Hazel Doughty

Latest

• Low-Resource Vision Challenges for Foundation Models
• 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