HFAT-HMR: Empowering ViT for human mesh recovery via high-frequency enhancement and auxiliary tokens
Authors:
- Jinming ZhangJZJinming Zhang
- Yingjie ChenYCYingjie Chen
- Linlin YangLYLinlin Yang
- Boshu JiaBJBoshu Jia
- Fang LiuFLFang Liu
- Baochang ZhangBZBaochang Zhang
- Xiaoyu WuXWXiaoyu Wu
- Libiao JinLJLibiao Jin
- 30 June 2026
- journal article
- Published by Elsevier in Neurocomputing
- Vol. 699
Abstract
No abstract availableFunding Information
- National University's Basic Research Foundation of China
- National Natural Science Foundation of China
This publication has 17 references indexed in Scilit:
- TSCMamba: Mamba meets multi-view learning for time series classificationInformation Fusion, 2025
- Part-Whole Relational Fusion Towards Multi-Modal Scene UnderstandingInternational Journal of Computer Vision, 2025
- Frequency-Assisted Mamba for Remote Sensing Image Super-ResolutionIEEE Transactions on Multimedia, 2024
- From Methods to Applications: A Review of Deep 3D Human Motion CaptureIEEE Transactions on Circuits and Systems for Video Technology, 2024
- Target-free measurement of cable forces based on computer vision and equivalent frequency differenceEngineering Structures, 2024
- Driver Distraction Behavior Recognition for Autonomous Driving: Approaches, Datasets and ChallengesIEEE Transactions on Intelligent Vehicles, 2024
- GBC-BCD: an improved bridge crack detection method based on bidirectional Laplacian pyramid structure with lightweight attention mechanism convolutionNondestructive Testing and Evaluation, 2024
- Human Action Recognition Systems: A Review of the Trends and State-of-the-ArtIEEE Access, 2024
- Towards comprehensive understanding of pedestrians for autonomous driving: Efficient multi-task-learning-based pedestrian detection, tracking and attribute recognitionRobotics and Autonomous Systems, 2023
- Multi-Modal Image Fusion via Deep Laplacian Pyramid Hybrid NetworkIEEE Transactions on Circuits and Systems for Video Technology, 2023