Search

Autoencoders excel at generating models for natural images, but often lack structure and interpretability due to their use of generic deep networks. In this work, we make the explicit assumption that the image distribution is generated from a multi-stage sparse deconvolution. The corresponding inverse map, which we use as an encoder, is a multi-stage convolution sparse coding (CSC), with each stage obtained from unrolling an optimization algorithm for solving the corresponding (convexified) sparse coding program. Instead of directly minimizing the distributional gap between actual and generated images, we employ the closed-loop transcription (CTRL) framework to enhance the efficiency of the sparse representations. Our approach achieves comparable results on datasets like ImageNet-1K while using simpler networks and less computational power. Our method enjoys several side benefits, including more structured and interpretable representations, more stable convergence, and scalability to large datasets. Our method is arguably the first to demonstrate that a concatenation of multiple convolution sparse coding/decoding layers leads to an interpretable and effective autoencoder for modeling the distribution of large-scale natural image datasets. © 2024 Proceedings of Machine Learning Research

This paper proposes an unsupervised method for learning a unified representation that serves both discriminative and generative purposes. While most existing unsupervised learning approaches focus on a representation for only one of these two goals, we show that a unified representation can enjoy the mutual benefits of having both. Such a representation is attainable by generalizing the recently proposed closed-loop transcription framework, known as CTRL, to the unsupervised setting. This entails solving a constrained maximin game over a rate reduction objective that expands features of all samples while compressing features of augmentations of each sample. Through this process, we see discriminative low-dimensional structures emerge in the resulting representations. Under comparable experimental conditions and network complexities, we demonstrate that these structured representations enable classification performance close to state-of-the-art unsupervised discriminative representations, and conditionally generated image quality significantly higher than that of state-of-the-art unsupervised generative models. © 2024 Proceedings of Machine Learning Research

Event cameras, characterized by high temporal resolution, high dynamic range, low power consumption, and high pixel bandwidth, offer unique capabilities for object detection in specialized contexts. Despite these advantages, the inherent sparsity and asynchrony of event data pose challenges to existing object detection algorithms. Spiking Neural Networks (SNNs), inspired by the way the human brain codes and processes information, offer a potential solution to these difficulties. However, their performance in object detection using event cameras is limited in current implementations. In this paper, we propose the Spiking Fusion Object Detector (SFOD), a simple and efficient approach to SNN-based object detection. Specifically, we design a Spiking Fusion Module, achieving the first-time fusion of feature maps from different scales in SNNs applied to event cameras. Additionally, through integrating our analysis and experiments conducted during the pretraining of the backbone network on the NCAR dataset, we delve deeply into the impact of spiking decoding strategies and loss functions on model performance. Thereby, we establish state-of-the-art classification results based on SNNs, achieving 93.7\% accuracy on the NCAR dataset. Experimental results on the GEN1 detection dataset demonstrate that the SFOD achieves a state-of-the-art mAP of 32.1\%, outperforming existing SNN-based approaches. Our research not only underscores the potential of SNNs in object detection with event cameras but also propels the advancement of SNNs. Code is available at https://github.com/yimeng-fan/SFOD., Comment: Accepted by CVPR2024

Visual entailment (VE) is a multimodal reasoning task consisting of image-sentence pairs whereby a promise is defined by an image, and a hypothesis is described by a sentence. The goal is to predict whether the image semantically entails the sentence. VE systems have been widely adopted in many downstream tasks. Metamorphic testing is the commonest technique for AI algorithms, but it poses a significant challenge for VE testing. They either only consider perturbations on single modality which would result in ineffective tests due to the destruction of the relationship of image-text pair, or just conduct shallow perturbations on the inputs which can hardly detect the decision error made by VE systems. Motivated by the fact that objects in the image are the fundamental element for reasoning, we propose VEglue, an object-aligned joint erasing approach for VE systems testing. It first aligns the object regions in the premise and object descriptions in the hypothesis to identify linked and un-linked objects. Then, based on the alignment information, three Metamorphic Relations are designed to jointly erase the objects of the two modalities. We evaluate VEglue on four widely-used VE systems involving two public datasets. Results show that VEglue could detect 11,609 issues on average, which is 194%-2,846% more than the baselines. In addition, VEglue could reach 52.5% Issue Finding Rate (IFR) on average, and significantly outperform the baselines by 17.1%-38.2%. Furthermore, we leverage the tests generated by VEglue to retrain the VE systems, which largely improves model performance (50.8% increase in accuracy) on newly generated tests without sacrificing the accuracy on the original test set., Comment: 12pages, 3 figures

Due to the advantages of fusing information from various modalities, multimodal learning is gaining increasing attention. Being a fundamental task of multimodal learning, Visual Grounding (VG), aims to locate objects in images through natural language expressions. Ensuring the quality of VG models presents significant challenges due to the complex nature of the task. In the black box scenario, existing adversarial testing techniques often fail to fully exploit the potential of both modalities of information. They typically apply perturbations based solely on either the image or text information, disregarding the crucial correlation between the two modalities, which would lead to failures in test oracles or an inability to effectively challenge VG models. To this end, we propose PEELING, a text perturbation approach via image-aware property reduction for adversarial testing of the VG model. The core idea is to reduce the property-related information in the original expression meanwhile ensuring the reduced expression can still uniquely describe the original object in the image. To achieve this, PEELING first conducts the object and properties extraction and recombination to generate candidate property reduction expressions. It then selects the satisfied expressions that accurately describe the original object while ensuring no other objects in the image fulfill the expression, through querying the image with a visual understanding technique. We evaluate PEELING on the state-of-the-art VG model, i.e. OFA-VG, involving three commonly used datasets. Results show that the adversarial tests generated by PEELING achieves 21.4% in MultiModal Impact score (MMI), and outperforms state-of-the-art baselines for images and texts by 8.2%--15.1%., Comment: 14pages, 6 figures

This study discusses a new method combining image steganography technology with Natural Language Processing (NLP) large models, aimed at improving the accuracy and robustness of extracting steganographic text. Traditional Least Significant Bit (LSB) steganography techniques face challenges in accuracy and robustness of information extraction when dealing with complex character encoding, such as Chinese characters. To address this issue, this study proposes an innovative LSB-NLP hybrid framework. This framework integrates the advanced capabilities of NLP large models, such as error detection, correction, and semantic consistency analysis, as well as information reconstruction techniques, thereby significantly enhancing the robustness of steganographic text extraction. Experimental results show that the LSB-NLP hybrid framework excels in improving the extraction accuracy of steganographic text, especially in handling Chinese characters. The findings of this study not only confirm the effectiveness of combining image steganography technology and NLP large models but also propose new ideas for research and application in the field of information hiding. The successful implementation of this interdisciplinary approach demonstrates the great potential of integrating image steganography technology with natural language processing technology in solving complex information processing problems.

