Courses/Computer Vision

Computer Vision

CSE471

Prof. Makarand Tapaswi + Prof. Charu Sharma•Spring 2025-26•4 credits

Revision Notes/Unit 12 — Video Understanding

Unit 12 — Video Understanding

Beyond images × T: action recognition, temporal localisation, 3D CNNs (I3D), Two-Stream, SlowFast, ViViT, and TimeSformer's divided space-time attention.

Video Architectures — 3D CNNs, Two-Stream, SlowFast, ViViT, TimeSformer

14 min

Video ≠ images × T. The thing the model needs to capture is the TEMPORAL pattern — 'sit down' and 'stand up' are the same image set in reverse order. The architecture choices are about how to consume the time dimension efficiently.