David Fan

6

Papers

39

Total Citations

Papers (6)

Scaling Language-Free Visual Representation Learning

MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

OASIS: A Large-Scale Dataset for Single Image 3D in the Wild

Shot Contrastive Self-Supervised Learning for Scene Boundary Detection

MEGA: Multimodal Alignment Aggregation and Distillation For Cinematic Video Segmentation

Motion-Guided Masking for Spatiotemporal Representation Learning