This study is based on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset and aims to explore early detection and disease progression in Alzheimer's disease (AD). We employ innovative data preprocessing strategies, including the use of the random forest algorithm to fill missing data and the handling of outliers and invalid data, thereby fully mining and utilizing these limited data resources. Through Spearman correlation coefficient analysis, we identify some features strongly correlated with AD diagnosis. We build and test three machine learning models using these features: random forest, XGBoost, and support vector machine (SVM). Among them, the XGBoost model performs the best in terms of diagnostic performance, achieving an accuracy of 91%. Overall, this study successfully overcomes the challenge of missing data and provides valuable insights into early detection of Alzheimer's disease, demonstrating its unique research value and practical significance.

With the development of LLMs, the security threats of LLMs are getting more and more attention. Numerous jailbreak attacks have been proposed to assess the security defense of LLMs. Current jailbreak attacks primarily utilize scenario camouflage techniques. However their explicitly mention of malicious intent will be easily recognized and defended by LLMs. In this paper, we propose an indirect jailbreak attack approach, Puzzler, which can bypass the LLM's defense strategy and obtain malicious response by implicitly providing LLMs with some clues about the original malicious query. In addition, inspired by the wisdom of "When unable to attack, defend" from Sun Tzu's Art of War, we adopt a defensive stance to gather clues about the original malicious query through LLMs. Extensive experimental results show that Puzzler achieves a query success rate of 96.6% on closed-source LLMs, which is 57.9%-82.7% higher than baselines. Furthermore, when tested against the state-of-the-art jailbreak detection approaches, Puzzler proves to be more effective at evading detection compared to baselines., Comment: 13 pages, 6 figures

Current techniques in Visual Simultaneous Localization and Mapping (VSLAM) estimate camera displacement by comparing image features of consecutive scenes. These algorithms depend on scene continuity, hence requires frequent camera inputs. However, processing images frequently can lead to significant memory usage and computation overhead. In this study, we introduce SemanticSLAM, an end-to-end visual-inertial odometry system that utilizes semantic features extracted from an RGB-D sensor. This approach enables the creation of a semantic map of the environment and ensures reliable camera localization. SemanticSLAM is scene-agnostic, which means it doesn't require retraining for different environments. It operates effectively in indoor settings, even with infrequent camera input, without prior knowledge. The strength of SemanticSLAM lies in its ability to gradually refine the semantic map and improve pose estimation. This is achieved by a convolutional long-short-term-memory (ConvLSTM) network, trained to correct errors during map construction. Compared to existing VSLAM algorithms, SemanticSLAM improves pose estimation by 17%. The resulting semantic map provides interpretable information about the environment and can be easily applied to various downstream tasks, such as path planning, obstacle avoidance, and robot navigation. The code will be publicly available at https://github.com/Leomingyangli/SemanticSLAM, Comment: 2023 IEEE Symposium Series on Computational Intelligence (SSCI) 6 pages

Precisely perceiving the geometric and semantic properties of real-world 3D objects is crucial for the continued evolution of augmented reality and robotic applications. To this end, we present Foundation Model Embedded Gaussian Splatting (FMGS), which incorporates vision-language embeddings of foundation models into 3D Gaussian Splatting (GS). The key contribution of this work is an efficient method to reconstruct and represent 3D vision-language models. This is achieved by distilling feature maps generated from image-based foundation models into those rendered from our 3D model. To ensure high-quality rendering and fast training, we introduce a novel scene representation by integrating strengths from both GS and multi-resolution hash encodings (MHE). Our effective training procedure also introduces a pixel alignment loss that makes the rendered feature distance of the same semantic entities close, following the pixel-level semantic boundaries. Our results demonstrate remarkable multi-view semantic consistency, facilitating diverse downstream tasks, beating state-of-the-art methods by 10.2 percent on open-vocabulary language-based object detection, despite that we are 851X faster for inference. This research explores the intersection of vision, language, and 3D scene representation, paving the way for enhanced scene understanding in uncontrolled real-world environments. We plan to release the code on the project page., Comment: Project page: https://xingxingzuo.github.io/fmgs

Although there is a growing body of literature on the COVID-19 pandemic and the implemented strategies that have imposed additional risks in tackling emergencies by increasing socio-economic vulnerabilities, studies on human evacuation behavior during lockdowns are lacking. This paper contributes to evacuation and emergency research by examining seismic evacuation decision-making by surveying the areas affected by the Luding earthquake on 5 September 2022, when most parts of Sichuan province were experiencing strict pandemic restrictions. Using these data and per the emergency evacuation decision-making mechanism, we developed six hierarchical series of logistic regression models. Our major results suggest that 1) Socio-demographic parameters have shown different correlations with the study's dependent variables in each stage of those hierarchical models, 2) Respondents at home at the time of the earthquake were more likely to identify the earthquake risk than those who stayed outdoors; the former group showed less willingness to evacuate, 3) Rural residents have perceived higher earthquake risks than urban residents, and 4) Loss of job, change in income due to COVID-19 restrictions, and difficulty accessing daily supplies during the lockdown affected the residents' risk assessment and evacuation decision-making negatively. Insights into these aspects are expected to contribute to a better understanding of evacuation behavior during double disasters by modifying emergency response regulations and providing the residents with information about emergencies during pandemic restrictions.

Form 10-K report is a financial report disclosing the annual financial state of a public company. It is an important evidence to conduct financial analysis, i.e., asset pricing, corporate finance. Practitioners and researchers are constantly designing algorithms to better conduct analysis on information in the Form 10-K report. The vast majority of previous works focus on quantitative data. With recent advancement on natural language processing (NLP), textual data in financial filing attracts more attention. However, to incorporate textual data for analyzing, Form 10-K Itemization is a necessary pre-process step. It aims to segment the whole document into several Item sections, where each Item section focuses on a specific financial aspect of the company. With the segmented Item sections, NLP techniques can directly apply on those Item sections related to downstream tasks. In this paper, we develop a Form 10-K Itemization system which can automatically segment all the Item sections in 10-K documents. The system is both effective and efficient. It reaches a retrieval rate of 93%., Comment: For demo website, see http://review10-k.ddns.net

Autoencoding has achieved great empirical success as a framework for learning generative models for natural images. Autoencoders often use generic deep networks as the encoder or decoder, which are difficult to interpret, and the learned representations lack clear structure. In this work, we make the explicit assumption that the image distribution is generated from a multi-stage sparse deconvolution. The corresponding inverse map, which we use as an encoder, is a multi-stage convolution sparse coding (CSC), with each stage obtained from unrolling an optimization algorithm for solving the corresponding (convexified) sparse coding program. To avoid computational difficulties in minimizing distributional distance between the real and generated images, we utilize the recent closed-loop transcription (CTRL) framework that optimizes the rate reduction of the learned sparse representations. Conceptually, our method has high-level connections to score-matching methods such as diffusion models. Empirically, our framework demonstrates competitive performance on large-scale datasets, such as ImageNet-1K, compared to existing autoencoding and generative methods under fair conditions. Even with simpler networks and fewer computational resources, our method demonstrates high visual quality in regenerated images. More surprisingly, the learned autoencoder performs well on unseen datasets. Our method enjoys several side benefits, including more structured and interpretable representations, more stable convergence, and scalability to large datasets. Our method is arguably the first to demonstrate that a concatenation of multiple convolution sparse coding/decoding layers leads to an interpretable and effective autoencoder for modeling the distribution of large-scale natural image datasets., Comment: 20 pages

