CVApr 21

Less is More: Token-Efficient Video-QA via Adaptive Frame-Pruning and Semantic Graph Integration

arXiv:2508.0333769.8
AI Analysis

For practitioners deploying MLLMs on video tasks, this method offers a practical solution to reduce computational cost without sacrificing performance, addressing a key bottleneck in real-world applications.

The paper tackles the high token cost in Video-QA by proposing a framework that combines adaptive frame-pruning and a semantic graph, reducing tokens by up to 82.2% while maintaining or improving accuracy on LongVideoBench and Video-MME benchmarks.

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 keyframe selection is the dominant strategy for mitigating this, we identify a critical flaw: even state-of-the-art selectors produce prompts suffering from significant temporal redundancy, a challenge unique to video that we term 'visual echoes'. This issue leads to context dilution and can paradoxically degrade performance. To address this dual challenge, we propose a novel refinement framework that synergistically combines Adaptive Frame-Pruning(AFP) with a lightweight text-based semantic graph. AFP intelligently prunes 'visual echoes' by adaptively clustering frames, while the semantic graph provides crucial, low-cost semantic compensation. Conducting extensive experiments on the LongVideoBench and Video-MME benchmarks against multiple state-of-the-art selectors, our approach demonstrates a drastic reduction in total input tokens by up to 82.2%. Crucially, by creating a concise, high-quality prompt, our framework not only enhances efficiency but also demonstrates a remarkable ability to robustify and improve the accuracy of upstream selectors, achieving results that are highly competitive with, and often superior to, baselines that use vastly more frames.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes