See More, Think Deeper: Query-Expanded Visual Evidence and Answer-Clue Guided Reflection for Long Video Understanding
2026-06-08 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors introduce CoVER, a new method to improve how video-based language models understand long videos. Their approach helps the model gather more visual information by expanding the search queries and then double-check the answers using specific visual clues. This shifts the process from just producing answers to carefully reasoning with visual evidence. Tests show that CoVER performs better than similar-sized models and even beats some top closed-source models on certain tasks.
Video Large Language Modelslong-video understandingvisual evidencequery expansionanswer verificationvisual feedbackevidence-centric reasoninglanguage modelsmodel evaluation
Authors
Shuning Wang, Zhiheng Wu, YiNuo Lu, Naiming Liu, Chen Jia, Bowen Liu, Shuo Nie, Weijie Zhu, Yumeng Zhang
Abstract
Recent advances in Video Large Language Models (Video-LLMs) have enabled performance on long-video understanding tasks. However, existing methods still face two key limitations: evidence acquisition often relies on a single search intent, and answer generation lacks an effective visual feedback mechanism. To address these limitations, we propose \textbf{CoVER}, a Comprehensive Visual Evidence and Reflection framework for long-video understanding. CoVER enables Video-LLMs to \textbf{See More} by dynamically gathering query-expanded visual evidence, and \textbf{Think Deeper} by verifying draft answers with effective answer-specific visual feedback. Together, these mechanisms shift long-video understanding from answer-centric generation to evidence-centric and visually verifiable reasoning. Experimental results show that CoVER-7B substantially outperforms models with the same parameter scale and even surpasses state-of-the-art closed-source models on certain metrics.