Michael Wray
14 papers · 2017–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Renaissance Researcher (7) π Interdisciplinary Bridge π Conference Polyglot (6) π Academic Marathon (9) πΊοΈ Taxonomy Completionist (26)
π£
Hot Topic Early Bird
π
Conference Polyglot
(6)
π
Academic Marathon
(9)
π€
Dynamic Duo
(11)
π₯
Mega-Team
(100)
π
Conference Pioneer
π
Century Club
(14)
ποΈ
Keyword Collector
(63)
Conferences
CVPR (6)
WACV (3)
ICCV (2)
ECCV (1)
EMNLP (1)
NIPS (1)
Top co-authors
Keywords
video understanding
(4)
egocentric vision
(3)
action recognition
(3)
egocentric video
(3)
activity recognition
(3)
zero-shot learning
(2)
self-supervised learning
(2)
cross-modal retrieval
(2)
video retrieval
(2)
transfer learning
(1)
depth estimation
(1)
multimodal learning
(1)
domain generalization
(1)
visual question answering
(1)
pose estimation
(1)
hand pose estimation
(1)
domain adaptation
(1)
compositional generalization
(1)
metric learning
(1)
contrastive learning
(1)
Papers
From Detection to Anticipation: Online Understanding of Struggles across Various Tasks and Activities
WACV 2026
Towards Egocentric 3D Hand Pose Estimation in Unseen Domains
WACV 2026
Evaluating Compositional Generalisation in VLMs and Diffusion Models
EMNLP 2025
Moment of Untruth: Dealing with Negative Queries in Video Moment Retrieval
WACV 2025
HD-EPIC: A Highly-Detailed Egocentric Video Dataset
CVPR 2025
ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions
CVPR 2025
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
CVPR 2024
GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos
CVPR 2024
Egocentric Video-Language Pretraining
NIPS 2022
Ego4D: Around the World in 3,000 Hours of Egocentric Video
CVPR 2022
On Semantic Similarity in Video Retrieval
CVPR 2021
Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings
ICCV 2019
Scaling Egocentric Vision: The EPIC-KITCHENS Dataset
ECCV 2018
Trespassing the Boundaries: Labeling Temporal Bounds for Object Interactions in Egocentric Video
ICCV 2017