# Ground, Cover, and Refine: Evidence-Centric Frame Selection for Long-Video Question Answering

arXiv: https://arxiv.org/abs/2608.01660 · HTML: https://mlsanity.com/paper/2608.01660/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 24 references that are in the map.
- First posted on arXiv 3 Aug 2026.

## Builds on (most cited first, 7 of 7)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024)
- [Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding](https://mlsanity.com/paper/2503.13139/) (2025)
- [Where to Focus: Query-Modulated Multimodal Keyframe Selection for Long Video Understanding](https://mlsanity.com/paper/2604.17422/) (2026)
- [MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering](https://mlsanity.com/paper/2606.05917/) (2026)

## Built on by (most cited first, 2 of 2)

- [LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception](https://mlsanity.com/paper/2609.39938/) (2026)
- [Video Evidence Indexing: Learning Where to Look from Video Previews for Token-Budgeted Long-Video Question Answering](https://mlsanity.com/paper/2610.00757/) (2026)

## Abstract (arXiv)

Long-video question answering requires identifying sparse yet critical evidence from videos containing thousands of frames under a constrained visual-token budget. Existing methods either select query-aware frames in a single pass or rely on timestamped text solely as retrieval guidance, leading to two key limitations. First, selected frames tend to cluster around local relevance peaks, and once the budget is exhausted, omitted evidence cannot be recovered. Second, textual and visual evidence remain weakly aligned. We propose GCR, a training-free framework that casts fixed-budget frame selection as a joint evidence curation problem. Ground converts timestamped text into temporal events, selects query-relevant real frame anchors, and renders each event text onto its temporally aligned frame. Cover supplements grounded events with direct visual anchors for complementary visual evidence and applies global maximal marginal relevance to preserve diverse context. Refine revisits omitted temporal regions and replaces the weakest revisable context frame with a real-frame medoid---but only when the medoid offers greater evidence value. GCR maintains a fixed number of chronologically ordered frames and requires no VLM training or architectural modification. Experiments on LongVideoBench and Video-MME, across three 7B backbones and frame budgets of 8, 32, and 64, demonstrate consistent improvements in long-video QA. With the 7B LLaVA-OV backbone and 32 frames, GCR achieves 64.25% and 62.15% on the two benchmarks, outperforming the strongest reproduced baselines by 2.54 and 1.93 percentage points, respectively.