ReQuest: Rethinking-based Question-Aware Frame Selection for Long-Form Video QA

• URL: http://arxiv.org/abs/2607.01737v1
• Date: Thu, 02 Jul 2026 05:46:42 GMT
• Title: ReQuest: Rethinking-based Question-Aware Frame Selection for Long-Form Video QA
• Abstract summary: ReQuest is an uncertainty-driven, question-adaptive selection pipeline that aligns question intent with relevant video content.<n> Experiments on Video-MME, MLVU, and LongBench demonstrate consistent accuracy gains with competitive computational cost.
• Score: 17.699690126341412
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent multimodal large language models (MLLMs) have substantially advanced video understanding, yet long-form video QA remains challenging under fixed input token budgets, where uniform sampling can be inefficient for evidence localization. We propose ReQuest , an uncertainty-driven, question-adaptive keyframe selection pipeline that aligns question intent with relevant video content through selective computation. ReQuest integrates (i) a lightweight question-aware selector distilled from MLLM-generated supervision, (ii) Re-thinking Routing that triggers additional inference only when the model is uncertain with a length-adaptive criterion, and (iii) uncertainty-guided adaptive non-maximum suppression that selects temporally diverse frames while adjusting spacing based on question difficulty. As a plug-andplay method, ReQuest improves long-video QA without modifying or fine-tuning the underlying MLLM. Experiments on Video-MME, MLVU, and LongVideoBench demonstrate consistent accuracy gains with competitive computational cost, with particularly strong improvements in medium and long video regimes.

Related papers

• Efficient Frame Selection for Long Videos at Test Time with Attention-Based MLLM Selectors [69.75895255395702]
  Cross-modal attention at validation-selected extraction layers in MLLMs already provides query-relevant frame evidence without requiring autoregressive generation.<n>A lightweight MLLM selector, even with only 2B parameters, can extract frame-level evidence by converting selected-layer attention into relevance scores through query-conditioned aggregation.<n>Under a 32-frame budget, our selector improves over uniform sampling by up to 6.4 points on Video-MME and outperforms prior training-based selectors under matched frame budgets.
  arXiv  Detail & Related papers  (2026-07-17T07:04:31Z)
• QSVideo: Query-Conditioned Semantic Temporal Retrieval for Video Understanding [31.789999490173255]
  Multimodal retrieval has emerged as a critical component of video understanding.<n>Existing multimodal retrieval methods suffer from biased relevance estimation, limited diversity, and temporal collapse.<n>We propose QSVideo, a unified framework that addresses relevance, diversity, and temporal modeling in video retrieval.
  arXiv  Detail & Related papers  (2026-07-06T00:19:42Z)
• Learning Question-Aware Keyframe Selection with Synthetic Supervision for Video Question Answering [11.557860792712171]
  Keyframe selection offers efficiency and sharper reasoning but suffers from sparse supervision and redundant frame choices when relying on image-text similarity.<n>We present a question-aware selection framework with two components: pseudo labels derived from LMMs that provide informative supervision and a coverage regularization that promotes diverse, complementary evidence across time.
  arXiv  Detail & Related papers  (2026-03-16T08:07:14Z)
• Optimizing Multimodal LLMs for Egocentric Video Understanding: A Solution for the HD-EPIC VQA Challenge [52.31833115696867]
  We propose a framework integrating query/choice pre-processing, domain-specific Qwen2.5-VL fine-tuning, and a novel Temporal Chain-of-Thought (T-CoT) prompting for multi-step reasoning.<n>This system achieves 41.6% accuracy on HD-EPIC VQA, highlighting the need for holistic pipeline optimization in demanding video understanding.
  arXiv  Detail & Related papers  (2026-01-15T09:43:49Z)
• Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding [33.58579390725519]
  Video-MTR is a reinforced multi-turn reasoning framework designed to enable iterative key video segment selection and question comprehension.<n>Unlike traditional video reasoning pipeline, which generate predictions in a single turn, Video-MTR performs reasoning in multiple turns.<n>To ensure intermediate reasoning process, we introduce a novel gated bi-level reward system.
  arXiv  Detail & Related papers  (2025-08-28T06:55:08Z)
• Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs [13.306662159600677]
  We introduce video QFrame, a novel approach for adaptive frame selection and multi-temporal scaling.<n>Q-Frame employs a training-free, plug-and-play strategy generated by a text-image matching network like CLIP.<n>We demonstrate Q-Frame's effectiveness through extensive experiments on benchmark datasets.
  arXiv  Detail & Related papers  (2025-06-27T11:30:51Z)
• Moment Sampling in Video LLMs for Long-Form Video QA [22.638644170177013]
  "moment sampling" is a model-agnostic approach that enables the model to select the most relevant frames according to the context of the question.<n>By focusing on the frames most pertinent to the given question, our method enhances long-form VideoQA performance in Video LLMs.
  arXiv  Detail & Related papers  (2025-06-18T03:23:56Z)
• Temporal Preference Optimization for Long-Form Video Understanding [63.196246578583136]
  Temporal Preference Optimization (TPO) is a novel post-training framework designed to enhance the temporal grounding capabilities of video-LMMs.<n>TPO significantly enhances temporal understanding while reducing reliance on manually annotated data.<n>LLaVA-Video-TPO establishes itself as the leading 7B model on the Video-MME benchmark.
  arXiv  Detail & Related papers  (2025-01-23T18:58:03Z)
• Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries [50.47265863322891]
  Video Question Answering (Video QA) is a challenging video understanding task that requires models to comprehend entire videos.<n>Recent advancements in Multimodal Large Language Models (MLLMs) have transformed video QA by leveraging their exceptional commonsense reasoning capabilities.<n>We propose T-Former, a novel temporal modeling method that creates a question-guided temporal bridge between frame-wise visual perception and the reasoning capabilities of LLMs.
  arXiv  Detail & Related papers  (2024-12-26T17:53:14Z)
• LMM-VQA: Advancing Video Quality Assessment with Large Multimodal Models [53.64461404882853]
  Video quality assessment (VQA) algorithms are needed to monitor and optimize the quality of streaming videos. Here, we propose the first Large Multi-Modal Video Quality Assessment (LMM-VQA) model, which introduces a novel visual modeling strategy for quality-aware feature extraction.
  arXiv  Detail & Related papers  (2024-08-26T04:29:52Z)
• LvBench: A Benchmark for Long-form Video Understanding with Versatile Multi-modal Question Answering [49.68215536040896]
  LvBench is a long-form video understanding benchmark for versatile multi-modal question-answering.<n>We consider videos ranging from 70 seconds to 4 hours, covering single-scene, multi-scene, and full-scene contexts.<n>Our dataset comprises 20,061 question-answer pairs sourced from 100 carefully selected movies.
  arXiv  Detail & Related papers  (2023-12-08T03:33:38Z)
• MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering [73.61182342844639]
  We introduce a new model named Multi-modal Iterative Spatial-temporal Transformer (MIST) to better adapt pre-trained models for long-form VideoQA. MIST decomposes traditional dense spatial-temporal self-attention into cascaded segment and region selection modules. Visual concepts at different granularities are then processed efficiently through an attention module.
  arXiv  Detail & Related papers  (2022-12-19T15:05:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.