The use of flexible, self-healing conductive hydrogels as a type of typical electronic skin with the function of transmitting sensory signals has attracted wide attention in the field of biomaterials. In this study, composite hydrogels based on polyvinyl alcohol (PVA), gelatin (GEL), oxidized sodium alginate (OSA), graphene oxide (GO), and single-walled carbon nanotubes (SWNTs) were successfully prepared. The hydrogen and imine bonding of the composite hydrogels gives them excellent self-healing properties. Their self-healing properties restore 68% of their breaking strength and over 95% of their electrical conductivity. The addition of GO and SWNTs enables the PGO-GS hydrogels to achieve a compressive modulus and conductivity of 42.2 kPa and 29.6 mS/m, which is 8.2 times and 1.5 times that of pure PGO, respectively. Furthermore, the PGO-GS hydrogels can produce profound feedback signals in response to deformation caused by external forces and human movements such as finger flexion and speech. In addition, the PGO-GS hydrogels exhibit superior biocompatibility compared to PGO. All of these results indicate that the PGO-GS hydrogels have great potential with respect to future applications in the field of electronic skin.

The ability to detect manipulation in multimedia data is vital in digital forensics. Existing Image Manipulation Detection (IMD) methods are mainly based on detecting anomalous features arisen from image editing or double compression artifacts. All existing IMD techniques encounter challenges when it comes to detecting small tampered regions from a large image. Moreover, compression-based IMD approaches face difficulties in cases of double compression of identical quality factors. To investigate the State-of-The-Art (SoTA) IMD methods in those challenging conditions, we introduce a new Challenging Image Manipulation Detection (CIMD) benchmark dataset, which consists of two subsets, for evaluating editing-based and compression-based IMD methods, respectively. The dataset images were manually taken and tampered with high-quality annotations. In addition, we propose a new two-branch network model based on HRNet that can better detect both the image-editing and compression artifacts in those challenging conditions. Extensive experiments on the CIMD benchmark show that our model significantly outperforms SoTA IMD methods on CIMD., Comment: 9 pages, 6 figures, 3 tabels. AAAI-24

Achieving efficient and consistent localization a prior map remains challenging in robotics. Conventional keyframe-based approaches often suffers from sub-optimal viewpoints due to limited field of view (FOV) and/or constrained motion, thus degrading the localization performance. To address this issue, we design a real-time tightly-coupled Neural Radiance Fields (NeRF)-aided visual-inertial navigation system (VINS). In particular, by effectively leveraging the NeRF's potential to synthesize novel views, the proposed NeRF-VINS overcomes the limitations of traditional keyframe-based maps (with limited views) and optimally fuses IMU, monocular images, and synthetically rendered images within an efficient filter-based framework. This tightly-coupled fusion enables efficient 3D motion tracking with bounded errors. We extensively compare the proposed NeRF-VINS against the state-of-the-art methods that use prior map information and demonstrate its ability to perform real-time localization, at over 10 Hz, on a resource-constrained Jetson AGX Orin embedded platform., Comment: 6 pages, 7 figures

With the popularization and application of Building Information Modeling (BIM), the demand for BIM technical talents in the construction industry is increasing. Exploring college students’ BIM technical learning behavior is of great practical significance to improve education activities. Based on the Unified Theory of Acceptance and Use of Technology (UTAUT), this research adds learning attitude variables to construct a theoretical model of influencing factors of college students’ BIM technology learning behavior. Chinese undergraduate students were asked to complete online questionnaires through peer-to-peer contact with sample colleges and universities. Finally, 1090 valid questionnaires were obtained. The students were sampled from research-oriented, applied research-oriented, application-oriented, and private research-oriented universities in seven regions of China: northeast, north, east, south, central, northwest, and southwest. The structural equation model was used to analyze the sampling data. The results indicate that college students’ BIM learning attitude, performance expectations, and social influence positively and directly impact their learning intention, which indirectly impacts their learning behavior. At the same time, promoting factors and learning intention demonstrate a significant positive and direct impact on learning behavior. Therefore, the following suggestions have been put forward to enhance college students’ learning motivation for BIM technology: increase the popularization of BIM technology in colleges and universities and improve the operation level of full-time BIM teachers. The latter enables colleges and universities to continuously and stably export qualified BIM technical talents to society and the market, resulting in a continuous industry development cycle, Design & Construction Management

This work proposes a new computational framework for learning a structured generative model for real-world datasets. In particular, we propose to learn a Closed-loop Transcriptionbetween a multi-class, multi-dimensional data distribution and a Linear discriminative representation (CTRL) in the feature space that consists of multiple independent multi-dimensional linear subspaces. In particular, we argue that the optimal encoding and decoding mappings sought can be formulated as a two-player minimax game between the encoder and decoderfor the learned representation. A natural utility function for this game is the so-called rate reduction, a simple information-theoretic measure for distances between mixtures of subspace-like Gaussians in the feature space. Our formulation draws inspiration from closed-loop error feedback from control systems and avoids expensive evaluating and minimizing of approximated distances between arbitrary distributions in either the data space or the feature space. To a large extent, this new formulation unifies the concepts and benefits of Auto-Encoding and GAN and naturally extends them to the settings of learning a both discriminative and generative representation for multi-class and multi-dimensional real-world data. Our extensive experiments on many benchmark imagery datasets demonstrate tremendous potential of this new closed-loop formulation: under fair comparison, visual quality of the learned decoder and classification performance of the encoder is competitive and arguably better than existing methods based on GAN, VAE, or a combination of both. Unlike existing generative models, the so-learned features of the multiple classes are structured instead of hidden: different classes are explicitly mapped onto corresponding independent principal subspaces in the feature space, and diverse visual attributes within each class are modeled by the independent principal components within each subspace.

