Scholar
Zehong Shen
Google Scholar ID: mjgQRNkAAAAJ
Ant Group
Citations & Impact
Citations
2,171
H-index
8
i10-index
8
Publications
10
Co-authors
7
list available
Publications
Resume (English only)
Academic Achievements
- MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training, ArXiv, 2025
- Motion-2-to-3: Leveraging 2D Motion Data to Boost 3D Motion Generation, ICCV, 2025
- World-Grounded Human Motion Recovery via Gravity-View Coordinates, SIGGRAPH Asia, 2024
- Generating Human Motion in 3D Scenes from Text Descriptions, CVPR, 2024
- Learning Human Mesh Recovery in 3D Scenes, CVPR, 2023
- Long-term Visual Localization with Mobile Sensors, CVPR, 2023
- Semi-Dense Feature Matching with Transformers and its Applications in Multiple-View Geometry, TPAMI, 2022
- LoFTR: Detector-Free Local Feature Matching with Transformers, CVPR, 2021, 1000+ Citations
- GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs, NeurIPS, 2019
Research Experience
- Research Scientist at Ant Group Research Institute
Education
- Ph.D. in Computer Science at the State Key Laboratory of CAD&CG, Zhejiang University, advised by Prof. Xiaowei Zhou; Bachelor's degree in Automation from Zhejiang University, minored in ACEE at the Chu Kochen Honors College.
Background
- Research Interests: Intersection of 3D computer vision and embodied intelligence; focused on reconstructing and generating human-like agents, aiming to accurately capture human interactions with the physical world and to develop agents capable of perception, reasoning, and interaction in real-world environments.
Miscellany
- Hiring research interns on Embodied AI and 3D Vision; providing strong resources and mentorship, along with the freedom to explore any relevant, impactful, and practical research topics.
