CORTEXA
← Browse
arxivcs.CV2026-07-02

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

Minkuk Kim, Suyong Yun, Young Tae Kim, Jinyoung Moon, Jinwoo Choi, Seong Tae Kim

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.

View free PDFSource page

Related papers

arxivcs.CV2026-07-22

Self Gradient Forcing: Native Long Video Extrapolation

Junhao Zhuang, Shiyi Zhang, Yuxuan Bian, Yaowei Li, Yawen Luo, Yijun Liu, et al.

Recent autoregressive video diffusion methods are increasingly built upon Self Forcing, where the student is trained on histories produced by its own rollout rather than ground-truth video contexts. This reduces exposure bias, but the historical key-value cache is still used by f…

View free PDFSource page
arxivcs.CV2026-07-31

HierDoc: Hierarchical Page-to-Region Evidence Routing for Long-Document Visual Question Answering

Rongjian Gu, Wengang Zhou, Junyu Xiong, Yonghui Wang, Bing Yin, Bei Wang, et al.

Multi-page document visual question answering requires locating sparse evidence at both the page and region levels. Existing approaches typically emphasize one level over the other: page-centric methods focus on page acquisition, with region operations serving mainly as navigatio…

View free PDFSource page
arxivcs.CV2026-07-23

AUCH-Net: Action Unit-Based Consistency-Aware Hypergraph Network for Cross-Domain Few-Shot Facial Expression Recognition

Xinhan Qiu, Yan Yan, Rui Zhu, Si Chen, Hanzi Wang

Recently, cross-domain few-shot facial expression recognition (CF-FER) has received considerable attention. However, the performance of existing CF-FER methods is still unsatisfactory due to inferior transferable feature learning under large domain discrepancy and limited target…

View free PDFSource page
arxivcs.LGcs.CV2026-07-24

Class-Balanced Softmax: A Bayes Theory-Based Method for Long-Tailed Recognition

Yi-Hang Zhu, Rajeev Raman, Shiqi Su, Jianyuan Sun, Xinyu Yang, Nan Xing, et al.

Deep learning models using traditional softmax classifiers have achieved remarkable success in various classification tasks. However, their performance degrades significantly on imbalanced datasets. Although Balanced Softmax is widely adopted as a state-of-the-art rebalancing met…

View free PDFSource page