This paper proposes an unsupervised method for learning a unified representation that serves both discriminative and generative purposes. While most existing unsupervised learning approaches focus on a representation for only one of these two goals, we show that a unified representation can enjoy the mutual benefits of having both. Such a representation is attainable by generalizing the recently proposed \textit{closed-loop transcription} framework, known as CTRL, to the unsupervised setting. This entails solving a constrained maximin game over a rate reduction objective that expands features of all samples while compressing features of augmentations of each sample. Through this process, we see discriminative low-dimensional structures emerge in the resulting representations. Under comparable experimental conditions and network complexities, we demonstrate that these structured representations enable classification performance close to state-of-the-art unsupervised discriminative representations, and conditionally generated image quality significantly higher than that of state-of-the-art unsupervised generative models. Source code can be found at https://github.com/Delay-Xili/uCTRL., Comment: 17 pages

Despite strong empirical performance for image classification, deep neural networks are often regarded as ``black boxes'' and they are difficult to interpret. On the other hand, sparse convolutional models, which assume that a signal can be expressed by a linear combination of a few elements from a convolutional dictionary, are powerful tools for analyzing natural images with good theoretical interpretability and biological plausibility. However, such principled models have not demonstrated competitive performance when compared with empirically designed deep networks. This paper revisits the sparse convolutional modeling for image classification and bridges the gap between good empirical performance (of deep learning) and good interpretability (of sparse convolutional models). Our method uses differentiable optimization layers that are defined from convolutional sparse coding as drop-in replacements of standard convolutional layers in conventional deep neural networks. We show that such models have equally strong empirical performance on CIFAR-10, CIFAR-100, and ImageNet datasets when compared to conventional neural networks. By leveraging stable recovery property of sparse modeling, we further show that such models can be much more robust to input corruptions as well as adversarial perturbations in testing through a simple proper trade-off between sparse regularization and data reconstruction terms. Source code can be found at https://github.com/Delay-Xili/SDNet., Comment: 17 pages. Accepted by NeurIPS2022

Natural language (NL) documentation is the bridge between software managers and testers, and NL test cases are prevalent in system-level testing and other quality assurance activities. Due to reasons such as requirements redundancy, parallel testing, and tester turnover within long evolving history, there are inevitably lots of redundant test cases, which significantly increase the cost. Previous redundancy detection approaches typically treat the textual descriptions as a whole to compare their similarity and suffer from low precision. Our observation reveals that a test case can have explicit test-oriented entities, such as tested function Components, Constraints, etc; and there are also specific relations between these entities. This inspires us with a potential opportunity for accurate redundancy detection. In this paper, we first define five test-oriented entity categories and four associated relation categories and re-formulate the NL test case redundancy detection problem as the comparison of detailed testing content guided by the test-oriented entities and relations. Following that, we propose Tscope, a fine-grained approach for redundant NL test case detection by dissecting test cases into atomic test tuple(s) with the entities restricted by associated relations. To serve as the test case dissection, Tscope designs a context-aware model for the automatic entity and relation extraction. Evaluation on 3,467 test cases from ten projects shows Tscope could achieve 91.8% precision, 74.8% recall, and 82.4% F1, significantly outperforming state-of-the-art approaches and commonly-used classifiers. This new formulation of the NL test case redundant detection problem can motivate the follow-up studies to further improve this task and other related tasks involving NL descriptions., Comment: 12 pages, 6 figures, to be published in ESEC/FSE 22

Poles and building edges are frequently observable objects on urban roads, conveying reliable hints for various computer vision tasks. To repetitively extract them as features and perform association between discrete LiDAR frames for registration, we propose the first learning-based feature segmentation and description model for 3D lines in LiDAR point cloud. To train our model without the time consuming and tedious data labeling process, we first generate synthetic primitives for the basic appearance of target lines, and build an iterative line auto-labeling process to gradually refine line labels on real LiDAR scans. Our segmentation model can extract lines under arbitrary scale perturbations, and we use shared EdgeConv encoder layers to train the two segmentation and descriptor heads jointly. Base on the model, we can build a highly-available global registration module for point cloud registration, in conditions without initial transformation hints. Experiments have demonstrated that our line-based registration method is highly competitive to state-of-the-art point-based approaches. Our code is available at https://github.com/zxrzju/SuperLine3D.git., Comment: 17 pages, ECCV 2022 Accepted

Existing permutation-invariant methods can be divided into two categories according to the aggregation scope, i.e. global aggregation and local one. Although the global aggregation methods, e. g., PointNet and Deep Sets, get involved in simpler structures, their performance is poorer than the local aggregation ones like PointNet++ and Point Transformer. It remains an open problem whether there exists a global aggregation method with a simple structure, competitive performance, and even much fewer parameters. In this paper, we propose a novel global aggregation permutation-invariant network based on dual MLP dot-product, called DuMLP-Pin, which is capable of being employed to extract features for set inputs, including unordered or unstructured pixel, attribute, and point cloud data sets. We strictly prove that any permutation-invariant function implemented by DuMLP-Pin can be decomposed into two or more permutation-equivariant ones in a dot-product way as the cardinality of the given input set is greater than a threshold. We also show that the DuMLP-Pin can be viewed as Deep Sets with strong constraints under certain conditions. The performance of DuMLP-Pin is evaluated on several different tasks with diverse data sets. The experimental results demonstrate that our DuMLP-Pin achieves the best results on the two classification problems for pixel sets and attribute sets. On both the point cloud classification and the part segmentation, the accuracy of DuMLP-Pin is very close to the so-far best-performing local aggregation method with only a 1-2% difference, while the number of required parameters is significantly reduced by more than 85% in classification and 69% in segmentation, respectively. The code is publicly available on https://github.com/JaronTHU/DuMLP-Pin., Comment: 16 pages, accepted by AAAI 2022 (https://ojs.aaai.org/index.php/AAAI/article/view/19939), with technical appendix

Global point cloud registration is an essential module for localization, of which the main difficulty exists in estimating the rotation globally without initial value. With the aid of gravity alignment, the degree of freedom in point cloud registration could be reduced to 4DoF, in which only the heading angle is required for rotation estimation. In this paper, we propose a fast and accurate global heading angle estimation method for gravity-aligned point clouds. Our key idea is that we generate a translation invariant representation based on Radon Transform, allowing us to solve the decoupled heading angle globally with circular cross-correlation. Besides, for heading angle estimation between point clouds with different distributions, we implement this heading angle estimator as a differentiable module to train a feature extraction network end- to-end. The experimental results validate the effectiveness of the proposed method in heading angle estimation and show better performance compared with other methods., Comment: Paper accepted in the 2022 IEEE International Conference on Robotics and Automation (ICRA)

This work proposes a minimal computational model for learning structured memories of multiple object classes in an incremental setting. Our approach is based on establishing a closed-loop transcription between the classes and a corresponding set of subspaces, known as a linear discriminative representation, in a low-dimensional feature space. Our method is simpler than existing approaches for incremental learning, and more efficient in terms of model size, storage, and computation: it requires only a single, fixed-capacity autoencoding network with a feature space that is used for both discriminative and generative purposes. Network parameters are optimized simultaneously without architectural manipulations, by solving a constrained minimax game between the encoding and decoding maps over a single rate reduction-based objective. Experimental results show that our method can effectively alleviate catastrophic forgetting, achieving significantly better performance than prior work of generative replay on MNIST, CIFAR-10, and ImageNet-50, despite requiring fewer resources. Source code can be found at https://github.com/tsb0601/i-CTRL, Comment: 20 pages

