion of participants who discontinued the treatment. Random effects model was used. An intention-to-treat analysis was conducted. Results: Eight studies with 979 participants were selected. At posttreatment, bibliotherapy was significantly more effective than the control conditions in reducing the symptoms of depression or anxiety (standardized mean difference, -0.52; 95% confidence interval [CI], -0.89 to -0.15). Bibliotherapy did not have statistically significantly more all-cause discontinuations than controls (risk ratios, 1.66; 95% CI, 0.93 to 2.95). We also performed subgroup analyses for efficacy outcomes in different categories (types of disorder, mean age, control conditions, and parental involvement) of stud

Introduction: Depressive disorder is common in children and adolescents, with important consequences and serious impairments in terms of personal and social functioning. While both pharmacological and psychological interventions have been shown to be effective, there is still uncertainty about the balance between these and what treatment strategy should be preferred in clinical practice. Therefore, we aim to compare and rank in a network meta-analysis (NMA) the commonly used psychological, pharmacological and combined interventions for depressive disorder in children and adolescents. Methods and analysis: We will update the literature search of two previous NMAs for the identification of trials of antidepressant and psychotherapy alone for depressive disorder in children and adolescents. For identification of trials of combination interventions, seven databases (PubMed, EMBASE, CENTRAL (Cochrane Central Register of Controlled Trials), Web of Science, PsycINFO, CINAHL, LiLACS) will be searched from date of inception. We will also search ClinicalTrials.gov, the WHO International Clinical Trials Registry Platform and check relevant reports on the US Food and Drug Administration website for unpublished data. Building on our previous findings in the field, we will include any commonly prescribed oral antidepressants and any manualised or structured psychotherapies, as well as their combinations. Randomised controlled trials assessing any active intervention against active comparator or pill placebo/psychological controls in acute treatment for depressive disorder in children and adolescents will be included. The primary outcomes will be efficacy (mean change in depressive symptoms), and acceptability of treatment (dropout rate due to any cause). The secondary outcomes will be remission rate, tolerability of treatment (dropouts for adverse events), as well as suicide-related outcomes (suicidal behaviour or ideation). We will perform Bayesian NMAs for all relative outcome

We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs). The new architecture utilizes two new operations, pointwise group convolution and channel shuffle, to greatly reduce computation cost while maintaining accuracy. Experiments on ImageNet classification and MS COCO object detection demonstrate the superior performance of ShuffleNet over other structures, e.g. lower top-1 error (absolute 7.8%) than recent MobileNet on ImageNet classification task, under the computation budget of 40 MFLOPs. On an ARM-based mobile device, ShuffleNet achieves ~13x actual speedup over AlexNet while maintaining comparable accuracy.

Previous approaches for scene text detection have already achieved promising performances across various benchmarks. However, they usually fall short when dealing with challenging scenarios, even when equipped with deep neural network models, because the overall performance is determined by the interplay of multiple stages and components in the pipelines. In this work, we propose a simple yet powerful pipeline that yields fast and accurate text detection in natural scenes. The pipeline directly predicts words or text lines of arbitrary orientations and quadrilateral shapes in full images, eliminating unnecessary intermediate steps (e.g., candidate aggregation and word partitioning), with a single neural network. The simplicity of our pipeline allows concentrating efforts on designing loss functions and neural network architecture. Experiments on standard datasets including ICDAR 2015, COCO-Text and MSRA-TD500 demonstrate that the proposed algorithm significantly outperforms state-of-the-art methods in terms of both accuracy and efficiency. On the ICDAR 2015 dataset, the proposed algorithm achieves an F-score of 0.7820 at 13.2fps at 720p resolution., Comment: Accepted to CVPR 2017, fix equation (3)

We introduce an Actor-Critic Ensemble(ACE) method for improving the performance of Deep Deterministic Policy Gradient(DDPG) algorithm. At inference time, our method uses a critic ensemble to select the best action from proposals of multiple actors running in parallel. By having a larger candidate set, our method can avoid actions that have fatal consequences, while staying deterministic. Using ACE, we have won the 2nd place in NIPS'17 Learning to Run competition, under the name of "Megvii-hzwer"., Comment: 3 pages, 4 figures