Video Representation Learning

Video representation learning studies how to encode frames and their evolution into features useful for tasks such as action recognition, dense tracking, retrieval, generation, and robot planning. Common approaches include masked reconstruction, contrastive learning, predictive latent objectives such as JEPA, explicit motion and trajectory cues, multimodal alignment, and transfer from image encoders. Evaluations span action datasets such as Kinetics and Something-Something, egocentric and tracking benchmarks such as Ego4D and TAP-Vid, and embodied settings such as NAVSIM and robotic manipulation. A central challenge is learning features that preserve semantic appearance while capturing temporal order, geometry, and action-relevant dynamics without prohibitive data and compute costs; standard recognition scores do not always reveal these capabilities.