Introduction: Rural roads and built environment in China have been developed enormously, but it is not clear whether these roads fulfill the needs of school children as they need to travel long to school every day. Objective: It is crucial to understand the influencing factors of their travel mode choices to better design future country roads and built environment, aiming to promote physical activities of school children in a safe built environment. Method: This study thus attempts to explore the impacts of rural built environment attributes on children's school travel mode preferences. Eight rural built environment attributes are considered: distance from home to school; the number of intersections passed on the way to school; whether there are sidewalks/bicycle lanes; the traffic speed of school access routes; whether there are separation facilities between motor vehicles and non-motor vehicles; whether there are traffic lights and zebra crossings; availability of greenery such as lawns, flower ponds and street trees and whether there are shops on the way to school and at the school gate. Six hundred and thirty eight valid questionnaires were obtained through face-to-face interviews with school-age children in villages. A multinomial logit model was estimated to unravel the preferences and choices of rural school-age children in different models of school travel using the stated choice data. Results: All the eight attributes have significant impacts on rural children's school travel choices on foot, bicycle, electric bicycle or motorbike. And four rural road design attributes have significant effects on rural children's school travel by private cars. A travel path with pavements or bike lanes, few intersections, low traffic speeds, greenery and shops can facilitate children's school travels on foot or by bike. The conclusions can provide reference for the further upgrading planning, designing and construction of rural roads, as well as e, Design & Construction Management

With the rise of global urbanization, the rural built environment has undergone tremendous changes. As such, the rural built environment impacts on residents’ daily travel behavior is getting more researchers’ attention. To date, most of the research focuses on urban areas in developed countries. To understand the state-of-the-art of interplay between the rural built environment and travel behaviors and to identify future research directions, this study adopts a science mapping approach to identify the relevant topics, authors, journals, and countries of the research done. This study proceeds through bibliometric retrieval of articles from 2005, followed by scientometric analysis and qualitative discussion. 37 documents are found to compare urban and rural domains, with 28 on the rural built environment. Research gaps and the research trends are discussed, of which the main themes are multi-dimensional correlation comparison of rural transportation service systems and emerging transportation modes, the influence of rural social and cultural factors on travel behavior, and low-carbon sustainable transportation. This review provides empirical foundation for current state-of-the-art and identifies the future research directions, specifically for rural built environment impact on travel behavior., Design & Construction Management

Under circumstances of pervasive global aging combined with weakened traditional family elder care, an incremental demand for institutional elder care is generated. This has led to a surge in research regarding institutional elder care. Rural residents’ institutional elder care is receiving more attention as a major theme in social sciences and humanities research. Based on 94 articles related to rural institutional elder care, this study identified the most influential articles, journals and countries in rural institutional elder care research since 1995. This was done using science mapping methods through a three-step workflow consisting of bibliometric retrieval, scoping analysis and qualitative discussion. Keywords revealed five research mainstreams in this field: (1) the cognition and mental state of aged populations, (2) the nursing quality and service supply of aged care institutions, (3) the aged care management systems’ establishment and improvements, (4) the risk factors of admission and discharge of aged care institutions, and (5) deathbed matters regarding the aged population. A qualitative discussion is also provided for 39 urban and rural comparative research papers and 55 pure rural research papers, summarizing the current research progress status regarding institutional elder care systems in rural areas. Gaps within existing research are also identified to indicate future research trends (such as the multi-dimensional and in-depth comparative research on institutional elder care, new rural institutional elder care model and technology, and correlative policy planning and development), which provides a multi-disciplinary guide for future research., Design & Construction Management

With the popularization and application of Building Information Modeling (BIM), the demand for BIM technical talents in the construction industry is increasing. Exploring college students’ BIM technical learning behavior is of great practical significance to improve education activities. Based on the Unified Theory of Acceptance and Use of Technology (UTAUT), this research adds learning attitude variables to construct a theoretical model of influencing factors of college students’ BIM technology learning behavior. Chinese undergraduate students were asked to complete online questionnaires through peer-to-peer contact with sample colleges and universities. Finally, 1090 valid questionnaires were obtained. The students were sampled from research-oriented, applied research-oriented, application-oriented, and private research-oriented universities in seven regions of China: northeast, north, east, south, central, northwest, and southwest. The structural equation model was used to analyze the sampling data. The results indicate that college students’ BIM learning attitude, performance expectations, and social influence positively and directly impact their learning intention, which indirectly impacts their learning behavior. At the same time, promoting factors and learning intention demonstrate a significant positive and direct impact on learning behavior. Therefore, the following suggestions have been put forward to enhance college students’ learning motivation for BIM technology: increase the popularization of BIM technology in colleges and universities and improve the operation level of full-time BIM teachers. The latter enables colleges and universities to continuously and stably export qualified BIM technical talents to society and the market, resulting in a continuous industry development cycle, Design & Construction Management

This work proposes a new computational framework for learning a structured generative model for real-world datasets. In particular, we propose to learn a closed-loop transcription between a multi-class multi-dimensional data distribution and a linear discriminative representation (LDR) in the feature space that consists of multiple independent multi-dimensional linear subspaces. In particular, we argue that the optimal encoding and decoding mappings sought can be formulated as the equilibrium point of a two-player minimax game between the encoder and decoder. A natural utility function for this game is the so-called rate reduction, a simple information-theoretic measure for distances between mixtures of subspace-like Gaussians in the feature space. Our formulation draws inspiration from closed-loop error feedback from control systems and avoids expensive evaluating and minimizing approximated distances between arbitrary distributions in either the data space or the feature space. To a large extent, this new formulation unifies the concepts and benefits of Auto-Encoding and GAN and naturally extends them to the settings of learning a both discriminative and generative representation for multi-class and multi-dimensional real-world data. Our extensive experiments on many benchmark imagery datasets demonstrate tremendous potential of this new closed-loop formulation: under fair comparison, visual quality of the learned decoder and classification performance of the encoder is competitive and often better than existing methods based on GAN, VAE, or a combination of both. Unlike existing generative models, the so learned features of the multiple classes are structured: different classes are explicitly mapped onto corresponding independent principal subspaces in the feature space. Source code can be found at https://github.com/Delay-Xili/LDR., Comment: 41 pages

Deep convolutional neural networks are shown to be overkill with high parametric and computational redundancy in many application scenarios, and an increasing number of works have explored model pruning to obtain lightweight and efficient networks. However, most existing pruning approaches are driven by empirical heuristic and rarely consider the joint impact of channels, leading to unguaranteed and suboptimal performance. In this paper, we propose a novel channel pruning method via Class-Aware Trace Ratio Optimization (CATRO) to reduce the computational burden and accelerate the model inference. Utilizing class information from a few samples, CATRO measures the joint impact of multiple channels by feature space discriminations and consolidates the layer-wise impact of preserved channels. By formulating channel pruning as a submodular set function maximization problem, CATRO solves it efficiently via a two-stage greedy iterative optimization procedure. More importantly, we present theoretical justifications on convergence of CATRO and performance of pruned networks. Experimental results demonstrate that CATRO achieves higher accuracy with similar computation cost or lower computation cost with similar accuracy than other state-of-the-art channel pruning algorithms. In addition, because of its class-aware property, CATRO is suitable to prune efficient networks adaptively for various classification subtasks, enhancing handy deployment and usage of deep networks in real-world applications., Comment: Paper accepted by IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

