120 citations · 850 across the 61 of their papers we have counts for
54 papers · 1 filter
MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking
Zheng Qin, Sanping Zhou, Le Wang +3
The main challenge of Multi-Object Tracking~(MOT) lies in maintaining a continuous trajectory for each target. Existing methods often learn reliable motion patterns to match the sa…
Exploring Discrete Diffusion Models for Image Captioning
Zixin Zhu, Yixuan Wei, Jianfeng Wang +7
The image captioning task is typically realized by an auto-regressive method that decodes the text tokens one by one. We present a diffusion-based captioning model, dubbed the name…
Social Interpretable Tree for Pedestrian Trajectory Prediction
Liushuai Shi, Le Wang, Chengjiang Long +4
Understanding the multiple socially-acceptable future behaviors is an essential task for many vision applications. In this paper, we propose a tree-based method, termed as Social I…
E^2TAD: An Energy-Efficient Tracking-based Action Detector
Xin Hu, Zhenyu Wu, Hao-Yu Miao +8
Video action detection (spatio-temporal action localization) is usually the starting point for human-centric intelligent analysis of videos nowadays. It has high practical impacts…
Progressive Backdoor Erasing via connecting Backdoor and Adversarial Attacks
Bingxu Mu, Zhenxing Niu, Le Wang +3
Deep neural networks (DNNs) are known to be vulnerable to both backdoor attacks as well as adversarial attacks. In the literature, these two types of attacks are commonly treated a…
Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning
Siming Yan, Zhenpei Yang, Haoxiang Li +5
This paper advocates the use of implicit surface representation in autoencoder-based self-supervised 3D representation learning. The most popular and accessible 3D representation,…
Weakly-guided Self-supervised Pretraining for Temporal Activity Detection
Kumara Kahatapitiya, Zhou Ren, Haoxiang Li +3
Temporal Activity Detection aims to predict activity classes per frame, in contrast to video-level predictions in Activity Classification (i.e., Activity Recognition). Due to the e…
DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval
Aichun Zhu, Zijie Wang, Yifeng Li +5
Many previous methods on text-based person retrieval tasks are devoted to learning a latent common space mapping, with the purpose of extracting modality-invariant features from bo…
Enriching Local and Global Contexts for Temporal Action Localization
Zixin Zhu, Wei Tang, Le Wang +2
Effectively tackling the problem of temporal action localization (TAL) necessitates a visual representation that jointly pursues two confounding goals, i.e., fine-grained discrimin…
Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking
Yiding Yang, Zhou Ren, Haoxiang Li +3
Multi-person pose estimation and tracking serve as crucial steps for video understanding. Most state-of-the-art approaches rely on first estimating poses in each frame and only the…
Adversarial Attack and Defense in Deep Ranking
Mo Zhou, Le Wang, Zhenxing Niu +3
Deep Neural Network classifiers are vulnerable to adversarial attack, where an imperceptible perturbation could result in misclassification. However, the vulnerability of DNN-based…
Video Imprint
Zhanning Gao, Le Wang, Nebojsa Jojic +3
A new unified video analytics framework (ER3) is proposed for complex event retrieval, recognition and recounting, based on the proposed video imprint representation, which exploit…
Semi-supervised Long-tailed Recognition using Alternate Sampling
Bo Liu, Haoxiang Li, Hao Kang +2
Main challenges in long-tailed recognition come from the imbalanced data distribution and sample scarcity in its tail classes. While techniques have been proposed to achieve a more…
GistNet: a Geometric Structure Transfer Network for Long-Tailed Recognition
Bo Liu, Haoxiang Li, Hao Kang +2
The problem of long-tailed recognition, where the number of examples per class is highly unbalanced, is considered. It is hypothesized that the well known tendency of standard clas…
Breadcrumbs: Adversarial Class-Balanced Sampling for Long-tailed Recognition
Bo Liu, Haoxiang Li, Hao Kang +2
The problem of long-tailed recognition, where the number of examples per class is highly unbalanced, is considered. While training with class-balanced sampling has been shown effec…
Sparse Pose Trajectory Completion
Bo Liu, Mandar Dixit, Roland Kwitt +2
We propose a method to learn, even using a dataset where objects appear only in sparsely sampled views (e.g. Pix3D), the ability to synthesize a pose trajectory for an arbitrary re…
SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction
Liushuai Shi, Le Wang, Chengjiang Long +4
Pedestrian trajectory prediction is a key technology in autopilot, which remains to be very challenging due to complex interactions between pedestrians. However, previous works bas…
Weakly Supervised Temporal Action Localization Through Learning Explicit Subspaces for Action and Context
Ziyi Liu, Le Wang, Wei Tang +3
Weakly-supervised Temporal Action Localization (WS-TAL) methods learn to localize temporal starts and ends of action instances in a video under only video-level supervision. Existi…
ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action Localization
Ziyi Liu, Le Wang, Qilin Zhang +4
The object of Weakly-supervised Temporal Action Localization (WS-TAL) is to localize all action instances in an untrimmed video with only video-level supervision. Due to the lack o…
Beyond Visual Attractiveness: Physically Plausible Single Image HDR Reconstruction for Spherical Panoramas
Wei Wei, Li Guan, Yue Liu +4
HDR reconstruction is an important task in computer vision with many industrial needs. The traditional approaches merge multiple exposure shots to generate HDRs that correspond to…
Diverse Semantic Image Synthesis via Probability Distribution Modeling
Zhentao Tan, Menglei Chai, Dongdong Chen +5
Semantic image synthesis, translating semantic layouts to photo-realistic images, is a one-to-many mapping problem. Though impressive progress has been recently made, diverse seman…
Deep Model Intellectual Property Protection via Deep Watermarking
Jie Zhang, Dongdong Chen, Jing Liao +4
Despite the tremendous success, deep neural networks are exposed to serious IP infringement risks. Given a target deep model, if the attacker knows its full information, it can be…
Efficient Semantic Image Synthesis via Class-Adaptive Normalization
Zhentao Tan, Dongdong Chen, Qi Chu +6
Spatially-adaptive normalization (SPADE) is remarkably successful recently in conditional semantic image synthesis \cite{park2019semantic}, which modulates the normalized activatio…
Passport-aware Normalization for Deep Model Protection
Jie Zhang, Dongdong Chen, Jing Liao +3
Despite tremendous success in many application scenarios, deep learning faces serious intellectual property (IP) infringement threats. Considering the cost of designing and trainin…