AI RESEARCH
GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding
arXiv CS.CV
•
ArXi:2603.25072v1 Announce Type: new Video Large Language Models (VLMs) have achieved remarkable success in video understanding, but the significant computational cost from processing dense frames severely limits their practical application. Existing methods alleviate this by selecting keyframes, but their greedy decision-making, combined with a decoupled evaluation of relevance and diversity, often falls into local optima and results in erroneously selecting irrelevant noise frames. To address these challenges, we propose GIFT: Global Irreplaceability Frame Targeting, a novel.