We present a novel method for visual mapping and localization for autonomous vehicles, by extracting, modeling, and optimizing semantic road elements. Specifically, our method integrates cascaded deep models to detect standardized road elements instead of traditional point features, to seek for improved pose accuracy and map representation compactness. To utilize the structural features, we model road lights and signs by their representative deep keypoints for skeleton and boundary, and parameterize lanes via piecewise cubic splines. Based on the road semantic features, we build a complete pipeline for mapping and localization, which includes a) image processing front-end, b) sensor fusion strategies, and c) optimization backend. Experiments on public datasets and our testing platform have demonstrated the effectiveness and advantages of our method by outperforming traditional approaches., Comment: Published at IEEE ROBOTICS AND AUTOMATION LETTERS

In this work, we propose a novel method for performing inertial aided navigation, by using deep neural networks (DNNs). To date, most DNN inertial navigation methods focus on the task of inertial odometry, by taking gyroscope and accelerometer readings as input and regressing for integrated IMU poses (i.e., position and orientation). While this design has been successfully applied on a number of applications, it is not of theoretical performance guarantee unless patterned motion is involved. This inevitably leads to significantly reduced accuracy and robustness in certain use cases. To solve this problem, we design a framework to compute observable IMU integration terms using DNNs, followed by the numerical pose integration and sensor fusion to achieve the performance gain. Specifically, we perform detailed analysis on the motion terms in IMU kinematic equations, propose a dedicated network design, loss functions, and training strategies for the IMU data processing, and conduct extensive experiments. The results show that our method is generally applicable and outperforms both traditional and DNN methods by wide margins., Comment: IEEE International Conference on Robotics and Automation (ICRA), Xi'an, China, 2021

Recently, the community has witnessed numerous datasets built for developing and testing state estimators. However, for some applications such as aerial transportation or search-and-rescue, the contact force or other disturbance must be perceived for robust planning and control, which is beyond the capacity of these datasets. This paper introduces a Visual-Inertial-Dynamical (VID) dataset, not only focusing on traditional six degrees of freedom (6-DOF) pose estimation but also providing dynamical characteristics of the flight platform for external force perception or dynamics-aided estimation. The VID dataset contains hardware synchronized imagery and inertial measurements, with accurate ground truth trajectories for evaluating common visual-inertial estimators. Moreover, the proposed dataset highlights rotor speed and motor current measurements, control inputs, and ground truth 6-axis force data to evaluate external force estimation. To the best of our knowledge, the proposed VID dataset is the first public dataset containing visual-inertial and complete dynamical information in the real world for pose and external force evaluation. The dataset: https://github.com/ZJU-FAST-Lab/VID-Dataset and related files: https://github.com/ZJU-FAST-Lab/VID-Flight-Platform are open-sourced., Comment: 7 pages,11 figures

Word alignment is essential for the downstream cross-lingual language understanding and generation tasks. Recently, the performance of the neural word alignment models has exceeded that of statistical models. However, they heavily rely on sophisticated translation models. In this study, we propose a super lightweight unsupervised word alignment model named MirrorAlign, in which bidirectional symmetric attention trained with a contrastive learning objective is introduced, and an agreement loss is employed to bind the attention maps, such that the alignments follow mirror-like symmetry hypothesis. Experimental results on several public benchmarks demonstrate that our model achieves competitive, if not better, performance compared to the state of the art in word alignment while significantly reducing the training and decoding time on average. Further ablation analysis and case studies show the superiority of our proposed MirrorAlign. Notably, we recognize our model as a pioneer attempt to unify bilingual word embedding and word alignments. Encouragingly, our approach achieves {16.4X speedup} against GIZA++, and {50X parameter compression} compared with the Transformer-based alignment methods. We release our code to facilitate the community: https://github.com/moore3930/MirrorAlign., Comment: IWSLT 2022 (oral)

Nursing homes (NHs) are critical healthcare infrastructures for caring frail older adults with 24/7 formal care and personal assistance. Adequate NH resource planning is of great importance to ensure desired quality of care and resident outcomes yet challenging. The challenge lies in the heterogeneous service demand of NH residents, due to the varied individual characteristics, the diverse dwelling duration with multiple competing discharge dispositions, and the diverse service need. Existing healthcare staffing literature often assumed a homogeneous population of NH residents and neglected the complexity of service demand heterogeneity. This work proposes an analytics-based modeling framework with a user-friendly decision support platform for NH resource planning. The proposed framework characterizes the heterogeneous service demand of NH residents via novel integration of advanced statistical modeling, computer simulation and optimization techniques. We further provide a case study using real data from our industrial collaborator to demonstrate the effectiveness and superior performance of the proposed work. The impacts of service utilization heterogeneity and service need heterogeneity on resource planning decisions are investigated as well., Comment: 19 pages

Modeling politeness across cultures helps to improve intercultural communication by uncovering what is considered appropriate and polite. We study the linguistic features associated with politeness across US English and Mandarin Chinese. First, we annotate 5,300 Twitter posts from the US and 5,300 Sina Weibo posts from China for politeness scores. Next, we develop an English and Chinese politeness feature set, `PoliteLex'. Combining it with validated psycholinguistic dictionaries, we then study the correlations between linguistic features and perceived politeness across cultures. We find that on Mandarin Weibo, future-focusing conversations, identifying with a group affiliation, and gratitude are considered to be more polite than on English Twitter. Death-related taboo topics, lack of or poor choice of pronouns, and informal language are associated with higher impoliteness on Mandarin Weibo compared to English Twitter. Finally, we build language-based machine learning models to predict politeness with an F1 score of 0.886 on Mandarin Weibo and a 0.774 on English Twitter., Comment: Accepted for CSCW 2020. To be published in PACM HCI

Facial image retrieval plays a significant role in forensic investigations where an untrained witness tries to identify a suspect from a massive pool of images. However, due to the difficulties in describing human facial appearances verbally and directly, people naturally tend to depict by referring to well-known existing images and comparing specific areas of faces with them and it is also challenging to provide complete comparison at each time. Therefore, we propose an end-to-end framework to retrieve facial images with relevance feedback progressively provided by the witness, enabling an exploitation of history information during multiple rounds and an interactive and iterative approach to retrieving the mental image. With no need of any extra annotations, our model can be applied at the cost of a little response effort. We experiment on \texttt{CelebA} and evaluate the performance by ranking percentile and achieve 99\% under the best setting. Since this topic remains little explored to the best of our knowledge, we hope our work can serve as a stepping stone for further research.

