Recent Publications and Preprints

AdaViT: Adaptive Vision Transformers for Efficient Image Recognition
Lingchen Meng^*, Hengduo Li^*, Bor-Chun Chen, Shiyi Lan, Zuxuan Wu, Yu-Gang Jiang, Ser-Nam Lim
CVPR 2022 [Paper]

Rethinking Pseudo Labels for Semi-Supervised Object Detection
Hengduo Li, Zuxuan Wu, Abhinav Shrivastava, Larry S Davis
AAAI 2022 [Paper]

A Coarse-to-Fine Framework for Resource Efficient Video Recognition
Zuxuan Wu, Hengduo Li, Yingbin Zheng, Caiming Xiong, Yu-Gang Jiang, Larry S Davis
IJCV 2021 [Paper] [Code]

An analysis of pre-training on object detection
Hengduo Li, Bharat Singh, Mahyar Najibi, Zuxuan Wu, Larry S Davis
ICCV 2021 SSLAD Workshop [Paper] [Pre-trained Model]

HMS: Hierarchical Modality Selection for Efficient Video Recognition
Zejia Weng, Zuxuan Wu, Hengduo Li, Yu-Gang Jiang
Preprint [Paper]

2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition
Hengduo Li, Zuxuan Wu, Abhinav Shrivastava, Larry S Davis
CVPR 2021 [Paper]

Learning from Noisy Anchors for One-stage Object Detection
Hengduo Li, Zuxuan Wu, Chen Zhu, Caiming Xiong, Richard Socher, Larry S Davis
CVPR 2020 [Paper] [Code]

A Dynamic Frame Selection Framework for Fast Video Recognition
Zuxuan Wu, Hengduo Li, Caiming Xiong, Yu-Gang Jiang, Larry S Davis
TPAMI 2020 [Paper]

Transferable clean-label poisoning attacks on deep neural nets
Chen Zhu, W Ronny Huang, Ali Shafahi, Hengduo Li, Gavin Taylor, Christoph Studer, Tom Goldstein
ICML 2019 [Paper] [Code]

R-FCN-3000 at 30fps: Decoupling Detection and Classification
Bharat Singh^* , Hengduo Li^*, Abhishek Sharma, Larry S Davis
CVPR 2018 [Paper] [Code]

(Note: ^* Equal contribution)