Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Limin Wang

End-to-End Dense Video Grounding via Parallel Regression


Sep 23, 2021
Fengyuan Shi, Limin Wang, Weilin Huang

* Technical report 

  Access Paper or Ask Questions

Mutual Supervision for Dense Object Detection


Sep 13, 2021
Ziteng Gao, Limin Wang, Gangshan Wu

* ICCV 2021 camera ready version 

  Access Paper or Ask Questions

Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding


Sep 10, 2021
Zhenzhi Wang, Limin Wang, Tao Wu, Tianhao Li, Gangshan Wu

* 18 pages, 18 figures. 1st place solution to HC-STVG challenge of the 3rd PIC workshop (http://www.picdataset.com/challenge/task/hcvg/

  Access Paper or Ask Questions

Self Supervision to Distillation for Long-Tailed Visual Recognition


Sep 09, 2021
Tianhao Li, Limin Wang, Gangshan Wu

* ICCV 2021 camera-ready version 

  Access Paper or Ask Questions

Target Adaptive Context Aggregation for Video Scene Graph Generation


Aug 18, 2021
Yao Teng, Limin Wang, Zhifeng Li, Gangshan Wu

* ICCV 2021 camera-ready version 

  Access Paper or Ask Questions

Structured Sparse R-CNN for Direct Scene Graph Generation


Jun 21, 2021
Yao Teng, Limin Wang

* Technical report 

  Access Paper or Ask Questions

Joint Landmark and Structure Learning for Automatic Evaluation of Developmental Dysplasia of the Hip


Jun 10, 2021
Xindi Hu, Limin Wang, Xin Yang, Xu Zhou, Wufeng Xue, Yan Cao, Shengfeng Liu, Yuhao Huang, Shuangping Guo, Ning Shang, Dong Ni, Ning Gu

* Accepted by IEEE Journal of Biomedical and Health Informatics. 14 pages, 10 figures and 10 tables 

  Access Paper or Ask Questions

SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction


Jun 06, 2021
Zeyu Ruan, Changqing Zou, Longhai Wu, Gangshan Wu, Limin Wang

* To appear in IEEE Transactions on Image Processing. Code and model is available at https://github.com/MCG-NJU/SADRNet 

  Access Paper or Ask Questions

FineAction: A Fined Video Dataset for Temporal Action Localization


May 24, 2021
Yi Liu, Limin Wang, Xiao Ma, Yali Wang, Yu Qiao

* One track of DeeperAction [email protected] HomePage: https://deeperaction.github.io/fineaction/ 

  Access Paper or Ask Questions

MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions


May 16, 2021
Yixuan Li, Lei Chen, Runyu He, Zhenzhi Wang, Gangshan Wu, Limin Wang

* One track of DeeperAction [email protected] HomePage: https://deeperaction.github.io/multisports/ 

  Access Paper or Ask Questions

MGSampler: An Explainable Sampling Strategy for Video Action Recognition


Apr 20, 2021
Yuan Zhi, Zhan Tong, Limin Wang, Gangshan Wu


  Access Paper or Ask Questions

3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop


Apr 01, 2021
Hongwen Zhang, Yating Tian, Xinchi Zhou, Wanli Ouyang, Yebin Liu, Limin Wang, Zhenan Sun

* Technical report. Code and model available at https://hongwenzhang.github.io/pymaf 

  Access Paper or Ask Questions

Target Transformed Regression for Accurate Tracking


Apr 01, 2021
Yutao Cui, Cheng Jiang, Limin Wang, Gangshan Wu


  Access Paper or Ask Questions

Relaxed Transformer Decoders for Direct Action Proposal Generation


Feb 03, 2021
Jing Tan, Jiaqi Tang, Limin Wang, Gangshan Wu

* Technical report 

  Access Paper or Ask Questions

TDN: Temporal Difference Networks for Efficient Action Recognition


Dec 18, 2020
Limin Wang, Zhan Tong, Bin Ji, Gangshan Wu

* Technical report 

  Access Paper or Ask Questions

Finding Action Tubes with a Sparse-to-Dense Framework


Aug 30, 2020
Yuxi Li, Weiyao Lin, Tao Wang, John See, Rui Qian, Ning Xu, Limin Wang, Shugong Xu

* 5 figures; AAAI 2020 

  Access Paper or Ask Questions

Context-Aware RCNN: A Baseline for Action Detection in Videos


Jul 20, 2020
Jianchao Wu, Zhanghui Kuang, Limin Wang, Wayne Zhang, Gangshan Wu

* ECCV 2020 Camera-ready version 

  Access Paper or Ask Questions

Dynamic Sampling Networks for Efficient Action Recognition in Videos


Jun 28, 2020
Yin-Dong Zheng, Zhaoyang Liu, Tong Lu, Limin Wang

* To appear in IEEE Transaction on Image Processing 

  Access Paper or Ask Questions

TAM: Temporal Adaptive Module for Video Recognition


May 14, 2020
Zhaoyang Liu, Limin Wang, Wayne Wu, Chen Qian, Tong Lu

* Technical report 

  Access Paper or Ask Questions

Fully Convolutional Online Tracking


Apr 15, 2020
Yutao Cui, Cheng Jiang, Limin Wang, Gangshan Wu

* Technical Report. Code will be made available at https://github.com/MCG-NJU/FCOT 

  Access Paper or Ask Questions

SketchyCOCO: Image Generation from Freehand Scene Sketches


Apr 07, 2020
Chengying Gao, Qi Liu, Qi Xu, Limin Wang, Jianzhuang Liu, Changqing Zou


  Access Paper or Ask Questions

TEA: Temporal Excitation and Aggregation for Action Recognition


Apr 03, 2020
Yan Li, Bin Ji, Xintian Shi, Jianguo Zhang, Bin Kang, Limin Wang

* CVPR2020. The code is available at https://github.com/Phoenix1327/tea-action-recognition 

  Access Paper or Ask Questions

Image Generation from Freehand Scene Sketches


Mar 11, 2020
Chengying Gao, Qi Liu, Qi Xu, Jianzhuang Liu, Limin Wang, Changqing Zou


  Access Paper or Ask Questions

Knowledge Integration Networks for Action Recognition


Feb 18, 2020
Shiwen Zhang, Sheng Guo, Limin Wang, Weilin Huang, Matthew R. Scott

* To appear in AAAI 2020 

  Access Paper or Ask Questions

V4D:4D Convolutional Neural Networks for Video-level Representation Learning


Feb 18, 2020
Shiwen Zhang, Sheng Guo, Weilin Huang, Matthew R. Scott, Limin Wang

* To appear in ICLR2020 

  Access Paper or Ask Questions

Learning Spatiotemporal Features via Video and Text Pair Discrimination


Jan 16, 2020
Tianhao Li, Limin Wang

* Technical Report 

  Access Paper or Ask Questions

Actions as Moving Points


Jan 14, 2020
Yixuan Li, Zixu Wang, Limin Wang, Gangshan Wu

* Technical Report 

  Access Paper or Ask Questions

TEINet: Towards an Efficient Architecture for Video Recognition


Nov 21, 2019
Zhaoyang Liu, Donghao Luo, Yabiao Wang, Limin Wang, Ying Tai, Chengjie Wang, Jilin Li, Feiyue Huang, Tong Lu

* Accepted by AAAI 2020 

  Access Paper or Ask Questions