DINOv2: Learning Robust Visual Features without Supervision
Editable reading note on general-purpose visual features learned without task-specific supervision.
Reading and notes
Research library
A small public collection of papers I have read, with concise notes, connections, and takeaways.
Filter by tag
Vision transformers for action recognition [reading note]
Placeholder note for comparing spatial and temporal attention in action-recognition systems.
Multimodal retrieval and RAG [reading note]
Placeholder note for studying retrieval across text and visual representations.