Joint Human Detection and Head Pose Estimation via Multistream Networks for RGB-D Videos von Guyue Zhang, Jun Liu, Hengduo Li, Yan Qiu Chen, Davis, Larry S.

Volltext

A Coarse-to-Fine Framework for Resource Efficient Video Recognition von Wu, Zuxuan, Li, Hengduo, Zheng, Yingbin, Xiong, Caiming, Jiang, Yu-Gang, Davis, Larry S

Volltext

A Dynamic Frame Selection Framework for Fast Video Recognition von Wu, Zuxuan, Li, Hengduo, Xiong, Caiming, Jiang, Yu-Gang, Davis, Larry S.

Volltext

HCMS: Hierarchical and Conditional Modality Selection for Efficient Video Recognition von Weng, Zejia, Wu, Zuxuan, Li, Hengduo, Chen, Jingjing, Jiang, Yu-Gang

Volltext

Efficient Video Transformers with Spatial-Temporal Token Selection von Wang, Junke, Yang, Xitong, Li, Hengduo, Liu, Li, Wu, Zuxuan, Jiang, Yu-Gang

Volltext

Semi-supervised Single-View 3D Reconstruction via Prototype Shape Priors von Xing, Zhen, Li, Hengduo, Wu, Zuxuan, Jiang, Yu-Gang

Volltext

BMB: Balanced Memory Bank for Imbalanced Semi-supervised Learning von Peng, Wujian, Weng, Zejia, Li, Hengduo, Wu, Zuxuan

Volltext bestellen

Semi-Supervised Single-View 3D Reconstruction via Prototype Shape Priors von Xing, Zhen, Li, Hengduo, Wu, Zuxuan, Jiang, Yu-Gang

Volltext bestellen

Object Recognition as Next Token Prediction von Yue, Kaiyu, Chen, Bor-Chun, Geiping, Jonas, Li, Hengduo, Goldstein, Tom, Lim, Ser-Nam

Volltext bestellen

SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentation von Meng, Lingchen, Lan, Shiyi, Li, Hengduo, Alvarez, Jose M, Wu, Zuxuan, Jiang, Yu-Gang

Volltext bestellen

MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding von He, Bo, Li, Hengduo, Jang, Young Kyun, Jia, Menglin, Cao, Xuefei, Shah, Ashish, Shrivastava, Abhinav, Lim, Ser-Nam

Volltext bestellen

Rethinking Pseudo Labels for Semi-Supervised Object Detection von Li, Hengduo, Wu, Zuxuan, Shrivastava, Abhinav, Davis, Larry S

Volltext bestellen

HCMS: Hierarchical and Conditional Modality Selection for Efficient Video Recognition von Weng, Zejia, Wu, Zuxuan, Li, Hengduo, Chen, Jingjing, Yu-Gang, Jiang

Volltext

2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition von Li, Hengduo, Wu, Zuxuan, Shrivastava, Abhinav, Davis, Larry S

Volltext bestellen

Efficient Video Transformers with Spatial-Temporal Token Selection von Wang, Junke, Yang, Xitong, Li, Hengduo, Liu, Li, Wu, Zuxuan, Jiang, Yu-Gang

Volltext bestellen

BMB: Balanced Memory Bank for Imbalanced Semi-supervised Learning von Peng, Wujian, Weng, Zejia, Li, Hengduo, Wu, Zuxuan

Volltext

AdaViT: Adaptive Vision Transformers for Efficient Image Recognition von Meng, Lingchen, Li, Hengduo, Chen, Bor-Chun, Lan, Shiyi, Wu, Zuxuan, Jiang, Yu-Gang, Lim, Ser-Nam

Volltext bestellen

SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentation von Meng, Lingchen, Shiyi Lan, Li, Hengduo, Alvarez, Jose M, Wu, Zuxuan, Yu-Gang, Jiang

Volltext

Semi-Supervised Single-View 3D Reconstruction via Prototype Shape Priors von Xing, Zhen, Li, Hengduo, Wu, Zuxuan, Yu-Gang, Jiang

Volltext

Object Recognition as Next Token Prediction von Yue, Kaiyu, Bor-Chun, Chen, Geiping, Jonas, Li, Hengduo, Goldstein, Tom, Ser-Nam Lim

Volltext