A5024579621- Human Pose and Action Recognition
- Gait Recognition and Analysis
- Video Surveillance and Tracking Methods
- Advanced Image and Video Retrieval Techniques
- Image Retrieval and Classification Techniques
- Hand Gesture Recognition Systems
- Diabetic Foot Ulcer Assessment and Management
- Advanced Neural Network Applications
- Anomaly Detection Techniques and Applications
- Face recognition and analysis
- Advanced Vision and Imaging
- Visual Attention and Saliency Detection
- Face and Expression Recognition
- Remote-Sensing Image Classification
- Robotics and Sensor-Based Localization
- Domain Adaptation and Few-Shot Learning
- Circular RNAs in diseases
- Multimodal Machine Learning Applications
- Indoor and Outdoor Localization Technologies
- Emotion and Mood Recognition
- Video Analysis and Summarization
- Algorithms and Data Compression
- Advanced Clustering Algorithms Research
- Gaze Tracking and Assistive Technology
- Topological and Geometric Data Analysis
Beijing Normal University
2021-2025
Center for Excellence in Brain Science and Intelligence Technology
2017-2022
Institute of Automation
2011-2022
University of Chinese Academy of Sciences
2017-2022
Chinese Academy of Sciences
2011-2020
Shandong Institute of Automation
2012-2020
First Affiliated Hospital of Henan University
2017
This paper studies an approach to gait based human identification via similarity learning by deep convolutional neural networks (CNNs). With a pretty small group of labeled multi-view walking videos, we can train recognize the most discriminative changes patterns which suggest change identity. To best our knowledge, this is first work on CNNs for recognition in literature. Here, provide extensive empirical evaluation terms various scenarios, namely, cross-view and cross-walking-condition,...
With the rapid growth of web images, hashing has received increasing interests in large scale image retrieval. Research efforts have been devoted to learning compact binary codes that preserve semantic similarity based on labels. However, most these methods are designed handle simple similarity. The complex multi-level structure images associated with multiple labels not yet well explored. Here we propose a deep ranking method for hash functions multilevel between multi-label images. In our...
While feedforward deep convolutional neural networks (CNNs) have been a great success in computer vision, it is important to note that the human visual cortex generally contains more feedback than connections. In this paper, we will briefly introduce background of feedbacks cortex, which motivates us develop computational mechanism networks. addition inference traditional networks, loop introduced infer activation status hidden layer neurons according "goal" network, e.g., high-level...
One key challenging issue of facial expression recognition is to capture the dynamic variation physical structure from videos. In this paper, we propose a part-based hierarchical bidirectional recurrent neural network (PHRNN) analyze information temporal sequences. Our PHRNN models morphological variations and dynamical evolution expressions, which effective extract "temporal features" based on landmarks (geometry information) consecutive frames. Meanwhile, in order complement still...
Gait recognition, applied to identify individual walking patterns in a long-distance, is one of the most promising video-based biometric technologies. At present, gait recognition methods take whole human body as unit establish spatio-temporal representations. However, we have observed that different parts possess evidently various visual appearances and movement during walking. In latest literature, employing partial features for description has been verified being beneficial recognition....
Image classification is a hot topic in computer vision and pattern recognition. Feature coding, as key component of image classification, has been widely studied over the past several years, number coding algorithms have proposed. However, there no comprehensive study concerning connections between different methods, especially how they evolved. In this paper, we first make survey on various feature including their motivations mathematical representations, then exploit relations, based which...
The codebook based (bag-of-words) model is a widely applied for image classification. We analyze recent coding strategies in this model, and find that saliency the fundamental characteristic of coding. means if visual code much closer to descriptor than other codes, it will obtain very strong response. salient representation under maximum pooling operation leads state-of-the-art performance on many databases competitions. However, most current schemes do not recognize role representation, so...
With the rapid growth of web images, hashing has received increasing interests in large scale image retrieval. Research efforts have been devoted to learning compact binary codes that preserve semantic similarity based on labels. However, most these methods are designed handle simple similarity. The complex multilevel structure images associated with multiple labels not yet well explored. Here we propose a deep ranking method for hash functions between multi-label images. In our approach,...
Recently, deep learning-based cross-view gait recognition has become popular owing to the strong capacity of convolutional neural networks (CNNs). Current learning methods often rely on loss functions used widely in task face recognition, e.g., contrastive and triplet loss. These have problem hard negative mining. In this paper, a robust, effective, gait-related function, called angle center (ACL), is proposed learn discriminative features. The function robust different local parts temporal...
This paper proposes to learn features from sets of labeled raw images. With this method, the problem over-fitting can be effectively suppressed, so that deep CNNs trained scratch with a small number training data, i.e., 420 albums about 30 000 photos. method deal images, no matter if bear temporal structures. A typical approach sequential image analysis usually leverages motions between adjacent frames, while proposed focuses on capturing co-occurrences and frequencies features....
The rapid advances of transportation infrastructure have led to a dramatic increase in the demand for smart systems capable monitoring traffic and street safety. Fundamental these applications are community-based evaluation platform benchmark object detection multi-object tracking. To this end, we organize AVSS2017 Challenge on Advanced Traffic Monitoring, conjunction with International Workshop Street Surveillance Safety Security (IWT4S), evaluate state-of-the-art tracking algorithms...
Gait recognition is beneficial for a variety of applications, including video surveillance, crime scene investigation, and social security, to mention few. However, gait often suffers from multiple exterior factors in real scenes, such as carrying conditions, wearing overcoats, diverse viewing angles. Recently, various deep learning-based methods have achieved promising results, but they tend extract one the salient features using fixed-weighted convolutional networks, do not well consider...
Gait recognition plays a special role in visual surveillance due to its unique advantage, <i>e.g.</i>, long-distance, cross-view and non-cooperative recognition. However, it has not yet been widely applied. One reason for this awkwardness is the lack of truly big dataset captured practical outdoor scenarios. Here, “big” at least means: (1) huge amount gait videos, (2) sufficient subjects, (3) rich attributes, (4) spatial temporal variations. Moreover, most existing large-scale...
Gait depicts individuals' unique and distinguishing walking patterns has become one of the most promising biometric features for human identification. As a fine-grained recognition task, gait is easily affected by many factors usually requires large amount completely annotated data that costly insatiable. This paper proposes large-scale self-supervised benchmark with contrastive learning, aiming to learn general representation from massive unlabelled videos practical applications via...