[CVPR 2025 Highlight] Code and datasets for "Which Viewpoint Shows it Best?Language for Weakly SupervisingView Selection in Multi-view Instructional Videos"
-
Updated
Jul 28, 2025 - Python
[CVPR 2025 Highlight] Code and datasets for "Which Viewpoint Shows it Best?Language for Weakly SupervisingView Selection in Multi-view Instructional Videos"
Resource-aware multimodal scene understanding with view selection for efficient captioning and QA.
Core implementation of VCAM (View Contribution Assessment Module) and Oracle Loss for View Selection, as presented in our PR submission.
Add a description, image, and links to the view-selection topic page so that developers can more easily learn about it.
To associate your repository with the view-selection topic, visit your repo's landing page and select "manage topics."