Year: 2025
Type: conference-paper
Abstract: We introduce PruneVid, a training-free visual token pruning method designed to enhance the efficiency of multimodal video understanding.While Large Language Models (LLMs) have shown promising performance on video tasks due to their advanced visual comprehension capabilities, the substantial redundancy inherent in video data poses significant computational challenges.To address this issue, PruneVid (1) reduces intrinsic video redundancy by merging temporally static and spatially similar tokens, and (2) leverages LLMs' inherent ability to selectively prune visual tokens irrelevant to specific queries, thereby improving model efficiency.We validate our method across multiple video benchmarks, demonstrating that PruneVid can prune over 80% of tokens while maintaining competitive performance when combined with different video LLMs.Our results highlight PruneVid's superior effectiveness and efficiency compared to existing pruning methods.
Authors: Xiaohu Huang, Hao Zhou, Kai Han
Institutions: University of Hong Kong, Baidu (China)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Award: G134391173
OpenAlex ID: W4412887841