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

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Improving Generalization in Reinforcement Learning with Mixture Regularization

Oct 21, 2020
Kaixin Wang, Bingyi Kang, Jie Shao, Jiashi Feng

* NeurIPS 2020 

  Access Paper or Ask Questions

Towards Accurate Human Pose Estimation in Videos of Crowded Scenes

Oct 21, 2020
Li Yuan, Shuning Chang, Xuecheng Nie, Ziyuan Huang, Yichen Zhou, Yunpeng Chen, Jiashi Feng, Shuicheng Yan

* 2nd Place in ACM Multimedia Grand Challenge: Human in Events, Track2: Crowd Pose Estimation in Complex Events. ACM Multimedia 2020. arXiv admin note: substantial text overlap with arXiv:2010.08365, arXiv:2010.10007 

  Access Paper or Ask Questions

A Simple Baseline for Pose Tracking in Videos of Crowded Scenes

Oct 21, 2020
Li Yuan, Shuning Chang, Ziyuan Huang, Yichen Zhou, Yunpeng Chen, Xuecheng Nie, Francis E. H. Tay, Jiashi Feng, Shuicheng Yan

* 2nd Place in ACM Multimedia Grand Challenge: Human in Events, Track3: Crowd Pose Tracking in Complex Events. ACM Multimedia 2020. arXiv admin note: substantial text overlap with arXiv:2010.08365, arXiv:2010.10008 

  Access Paper or Ask Questions

Toward Accurate Person-level Action Recognition in Videos of Crowded Scenes

Oct 16, 2020
Li Yuan, Yichen Zhou, Shuning Chang, Ziyuan Huang, Yunpeng Chen, Xuecheng Nie, Tao Wang, Jiashi Feng, Shuicheng Yan

* ACM Multimedia 2020 
* 1'st Place in ACM Multimedia Grand Challenge: Human in Events, Track4: Person-level Action Recognition in Complex Events 

  Access Paper or Ask Questions

Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning

Oct 12, 2020
Pan Zhou, Jiashi Feng, Chao Ma, Caiming Xiong, Steven HOI, Weinan E

* NeurIPS 2020 

  Access Paper or Ask Questions

RVL-BERT: Visual Relationship Detection with Visual-Linguistic Knowledge from Pre-trained Representations

Sep 10, 2020
Meng-Jiun Chiou, Roger Zimmermann, Jiashi Feng

* 9 pages, 4 figures, 4 tables 

  Access Paper or Ask Questions

Dual Adversarial Auto-Encoders for Clustering

Aug 23, 2020
Pengfei Ge, Chuan-Xian Ren, Jiashi Feng, Shuicheng Yan


  Access Paper or Ask Questions

ConvBERT: Improving BERT with Span-based Dynamic Convolution

Aug 06, 2020
Zihang Jiang, Weihao Yu, Daquan Zhou, Yunpeng Chen, Jiashi Feng, Shuicheng Yan

* 16 pages 

  Access Paper or Ask Questions

Few-shot Classification via Adaptive Attention

Aug 06, 2020
Zihang Jiang, Bingyi Kang, Kuangqi Zhou, Jiashi Feng

* 11 pages, 4 figures 

  Access Paper or Ask Questions

The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation

Jul 31, 2020
Tao Wang, Yu Li, Bingyi Kang, Junnan Li, Junhao Liew, Sheng Tang, Steven Hoi, Jiashi Feng

* LVIS 2019 challenge winner, performance significantly improved after challenge submission, accepted at ECCV 2019 

  Access Paper or Ask Questions

Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition

Jul 12, 2020
Chenyang Si, Xuecheng Nie, Wei Wang, Liang Wang, Tieniu Tan, Jiashi Feng

* Accepted by ECCV2020 

  Access Paper or Ask Questions

Combating Domain Shift with Self-Taught Labeling

Jul 08, 2020
Jian Liang, Dapeng Hu, Jiashi Feng


  Access Paper or Ask Questions

Rethinking Bottleneck Structure for Efficient Mobile Network Design

Jul 07, 2020
Zhou Daquan, Qibin Hou, Yunpeng Chen, Jiashi Feng, Shuicheng Yan

* 24 pages, published as a ECCV20 conference paper 

  Access Paper or Ask Questions

Local Grid Rendering Networks for 3D Object Detection in Point Clouds

Jul 04, 2020
Jianan Li, Jiashi Feng


  Access Paper or Ask Questions

Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation

Jul 04, 2020
Jianfeng Zhang, Xuecheng Nie, Jiashi Feng


  Access Paper or Ask Questions

Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax

Jun 18, 2020
Yu Li, Tao Wang, Bingyi Kang, Sheng Tang, Chunfeng Wang, Jintao Li, Jiashi Feng

* CVPR 2020 (Oral). Code is available at https://github.com/FishYuLi/BalancedGroupSoftmax 

  Access Paper or Ask Questions

Multi-Miner: Object-Adaptive Region Mining for Weakly-Supervised Semantic Segmentation

Jun 14, 2020
Kuangqi Zhou, Qibin Hou, Zun Li, Jiashi Feng


  Access Paper or Ask Questions

Effective Training Strategies for Deep Graph Neural Networks

Jun 12, 2020
Kuangqi Zhou, Yanfei Dong, Wee Sun Lee, Bryan Hooi, Huan Xu, Jiashi Feng

* Code is available at  

  Access Paper or Ask Questions

Boosting Few-Shot Learning With Adaptive Margin Loss

May 28, 2020
Aoxue Li, Weiran Huang, Xu Lan, Jiashi Feng, Zhenguo Li, Liwei Wang

* Accepted by CVPR 2020 

  Access Paper or Ask Questions

RAIN: Robust and Accurate Classification Networks with Randomization and Enhancement

Apr 24, 2020
Jiawei Du, Hanshu Yan, Joey Tianyi Zhou, Rick Siow Mong Goh, Jiashi Feng


  Access Paper or Ask Questions

PANDA: Prototypical Unsupervised Domain Adaptation

Apr 12, 2020
Dapeng Hu, Jian Liang, Qibin Hou, Hanshu Yan, Yunpeng Chen, Shuicheng Yan, Jiashi Feng


  Access Paper or Ask Questions

Strip Pooling: Rethinking Spatial Pooling for Scene Parsing

Mar 30, 2020
Qibin Hou, Li Zhang, Ming-Ming Cheng, Jiashi Feng

* Published as a CVPR2020 paper 

  Access Paper or Ask Questions

A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation

Mar 05, 2020
Jian Liang, Yunbo Wang, Dapeng Hu, Ran He, Jiashi Feng


  Access Paper or Ask Questions

Cross-layer Feature Pyramid Network for Salient Object Detection

Feb 25, 2020
Zun Li, Congyan Lang, Junhao Liew, Qibin Hou, Yidong Li, Jiashi Feng

* 10 pages, 7 figures 

  Access Paper or Ask Questions

Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation

Feb 20, 2020
Jian Liang, Dapeng Hu, Jiashi Feng


  Access Paper or Ask Questions

MetaSelector: Meta-Learning for Recommendation with User-Level Adaptive Model Selection

Feb 13, 2020
Mi Luo, Fei Chen, Pengxiang Cheng, Zhenhua Dong, Xiuqiang He, Jiashi Feng, Zhenguo Li


  Access Paper or Ask Questions