This paper proposes a knowledge distillation method for foreground object search (FoS). Given a background and a rectangle specifying the foreground location and scale, FoS retrieves compatible foregrounds in a certain category for later image composition. Foregrounds within the same category can be grouped into a small number of patterns. Instances within each pattern are compatible with any query input interchangeably. These instances are referred to as interchangeable foregrounds. We first present a pipeline to build pattern-level FoS dataset containing labels of interchangeable foregrounds. We then establish a benchmark dataset for further training and testing following the pipeline. As for the proposed method, we first train a foreground encoder to learn representations of interchangeable foregrounds. We then train a query encoder to learn query-foreground compatibility following a knowledge distillation framework. It aims to transfer knowledge from interchangeable foregrounds to supervise representation learning of compatibility. The query feature representation is projected to the same latent space as interchangeable foregrounds, enabling very efficient and interpretable instance-level search. Furthermore, pattern-level search is feasible to retrieve more controllable, reasonable and diverse foregrounds. The proposed method outperforms the previous state-of-the-art by 10.42% in absolute difference and 24.06% in relative improvement evaluated by mean average precision (mAP). Extensive experimental results also demonstrate its efficacy from various aspects. The benchmark dataset and code will be release shortly., Comment: This paper will appear at ECCV 2020

Researchers have attempted utilizing deep neural network (DNN) to learn novel local features from images inspired by its recent successes on a variety of vision tasks. However, existing DNN-based algorithms have not achieved such remarkable progress that could be partly attributed to insufficient utilization of the interactive characters between local feature detector and descriptor. To alleviate these difficulties, we emphasize two desired properties, i.e., repeatability and reliability, to simultaneously summarize the inherent and interactive characters of local feature detector and descriptor. Guided by these properties, a self-supervised framework, namely self-evolving keypoint detection and description (SEKD), is proposed to learn an advanced local feature model from unlabeled natural images. Additionally, to have performance guarantees, novel training strategies have also been dedicatedly designed to minimize the gap between the learned feature and its properties. We benchmark the proposed method on homography estimation, relative pose estimation, and structure-from-motion tasks. Extensive experimental results demonstrate that the proposed method outperforms popular hand-crafted and DNN-based methods by remarkable margins. Ablation studies also verify the effectiveness of each critical training strategy. We will release our code along with the trained model publicly.

To build commercial robots, skid-steering mechanical design is of increased popularity due to its manufacturing simplicity and unique mechanism. However, these also cause significant challenges on software and algorithm design, especially for the pose estimation (i.e., determining the robot's rotation and position) of skid-steering robots, since they change their orientation with an inevitable skid. To tackle this problem, we propose a probabilistic sliding-window estimator dedicated to skid-steering robots, using measurements from a monocular camera, the wheel encoders, and optionally an inertial measurement unit (IMU). Specifically, we explicitly model the kinematics of skid-steering robots by both track instantaneous centers of rotation (ICRs) and correction factors, which are capable of compensating for the complexity of track-to-terrain interaction, the imperfectness of mechanical design, terrain conditions and smoothness, etc. To prevent performance reduction in robots' long-term missions, the time- and location- varying kinematic parameters are estimated online along with pose estimation states in a tightly-coupled manner. More importantly, we conduct in-depth observability analysis for different sensors and design configurations in this paper, which provides us with theoretical tools in making the correct choice when building real commercial robots. In our experiments, we validate the proposed method by both simulation tests and real-world experiments, which demonstrate that our method outperforms competing methods by wide margins., Comment: 19 pages in total

Conventional uncertainty quantification methods usually lacks the capability of dealing with high-dimensional problems due to the curse of dimensionality. This paper presents a semi-supervised learning framework for dimension reduction and reliability analysis. An autoencoder is first adopted for mapping the high-dimensional space into a low-dimensional latent space, which contains a distinguishable failure surface. Then a deep feedforward neural network (DFN) is utilized to learn the mapping relationship and reconstruct the latent space, while the Gaussian process (GP) modeling technique is used to build the surrogate model of the transformed limit state function. During the training process of the DFN, the discrepancy between the actual and reconstructed latent space is minimized through semi-supervised learning for ensuring the accuracy. Both labeled and unlabeled samples are utilized for defining the loss function of the DFN. Evolutionary algorithm is adopted to train the DFN, then the Monte Carlo simulation method is used for uncertainty quantification and reliability analysis based on the proposed framework. The effectiveness is demonstrated through a mathematical example.

The inherent heavy computation of deep neural networks prevents their widespread applications. A widely used method for accelerating model inference is quantization, by replacing the input operands of a network using fixed-point values. Then the majority of computation costs focus on the integer matrix multiplication accumulation. In fact, high-bit accumulator leads to partially wasted computation and low-bit one typically suffers from numerical overflow. To address this problem, we propose an overflow aware quantization method by designing trainable adaptive fixed-point representation, to optimize the number of bits for each input tensor while prohibiting numeric overflow during the computation. With the proposed method, we are able to fully utilize the computing power to minimize the quantization loss and obtain optimized inference performance. To verify the effectiveness of our method, we conduct image classification, object detection, and semantic segmentation tasks on ImageNet, Pascal VOC, and COCO datasets, respectively. Experimental results demonstrate that the proposed method can achieve comparable performance with state-of-the-art quantization methods while accelerating the inference process by about 2 times.

Monocular 3D object detection is an essential component in autonomous driving while challenging to solve, especially for those occluded samples which are only partially visible. Most detectors consider each 3D object as an independent training target, inevitably resulting in a lack of useful information for occluded samples. To this end, we propose a novel method to improve the monocular 3D object detection by considering the relationship of paired samples. This allows us to encode spatial constraints for partially-occluded objects from their adjacent neighbors. Specifically, the proposed detector computes uncertainty-aware predictions for object locations and 3D distances for the adjacent object pairs, which are subsequently jointly optimized by nonlinear least squares. Finally, the one-stage uncertainty-aware prediction structure and the post-optimization module are dedicatedly integrated for ensuring the run-time efficiency. Experiments demonstrate that our method yields the best performance on KITTI 3D detection benchmark, by outperforming state-of-the-art competitors by wide margins, especially for the hard samples., Comment: CVPR 2020 accepted

Online hand gesture recognition (HGR) techniques are essential in augmented reality (AR) applications for enabling natural human-to-computer interaction and communication. In recent years, the consumer market for low-cost AR devices has been rapidly growing, while the technology maturity in this domain is still limited. Those devices are typical of low prices, limited memory, and resource-constrained computational units, which makes online HGR a challenging problem. To tackle this problem, we propose a lightweight and computationally efficient HGR framework, namely LE-HGR, to enable real-time gesture recognition on embedded devices with low computing power. We also show that the proposed method is of high accuracy and robustness, which is able to reach high-end performance in a variety of complicated interaction environments. To achieve our goal, we first propose a cascaded multi-task convolutional neural network (CNN) to simultaneously predict probabilities of hand detection and regress hand keypoint locations online. We show that, with the proposed cascaded architecture design, false-positive estimates can be largely eliminated. Additionally, an associated mapping approach is introduced to track the hand trace via the predicted locations, which addresses the interference of multi-handedness. Subsequently, we propose a trace sequence neural network (TraceSeqNN) to recognize the hand gesture by exploiting the motion features of the tracked trace. Finally, we provide a variety of experimental results to show that the proposed framework is able to achieve state-of-the-art accuracy with significantly reduced computational cost, which are the key properties for enabling real-time applications in low-cost commercial devices such as mobile devices and AR/VR headsets., Comment: Published in: 2019 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)

Fast-pyrolysis bio-oil is an important feedstock for energy application and value-added chemicals production. Phase instability of fast-pyrolysis bio-oil is a key problem taking place during bio-oil handling, storage and transport, leading to undesired severe consequences including pumping problems, blockages and combustion issues. This project reports a systematic study into the stability and phase behaviour of bio-oil and the development of a set of phase diagrams of understanding and controlling bio-oil phase stability.

