Yuhan Shen

7 papers · 2021–2026 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (19) 🐣 Hot Topic Early Bird

Venues

CVPR (6) ICCV (1)

Top co-authors

Ehsan Elhamifar (7) Arun Innanje (1) Zhongpai Gao (1) Effrosyni Mavroudi (1) Ziyan Wu (1) Terrence Chen (1) Lorenzo Torresani (1) Meng Zheng (1) Xitong Yang (1) Van Nguyen Nguyen (1)

Research topics

Artificial Intelligence (5) Computer Vision (5) Deep Learning (5) Machine Learning (5) Analysis (5) Learning Types · Machine Learning (5) Core AI (4) Learning Types · Deep Learning (4) Processing (4) Healthcare & Medicine (1) Architectures (1) Clinical (1) Domain-Specific (1) Learning Paradigms (1)

Keywords

video understanding (4) weakly supervised learning (4) action segmentation (3) egocentric video (3) instructional video (2) vision-language model (2) action recognition (2) multi-task learning (2) visual-language alignment (1) task graph (1) pseudo transcript (1) video object segmentation (1) weakly supervised segmentation (1) reward normalization (1) procedural video (1) zero-shot grounding (1) object state prediction (1) online segmentation (1) pixel-level grounding (1) progress prediction (1)

Papers

MedGRPO: Multi-Task Reinforcement Learning for Heterogeneous Medical Video Understanding CVPR 2026 MOSCATO: Predicting Multiple Object State Change Through Actions ICCV 2025 Understanding Multi-Task Activities from Single-Task Videos CVPR 2025 Learning to Segment Referred Objects from Narrated Egocentric Videos CVPR 2024 Progress-Aware Online Action Segmentation for Egocentric Procedural Task Videos CVPR 2024 Semi-Weakly-Supervised Learning of Complex Actions From Instructional Task Videos CVPR 2022 Learning To Segment Actions From Visual and Language Instructions via Differentiable Weak Sequence Alignment CVPR 2021