Less is More: Token-Efficient Video-QA via Adaptive Frame-Pruning and Semantic Graph Integration
By: Shaoguang Wang , Ziyang Chen , Yijie Xu and more
Potential Business Impact:
Makes videos easier for computers to understand.
The practical application of Multimodal Large Language Models (MLLMs) to Video Question Answering (Video-QA) is severely hindered by the high token cost of processing numerous video frames. While increasing the number of sampled frames is a common strategy, we observe a "less is more" phenomenon where excessive frames can paradoxically degrade performance due to context dilution. Concurrently, state-of-the-art keyframe selection methods, while effective, still yield significant temporal redundancy, which we term 'visual echoes'. To address these dual challenges, we propose Adaptive Frame-Pruning (AFP), a novel post-processing method that intelligently prunes the selected keyframes. AFP employs an adaptive hierarchical clustering algorithm on a fused ResNet-50 and CLIP feature space to identify and merge these echoes into single representatives. To compensate for information loss, we then introduce a lightweight, text-based semantic graph that provides critical context with minimal token overhead. Conducting extensive experiments on the LongVideoBench and VideoMME benchmarks across multiple leading MLLMs, our full approach demonstrates a drastic reduction in required frames by up to 86.9% and total input tokens by up to 83.2%. Crucially, by providing a concise, high-quality set of frames, our method not only enhances efficiency but often improves accuracy over baselines that use more frames. The code will be released upon publication.
Similar Papers
Less is More: Token-Efficient Video-QA via Adaptive Frame-Pruning and Semantic Graph Integration
CV and Pattern Recognition
Makes AI understand videos using fewer pictures.
Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing
Machine Learning (CS)
Makes computers understand long videos faster.
From Frames to Clips: Efficient Key Clip Selection for Long-Form Video Understanding
CV and Pattern Recognition
Helps computers understand long videos better.