Search

VIS Lab

Hazel Doughty

SelEx: Self-Expertise in Fine-Grained Generalized Category Discovery
Low-Resource Vision Challenges for Foundation Models
Background no more: Action recognition across domains by causal interventions
Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery
Learning Unseen Modality Interaction
Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization
How Severe is Benchmark-Sensitivity in Video Self-Supervised Learning?
Audio-Adaptive Activity Recognition Across Video Domains
How Do You Do It? Fine-Grained Action Understanding with Pseudo-Adverbs
Skeleton-Contrastive 3D Action Representation Learning
Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100
On Semantic Similarity in Video Retrieval