Hengduo Li
Hengduo Li
Meta AI
Verified email at - Homepage
Cited by
Cited by
Transferable clean-label poisoning attacks on deep neural nets
C Zhu, WR Huang, A Shafahi, H Li, G Taylor, C Studer, T Goldstein
ICML 2019, 2019
AdaViT: Adaptive Vision Transformers for Efficient Image Recognition
L Meng*, H Li*, BC Chen, S Lan, Z Wu, YG Jiang, SN Lim
CVPR 2022, 2022
A Coarse-to-Fine Framework for Resource Efficient Video Recognition
Z Wu, H Li, Y Zheng, C Xiong, YG Jiang, LS Davis
IJCV 2021, 2021
R-FCN-3000 at 30fps: Decoupling Detection and Classification
B Singh*, H Li*, A Sharma, LS Davis
CVPR 2018, 2018
Learning from noisy anchors for one-stage object detection
H Li, Z Wu, C Zhu, C Xiong, R Socher, LS Davis
CVPR 2020, 2020
Rethinking Pseudo Labels for Semi-Supervised Object Detection
H Li, Z Wu, A Shrivastava, LS Davis
AAAI 2022, 2022
Joint human detection and head pose estimation via multistream networks for RGB-D videos
G Zhang, J Liu, H Li, YQ Chen, LS Davis
IEEE Signal Processing Letters 24 (11), 1666-1670, 2017
Efficient video transformers with spatial-temporal token selection
J Wang, X Yang, H Li, Z Wu, YG Jiang
ECCV 2022 & arXiv:2111.11591, 2022
A Dynamic Frame Selection Framework for Fast Video Recognition
Z Wu, H Li, C Xiong, YG Jiang, LS Davis
IEEE TPAMI 2020, 2020
An analysis of pre-training on object detection
H Li, B Singh, M Najibi, Z Wu, LS Davis
ICCV Workshop 2021 & arXiv:1904.05871, 2021
2D or not 2D? Adaptive 3d Convolution Selection for Efficient Video Recognition
H Li, Z Wu, A Shrivastava, LS Davis
CVPR 2021, 2021
Multi-glimpse LSTM with color-depth feature fusion for human detection
H Li, J Liu, G Zhang, Y Gao, Y Wu
ICIP 2017, 2017
Semi-Supervised Single-View 3D Reconstruction via Prototype Shape Priors
Z Xing, H Li, Z Wu, YG Jiang
ECCV 2022 & arXiv:2209.15383, 2022
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
B He, H Li, YK Jang, M Jia, X Cao, A Shah, A Shrivastava, SN Lim
CVPR 2024, 2024
Hcms: Hierarchical and conditional modality selection for efficient video recognition
Z Weng, Z Wu, H Li, J Chen, YG Jiang
ACM Transactions on Multimedia Computing, Communications and Applications 20 …, 2023
Hms: Hierarchical modality selection for efficient video recognition
Z Weng, Z Wu, H Li, YG Jiang
arXiv preprint, 2021
Improving the tightness of convex relaxation bounds for training certifiably robust classifiers
C Zhu, R Ni, P Chiang, H Li, F Huang, T Goldstein
arXiv preprint arXiv:2002.09766, 2020
Object Recognition as Next Token Prediction
K Yue, BC Chen, J Geiping, H Li, T Goldstein, SN Lim
CVPR 2024, 2024
SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentation
L Meng, S Lan, H Li, JM Alvarez, Z Wu, YG Jiang
arXiv preprint arXiv:2311.14671, 2023
BMB: Balanced Memory Bank for Imbalanced Semi-supervised Learning
W Peng, Z Weng, H Li, Z Wu
arXiv preprint arXiv:2305.12912, 2023
The system can't perform the operation now. Try again later.
Articles 1–20