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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

On Non-Random Missing Labels in Semi-Supervised Learning



Xinting Hu , Yulei Niu , Chunyan Miao , Xian-Sheng Hua , Hanwang Zhang

* ICLR 2022 

   Access Paper or Ask Questions

Exploiting Semantic Role Contextualized Video Features for Multi-Instance Text-Video Retrieval EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022



Burak Satar , Hongyuan Zhu , Hanwang Zhang , Joo Hwee Lim

* Ranked joint 3rd place in the Multi-Instance Retrieval Challenge at [email protected] 

   Access Paper or Ask Questions

RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval



Burak Satar , Hongyuan Zhu , Hanwang Zhang , Joo Hwee Lim

* Preprint, under review in TCSVT Journal 

   Access Paper or Ask Questions

Prompt-aligned Gradient for Prompt Tuning



Beier Zhu , Yulei Niu , Yucheng Han , Yue Wu , Hanwang Zhang


   Access Paper or Ask Questions

Certified Robustness Against Natural Language Attacks by Causal Intervention



Haiteng Zhao , Chang Ma* , Xinshuai Dong , Anh Tuan Luu , Zhi-Hong Deng , Hanwang Zhang


   Access Paper or Ask Questions

Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation



Zhaozheng Chen , Tan Wang , Xiongwei Wu , Xian-Sheng Hua , Hanwang Zhang , Qianru Sun

* Accepted to CVPR 2022 

   Access Paper or Ask Questions

Deconfounded Visual Grounding



Jianqiang Huang , Yu Qin , Jiaxin Qi , Qianru Sun , Hanwang Zhang

* AAAI 2022 Accepted 

   Access Paper or Ask Questions

Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification



Beier Zhu , Yulei Niu , Xian-Sheng Hua , Hanwang Zhang


   Access Paper or Ask Questions

How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?



Xinhsuai Dong , Luu Anh Tuan , Min Lin , Shuicheng Yan , Hanwang Zhang

* Accepted by NeurIPS-2021 

   Access Paper or Ask Questions

Introspective Distillation for Robust Question Answering



Yulei Niu , Hanwang Zhang

* Accepted by NeurIPS 2021 

   Access Paper or Ask Questions

1
2
3
4
5
6
7
>>