Xiaomin Cai,1,* Bin Wei,1,2,* Lele Li,1,* Xiaofeng Chen,1 Jing Yang,1 Xiaofei Li,1 Xiaozheng Jiang,1 Mu Lv,1 Mingyang Li,1 Yumeng Lin,3 Qiang Xu,3 Wenjie Guo,3 Yanhong Gu1 1Department of Oncology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, People’s Republic of China; 2Department of Oncology, The Affiliated Huaian No.1 People’s Hospital of Nanjing Medical University, Huai’an 223300, People’s Republic of China; 3State Key Laboratory of Pharmaceutical Biotechnology, School of Life Sciences, Nanjing University, Nanjing, People’s Republic of China*These authors contributed equally to this workCorrespondence: Yanhong GuDepartment of Oncology, The First Affiliated Hospital of Nanjing Medical University, 300 Guangzhou Road, Nanjing 210029, People’s Republic of ChinaEmail guyhphd@163.comWenjie GuoState Key Laboratory of Pharmaceutical Biotechnology, School of Life Sciences, Nanjing University, 163 Xianlin Avenue, Nanjing 210023, People’s Republic of ChinaEmail guowj@nju.edu.cnPurpose: Apatinib is an inhibitor of VEGFR2 (vascular endothelial growth factor receptor 2) that has attracted a great deal of attention due to its promotion of anticancer activity. In the present study, we investigated the therapeutic effects of apatinib against colorectal cancer (CRC) and examined the underlying mechanism.Materials and Methods: Both in vivo and in vitro assays were conducted to study the effect of apatinib on CRC. To elucidate the associated mechanism, RNA-seq (transcriptome) analysis was conducted on apatinib-treated HCT116 cells.Results: Apatinib showed antiproliferative and proapoptotic effects, induced G0/G1 arrest and blocked cell migration and invasion in CRC. An analysis of the mechanism associated with apatinib activity demonstrated that by interacting with VEGFR2, apatinib decreased p-Src, p-Akt, and p-GSK3β levels, which further increased β-catenin ubiquitinatio

Lei Yang,1 Guangping Zhou,2 Mingyang Li,1 Yan Li,1 Liqing Yang,1 Qin Fu,1 Ye Tian1 1Orthopedics Department, Shengjing Hospital of China Medical University, Shenyang, Liaoning Province, People’s Republic of China; 2Orthopedics Department, Shenyang Orthopedics Hospital, Shenyang, Liaoning Province, People’s Republic of ChinaCorrespondence: Qin Fu Tel +86-18940251086Email fuqsj_hospital@126.comPurpose: Osteocyte network structure correlates with bone material quality. This network is profoundly altered in diabetic mice; however, the underlying mechanisms are unknown. The gap junction protein connexin 43 (Cx43) is necessary for normal osteocyte function and osteocyte network formation. Here, we evaluated Cx43 expression in patients with diabetes, the effect of high glucose on Cx43 expression, and the function of Cx43 gap junctions and hemichannels in osteocyte-like MLO-Y4 (MLO-Y4) cells.Patients and Methods: Human cortical bone samples were obtained from patients with or without type II diabetes mellitus (T2DM) who underwent arthroplasty surgery to treat osteoporosis-induced femoral neck fracture.Cx43 expression was quantified in human cortical bone samples from both groups of patients and MLO-Y4 cells. The functions of Cx43 gap junctions and hemichannels in MLO-Y4 cells were evaluated using dye transfer and dye uptake assays, respectively. Furthermore, we evaluated levels of membrane Cx43 (mCx43), the functional form, and p38MAPK/ERK1/2 signaling, which is involved in mCx43 internalization, to characterize the mechanism of decreased Cx43 expression and gap junctions and hemichannels function.Results: Osteocyte Cx43 expression was decreased in femoral neck cortical bone samples of patients with T2DM patients compared with the non-diabetic control group. In addition, Cx43 expression was decreased in MLO-Y4 cells treated with high glucose. The functions of Cx43 gap junctions and hemichannels were inhibited in MLO-Y4 cells treated with high glucose. mCx

Ultrafast-charging energy storage devices are attractive for powering personal electronics and electric vehicles. Most ultrafast-charging devices are made of carbonaceous materials such as chemically converted graphene and carbon nanotubes. Yet, their relatively low electrical conductivity may restrict their performance at ultrahigh charging rate. Here, we report the fabrication of a porous titanium nitride (TiN) paper as an alternative electrode material for ultrafast-charging devices. The TiN paper shows an excellent conductivity of 3.67 × 104 S m-1, which is considerably higher than most carbon-based electrodes. The paper-like structure also contains a combination of large pores between interconnected nanobelts and mesopores within the nanobelts. This unique electrode enables fast charging by simultaneously providing efficient ion diffusion and electron transport. The supercapacitors (SCs) made of TiN paper enable charging/discharging at an ultrahigh scan rate of 100 V s-1 in a wide voltage window of 1.5 V in Na2SO4 neutral electrolyte. It has an outstanding response time with a characteristic time constant of 4 ms. Significantly, the TiN paper-based SCs also show zero capacitance loss after 200,000 cycles, which is much better than the stability performance reported for other metal nitride SCs. Furthermore, the device shows great promise in scalability. The filtration method enables good control of the thickness and mass loading of TiN electrodes and devices.

We herein demonstrate the unusual effectiveness of two strategies in combination to enhance photoelectrochemical water splitting. First, the work function adjustment via molybdenum (Mo) doping significantly reduces the interfacial energy loss and increases the open-circuit photovoltage of bismuth vanadate (BiVO4) photoelectrochemical cells. Second, the creation and optimization of the heterojunction of boron (B) doping carbon nitride (C3N4) and Mo doping BiVO4 to enforce directional charge transfer, accomplished by work function adjustment via B doping for C3N4, substantially boost the charge separation of photo-generated electron-hole pairs at the B-C3N4 and Mo-BiVO4 interface. The synergy between the above efforts have significantly reduced the onset potential, and enhanced charge separation and optical properties of the BiVO4-based photoanode, culminating in achieving a record applied bias photon-to-current efficiency of 2.67% at 0.54 V vs. the reversible hydrogen electrode. This work sheds light on designing and fabricating the semiconductor structures for the next-generation photoelectrodes. © 2019, The Author(s).