Pinned Loading

1. bytedance/Shot2Story bytedance/Shot2Story Public

   A new multi-shot video understanding benchmark Shot2Story with comprehensive video summaries and detailed shot-level captions.

   Python 164 7

2. HVRNet HVRNet Public

   Code for Mining Inter-Video Proposal Relations for Video Object Detection, ECCV 2020

   Python 49 6

3. bytedance/Portrait-Mode-Video bytedance/Portrait-Mode-Video Public

   Video dataset dedicated to portrait-mode video recognition.

   Python 55 1

4. roomtour3d/roomtour3d-NaviLLM roomtour3d/roomtour3d-NaviLLM Public

   [CVPR 2025] RoomTour3D - Geometry-aware, cheap and automatic data from web videos for embodied navigation

   Python 67 4