32 citations · 71 across the 13 of their papers we have counts for
13 papers
GeT: Generative Target Structure Debiasing for Domain Adaptation
Can Zhang, Gim Hee Lee
Domain adaptation (DA) aims to transfer knowledge from a fully labeled source to a scarcely labeled or totally unlabeled target under domain shift. Recently, semi-supervised learni…
Improving Scene Graph Generation with Superpixel-Based Interaction Learning
Jingyi Wang, Can Zhang, Jinfa Huang +2
Recent advances in Scene Graph Generation (SGG) typically model the relationships among entities utilizing box-level features from pre-defined detectors. We argue that an overlooke…
Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs
Jingyi Wang, Jinfa Huang, Can Zhang +1
Dynamic scene graphs generated from video clips could help enhance the semantic visual understanding in a wide range of challenging tasks such as environmental perception, autonomo…
LocVTP: Video-Text Pre-training for Temporal Localization
Meng Cao, Tianyu Yang, Junwu Weng +3
Video-Text Pre-training (VTP) aims to learn transferable representations for various downstream tasks from large-scale web videos. To date, almost all existing VTP methods are limi…
Unsupervised Pre-training for Temporal Action Localization Tasks
Can Zhang, Tianyu Yang, Junwu Weng +3
Unsupervised video representation learning has made remarkable achievements in recent years. However, most existing methods are designed and optimized for video classification. The…
On Pursuit of Designing Multi-modal Transformer for Video Grounding
Meng Cao, Long Chen, Mike Zheng Shou +2
Video grounding aims to localize the temporal segment corresponding to a sentence query from an untrimmed video. Almost all existing video grounding methods fall into two framework…
Deep Motion Prior for Weakly-Supervised Temporal Action Localization
Meng Cao, Can Zhang, Long Chen +2
Weakly-Supervised Temporal Action Localization (WSTAL) aims to localize actions in untrimmed videos with only video-level labels. Currently, most state-of-the-art WSTAL methods fol…
Long-Short Temporal Modeling for Efficient Action Recognition
Liyu Wu, Yuexian Zou, Can Zhang
Efficient long-short temporal modeling is key for enhancing the performance of action recognition task. In this paper, we propose a new two-stream action recognition network, terme…
SRF-Net: Selective Receptive Field Network for Anchor-Free Temporal Action Detection
Ranyu Ning, Can Zhang, Yuexian Zou
Temporal action detection (TAD) is a challenging task which aims to temporally localize and recognize the human action in untrimmed videos. Current mainstream one-stage TAD approac…
All You Need is a Second Look: Towards Arbitrary-Shaped Text Detection
Meng Cao, Can Zhang, Dongming Yang +1
Arbitrary-shaped text detection is a challenging task since curved texts in the wild are of the complex geometric layouts. Existing mainstream methods follow the instance segmentat…
RR-Net: Injecting Interactive Semantics in Human-Object Interaction Detection
Dongming Yang, Yuexian Zou, Can Zhang +2
Human-Object Interaction (HOI) detection devotes to learn how humans interact with surrounding objects. Latest end-to-end HOI detectors are short of relation reasoning, which leads…
CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning
Can Zhang, Meng Cao, Dongming Yang +2
Weakly-supervised temporal action localization (WS-TAL) aims to localize actions in untrimmed videos with only video-level labels. Most existing models follow the "localization by…
PAN: Towards Fast Action Recognition via Learning Persistence of Appearance
Can Zhang, Yuexian Zou, Guang Chen +1
Efficiently modeling dynamic motion information in videos is crucial for action recognition task. Most state-of-the-art methods heavily rely on dense optical flow as motion represe…