Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation

Wenhao Li,Mengyuan Liu,Hong Liu,Pichao Wang,Jialun Cai,Nicu Sebe

2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2024（2024）

Cited 0|Views74

Key words

Human Pose Estimation,Efficient 3D,3D Human Pose,Computational Cost,Video Frames,Original Resolution,Floating-point Operations,Spatiotemporal Information,Fast Inference,3D Pose,Transformer Block,Large Distances,Temporal Dimension,Temporal Information,Cluster Centers,Area Under Curve,Video Sequences,Redundant Data,Pose Of Frame,2D Pose,Pruning Strategy,Outdoor Scenes,Body Joints,Future Information,High-resolution Input,Temporal Domain,Small Receptive Field

AI Read Science

Must-Reading Tree

Example

Generate MRT to find the research sequence of this paper

Chat Paper

Summary is being generated by the instructions you defined