Scholar
Di Yang
Google Scholar ID: Q-koPr0AAAAJ
Inria
Citations & Impact
Citations
520
H-index
9
i10-index
9
Publications
20
Co-authors
13
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- - Publications:
- - LAC: Latent Action Composition for Skeleton-based Action Segmentation (ICCV 2023)
- - Self-supervised Video Representation Learning via Latent Time Navigation (AAAI 2023)
- - ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting (IJCV 2024)
- - Latent Image Animator: Learning to Animate Images via Latent Space Navigation (ICLR 2022)
- - UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition (BMVC 2021, Oral)
- - VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living (IEEE T-PAMI 2021)
- - Selective Spatio-Temporal Aggregation Based Pose Refinement System (WACV 2021)
Research Experience
- - April 2023 - Present: Toyota Motor Europe - Robotics & AI Lab, Research Intern in Belgium
- - July 2023: Attended the Cambridge Ellis Unit Summer School on Probabilistic Machine Learning in the UK
Education
- - Ph.D. Degree: 2024, Inria, STARS team, supervised by Dr. François Brémond
- - M.Eng. Degree: 2019, Télécom Saint-Étienne, University of Lyon, France, in Computer Vision
- - B.S. Degree: 2017, Xidian University, China, in Communication Engineering
Background
- - Research Interests: Computer vision and deep learning, with a special interest in video understanding and action recognition
- - Professional Field: Computer Vision, Deep Learning
Miscellany
- - Personal Interests: Not mentioned
