# Coverage-Driven Adaptive Keyframe Selection for Video Understanding

arXiv: https://arxiv.org/abs/2608.00714 · HTML: https://mlsanity.com/paper/2608.00714/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 13 of its 22 references that are in the map.
- First posted on arXiv 1 Aug 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 13 of 13)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding](https://mlsanity.com/paper/2407.15754/) (2024)
- [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024)
- [VideoAgent: Long-form Video Understanding with Large Language Model as Agent](https://mlsanity.com/paper/2403.10517/) (2024)
- [HourVideo: 1-Hour Video-Language Understanding](https://mlsanity.com/paper/2411.04998/) (2024)
- [M-LLM Based Video Frame Selection for Efficient Video Understanding](https://mlsanity.com/paper/2502.19680/) (2025)
- [Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs](https://mlsanity.com/paper/2506.22139/) (2025)
- [MDP3: A Training-free Approach for List-wise Frame Selection in Video-LLMs](https://mlsanity.com/paper/2501.02885/) (2025)
- [LongVideoAgent: Multi-Agent Reasoning with Long Videos](https://mlsanity.com/paper/2512.20618/) (2025)
- [Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding](https://mlsanity.com/paper/2512.04000/) (2025)
- [Towards Fast and Effective Long Video Understanding of Multimodal Large Language Models via Adaptive Quasi-Gaussian Sampling](https://mlsanity.com/paper/2606.24187/) (2026)
- [Efficient Frame Selection for Long Videos at Test Time with Attention-Based MLLM Selectors](https://mlsanity.com/paper/2607.15689/) (2026)

## Built on by (most cited first, 1 of 1)

- [MetaSampling: Making Frame Samplers Efficient for Long-Video Question Answering](https://mlsanity.com/paper/2609.33998/) (2026)

## Abstract (arXiv)

Recent advances in large vision-language models (LVLMs) have enabled long-video understanding and analysis. However, processing the large number of frames in a video incurs substantial computational overhead. Existing methods reduce LVLM inference costs by scoring frame-query relevance before inference and selecting keyframes accordingly. Nevertheless, the distribution of relevant frames varies across queries, and these methods often need to score hundreds or thousands of frames. To address this limitation, we propose CSES, a training-free semantic keyframe selector that adaptively determines the numbers of frames to score and keyframes to select. CSES estimates the prominence of the frame-query relevance profile to guide active acquisition and adapt the temporal coverage of each input. It then formulates keyframe selection as a coverage problem that jointly accounts for semantic relevance, temporal redundancy, and visual redundancy. Active acquisition and keyframe selection terminate based on coverage saturation. The selection objective is monotone and submodular, enabling greedy optimization with a standard approximation guarantee. Experiments with four LVLMs on two benchmarks show that our method preserves accuracy while scoring 4-13× fewer frames and selecting 18.4%-20.5% fewer input keyframes than existing baselines. CSES further achieves a 3.1-5.4× speedup in frame selection over baselines.