Scholar
Xinchen Liu
Google Scholar ID: 31Dv7M0AAAAJ
JD Explore Academy
Computer Vision
Multimedia
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
3,090
H-index
16
i10-index
21
Publications
20
Co-authors
15
list available
Contact
CV
Open ↗
GitHub
Open ↗
Publications
5 items
A Paradigm Shift: Fully End-to-End Training for Temporal Sentence Grounding in Videos
2026
Cited
0
Reflection-Based Task Adaptation for Self-Improving VLA
2025
Cited
0
HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation
2025
Cited
0
Scaling Down Text Encoders of Text-to-Image Diffusion Models
2025
Cited
0
Motion Capture from Inertial and Vision Sensors
arXiv.org · 2024
Cited
5
Resume (English only)
Academic Achievements
Two papers on multi-modal generation accepted by CVPR 2025 (Feb 2025)
Team awarded the 2024 CAIA Wu Wenjun AI Science and Technology Award – Special Prize for Technology Progress (Feb 2025)
Paper on gait recognition with multi-modal representations accepted by ACM Multimedia 2024 (Jul 2024)
Paper on action segmentation using IoT signals accepted by ACM ToMM (Mar 2024)
Paper on efficient human NeRF accepted by CVPR 2024 (Feb 2024)
Paper on gait recognition with a new dataset accepted by ACM Multimedia 2023 (Aug 2023)
Open-source toolbox FastReID accepted by ACM Multimedia 2023 Open-Source Software Competition (Sep 2023)
Paper 'PROVID' recognized as ESI Highly Cited Paper (Top 1%) in Nov 2022
Released HOIGen-1M dataset for human-object interaction video generation on Hugging Face (May 2025)
Co-authors
15 total
Tao Mei
HiDream.ai; Fellow of CAE/IEEE/IAPR/CAAI
Huadong Ma
BUPT
Wu Liu (刘武)
University of Science and Technology of China; previously JD.com; BUPT; ICT, CAS
Jinkai Zheng (郑锦凯)
Hangzhou Dianzi University
Chenggang Yan
Hangzhou Dianzi University
Co-author 6
Co-author 7
Jingkuan Song(宋井宽)
Tongji University(同济大学)
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up