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 Changhu Wang

Recovering the Unbiased Scene Graphs from the Biased Ones


Jul 05, 2021
Meng-Jiun Chiou, Henghui Ding, Hanshu Yan, Changhu Wang, Roger Zimmermann, Jiashi Feng

* Accepted by ACMMM 2021. Source code will be available at https://github.com/coldmanck/recovering-unbiased-scene-graphs 

  Access Paper or Ask Questions

How Incomplete is Contrastive Learning? An Inter-intra Variant Dual Representation Method for Self-supervised Video Recognition


Jul 05, 2021
Lin Zhang, Qi She, Zhengyang Shen, Changhu Wang

* 10 pages with appendix 

  Access Paper or Ask Questions

Rethinking Re-Sampling in Imbalanced Semi-Supervised Learning


Jun 01, 2021
Ju He, Adam Kortylewski, Shaokang Yang, Shuai Liu, Cheng Yang, Changhu Wang, Alan Yuille


  Access Paper or Ask Questions

I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition


May 18, 2021
Chuhui Xue, Shijian Lu, Song Bai, Wenqing Zhang, Changhu Wang


  Access Paper or Ask Questions

ConTNet: Why not use convolution and transformer at the same time?


May 10, 2021
Haotian Yan, Zhe Li, Weijian Li, Changhu Wang, Ming Wu, Chuang Zhang


  Access Paper or Ask Questions

Center Prediction Loss for Re-identification


Apr 30, 2021
Lu Yang, Yunlong Wang, Lingqiao Liu, Peng Wang, Lu Chi, Zehuan Yuan, Changhu Wang, Yanning Zhang


  Access Paper or Ask Questions

Improving Long-Tailed Classification from Instance Level


Apr 13, 2021
Yan Zhao, Weicong Chen, Xu Tan, Kai Huang, Jin Xu, Changhu Wang, Jihong Zhu


  Access Paper or Ask Questions

Conditional Meta-Network for Blind Super-Resolution with Multiple Degradations


Apr 09, 2021
Guanghao Yin, Wei Wang, Zehuan Yuan, Dongdong Yu, Shouqian Sun, Changhu Wang


  Access Paper or Ask Questions

NeMI: Unifying Neural Radiance Fields with Multiplane Images for Novel View Synthesis


Apr 08, 2021
Jiaxin Li, Zijian Feng, Qi She, Henghui Ding, Changhu Wang, Gim Hee Lee

* Main paper and supplementary materials 

  Access Paper or Ask Questions

TransFG: A Transformer Architecture for Fine-grained Recognition


Mar 28, 2021
Ju He, Jie-Neng Chen, Shuai Liu, Adam Kortylewski, Cheng Yang, Yutong Bai, Changhu Wang, Alan Yuille

* Release official PyTorch implementation of the paper 

  Access Paper or Ask Questions

Involution: Inverting the Inherence of Convolution for Visual Recognition


Mar 10, 2021
Duo Li, Jie Hu, Changhu Wang, Xiangtai Li, Qi She, Lei Zhu, Tong Zhang, Qifeng Chen

* Accepted to CVPR 2021. Code and models are available at https://github.com/d-li14/involution 

  Access Paper or Ask Questions

Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognition


Feb 19, 2021
Shaokang Yang, Shuai Liu, Cheng Yang, Changhu Wang

* 10 pages, 7 figures 

  Access Paper or Ask Questions

Incorporating Vision Bias into Click Models for Image-oriented Search Engine


Jan 07, 2021
Ningxin Xu, Cheng Yang, Yixin Zhu, Xiaowei Hu, Changhu Wang


  Access Paper or Ask Questions

TransTrack: Multiple-Object Tracking with Transformer


Dec 31, 2020
Peize Sun, Yi Jiang, Rufeng Zhang, Enze Xie, Jinkun Cao, Xinting Hu, Tao Kong, Zehuan Yuan, Changhu Wang, Ping Luo


  Access Paper or Ask Questions

Slimmable Generative Adversarial Networks


Dec 15, 2020
Liang Hou, Zehuan Yuan, Lei Huang, Huawei Shen, Xueqi Cheng, Changhu Wang

* Accepted to AAAI 2021 

  Access Paper or Ask Questions

OneNet: Towards End-to-End One-Stage Object Detection


Dec 10, 2020
Peize Sun, Yi Jiang, Enze Xie, Zehuan Yuan, Changhu Wang, Ping Luo


  Access Paper or Ask Questions

F2Net: Learning to Focus on the Foreground for Unsupervised Video Object Segmentation


Dec 04, 2020
Daizong Liu, Dongdong Yu, Changhu Wang, Pan Zhou

* Accepted by AAAI2021 

  Access Paper or Ask Questions

Sparse R-CNN: End-to-End Object Detection with Learnable Proposals


Nov 25, 2020
Peize Sun, Rufeng Zhang, Yi Jiang, Tao Kong, Chenfeng Xu, Wei Zhan, Masayoshi Tomizuka, Lei Li, Zehuan Yuan, Changhu Wang, Ping Luo


  Access Paper or Ask Questions

Learning the Best Pooling Strategy for Visual Semantic Embedding


Nov 09, 2020
Jiacheng Chen, Hexiang Hu, Hao Wu, Yuning Jiang, Changhu Wang


  Access Paper or Ask Questions

Context Encoding for Video Retrieval with Contrastive Learning


Aug 04, 2020
Jie Shao, Xin Wen, Bingchen Zhao, Changhu Wang, Xiangyang Xue


  Access Paper or Ask Questions

Towards Good Practices for Instance Segmentation


Oct 28, 2019
Dongdong Yu, Zehuan Yuan, Jinlai Liu, Kun Yuan, Changhu Wang


  Access Paper or Ask Questions

Towards Good Practices for Multi-Person Pose Estimation


Oct 28, 2019
Dongdong Yu, Kai Su, Changhu Wang


  Access Paper or Ask Questions

Towards Good Practices for Video Object Segmentation


Sep 30, 2019
Dongdong Yu, Kai Su, Hengkai Guo, Jian Wang, Kaihui Zhou, Yuanyuan Huang, Minghui Dong, Jie Shao, Changhu Wang


  Access Paper or Ask Questions

Deformable Tube Network for Action Detection in Videos


Jul 03, 2019
Wei Li, Zehuan Yuan, Dashan Guo, Lei Huang, Xiangzhong Fang, Changhu Wang


  Access Paper or Ask Questions