346 citations · 2.2k across the 66 of their papers we have counts for
66 papers
Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training
Xiao-Ming Wu, Dian Zheng, Zuhao Liu +1
Binarization of neural networks is a dominant paradigm in neural networks compression. The pioneering work BinaryConnect uses Straight Through Estimator (STE) to mimic the gradient…
PSLT: A Light-weight Vision Transformer with Ladder Self-Attention and Progressive Shift
Gaojie Wu, Wei-Shi Zheng, Yutong Lu +1
Vision Transformer (ViT) has shown great potential for various visual tasks due to its ability to model long-range dependency. However, ViT requires a large amount of computing res…
Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractor
Yang Yang, Zhiying Cui, Junjie Xu +3
Deep learning has shown its human-level performance in various applications. However, current deep learning models are characterised by catastrophic forgetting of old knowledge whe…
Cross-Camera Trajectories Help Person Retrieval in a Camera Network
Xin Zhang, Xiaohua Xie, Jianhuang Lai +1
We are concerned with retrieving a query person from multiple videos captured by a non-overlapping camera network. Existing methods often rely on purely visual matching or consider…
Letter-level Online Writer Identification
Zelin Chen, Hong-Xing Yu, Ancong Wu +1
Writer identification (writer-id), an important field in biometrics, aims to identify a writer by their handwriting. Identification in existing writer-id studies requires a complet…
Understanding of Kernels in CNN Models by Suppressing Irrelevant Visual Features in Images
Jia-Xin Zhuang, Wanying Tao, Jianfei Xing +3
Deep learning models have shown their superior performance in various vision tasks. However, the lack of precisely interpreting kernels in convolutional neural networks (CNNs) is b…
Discriminative Distillation to Reduce Class Confusion in Continual Learning
Changhong Zhong, Zhiying Cui, Ruixuan Wang +1
Successful continual learning of new knowledge would enable intelligent systems to recognize more and more classes of objects. However, current intelligent systems often fail to co…
Cross-Camera Feature Prediction for Intra-Camera Supervised Person Re-identification across Distant Scenes
Wenhang Ge, Chunyan Pan, Ancong Wu +2
Person re-identification (Re-ID) aims to match person images across non-overlapping camera views. The majority of Re-ID methods focus on small-scale surveillance systems in which e…
Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization
Fa-Ting Hong, Jia-Chang Feng, Dan Xu +2
Weakly supervised temporal action localization (WS-TAL) is a challenging task that aims to localize action instances in the given video with video-level categorical supervision. Bo…
Discriminator-Free Generative Adversarial Attack
Shaohao Lu, Yuqiao Xian, Ke Yan +5
The Deep Neural Networks are vulnerable toadversarial exam-ples(Figure 1), making the DNNs-based systems collapsed byadding the inconspicuous perturbations to the images. Most of t…
Augmented 2D-TAN: A Two-stage Approach for Human-centric Spatio-Temporal Video Grounding
Chaolei Tan, Zihang Lin, Jian-Fang Hu +2
We propose an effective two-stage approach to tackle the problem of language-based Human-centric Spatio-Temporal Video Grounding (HC-STVG) task. In the first stage, we propose an A…
Learning Multi-Attention Context Graph for Group-Based Re-Identification
Yichao Yan, Jie Qin, Bingbing Ni +6
Learning to re-identify or retrieve a group of people across non-overlapped camera systems has important applications in video surveillance. However, most existing methods focus on…
Preserving Earlier Knowledge in Continual Learning with the Help of All Previous Feature Extractors
Zhuoyun Li, Changhong Zhong, Sijia Liu +2
Continual learning of new knowledge over time is one desirable capability for intelligent systems to recognize more and more classes of objects. Without or with very limited amount…
Combined Depth Space based Architecture Search For Person Re-identification
Hanjun Li, Gaojie Wu, Wei-Shi Zheng
Most works on person re-identification (ReID) take advantage of large backbone networks such as ResNet, which are designed for image classification instead of ReID, for feature ext…
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection
Jia-Chang Feng, Fa-Ting Hong, Wei-Shi Zheng
Weakly supervised video anomaly detection (WS-VAD) is to distinguish anomalies from normal events based on discriminative representations. Most existing works are limited in insuff…
Towards Unbiased COVID-19 Lesion Localisation and Segmentation via Weakly Supervised Learning
Yang Yang, Jiancong Chen, Ruixuan Wang +5
Despite tremendous efforts, it is very challenging to generate a robust model to assist in the accurate quantification assessment of COVID-19 on chest CT images. Due to the nature…
One for More: Selecting Generalizable Samples for Generalizable ReID Model
Enwei Zhang, Xinyang Jiang, Hao Cheng +7
Current training objectives of existing person Re-IDentification (ReID) models only ensure that the loss of the model decreases on selected training batch, with no regards to the p…
Contextual Heterogeneous Graph Network for Human-Object Interaction Detection
Hai Wang, Wei-Shi Zheng, Ling Yingbiao
Human-object interaction(HOI) detection is an important task for understanding human activity. Graph structure is appropriate to denote the HOIs in the scene. Since there is an sub…
Devil's in the Details: Aligning Visual Clues for Conditional Embedding in Person Re-Identification
Fufu Yu, Xinyang Jiang, Yifei Gong +5
Although Person Re-Identification has made impressive progress, difficult cases like occlusion, change of view-pointand similar clothing still bring great challenges. Besides overa…
Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians
Shizhen Zhao, Changxin Gao, Jun Zhang +7
In the conventional person Re-ID setting, it is widely assumed that cropped person images are for each individual. However, in a crowded scene, off-shelf-detectors may generate bou…
MINI-Net: Multiple Instance Ranking Network for Video Highlight Detection
Fa-Ting Hong, Xuanteng Huang, Wei-Hong Li +1
We address the weakly supervised video highlight detection problem for learning to detect segments that are more attractive in training videos given their video event label but wit…
Adaptive Interaction Modeling via Graph Operations Search
Haoxin Li, Wei-Shi Zheng, Yu Tao +2
Interaction modeling is important for video action analysis. Recently, several works design specific structures to model interactions in videos. However, their structures are manua…
Learning to Detect Important People in Unlabelled Images for Semi-supervised Important People Detection
Fa-Ting Hong, Wei-Hong Li, Wei-Shi Zheng
Important people detection is to automatically detect the individuals who play the most important roles in a social event image, which requires the designed model to understand a h…
Person Re-identification by Contour Sketch under Moderate Clothing Change
Qize Yang, Ancong Wu, Wei-Shi Zheng
Person re-identification (re-id), the process of matching pedestrian images across different camera views, is an important task in visual surveillance. Substantial development of r…