REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding
- URL: http://arxiv.org/abs/2511.13026v1
- Date: Mon, 17 Nov 2025 06:25:12 GMT
- Title: REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding
- Authors: Jiaze Li, Hao Yin, Wenhui Tan, Jingyang Chen, Boshen Xu, Yuxun Qu, Yijing Chen, Jianzhong Ju, Zhenbo Luo, Jian Luan,
- Abstract summary: Long-form video understanding involves richer and more dynamic visual input.<n> purely text-based reflection mechanisms lack cross-modal interaction capabilities.<n>We propose REVISOR, a novel framework for tool-augmented multimodal reflection.
- Score: 23.684146245231457
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Self-reflection mechanisms that rely on purely text-based rethinking processes perform well in most multimodal tasks. However, when directly applied to long-form video understanding scenarios, they exhibit clear limitations. The fundamental reasons for this lie in two points: (1)long-form video understanding involves richer and more dynamic visual input, meaning rethinking only the text information is insufficient and necessitates a further rethinking process specifically targeting visual information; (2) purely text-based reflection mechanisms lack cross-modal interaction capabilities, preventing them from fully integrating visual information during reflection. Motivated by these insights, we propose REVISOR (REflective VIsual Segment Oriented Reasoning), a novel framework for tool-augmented multimodal reflection. REVISOR enables MLLMs to collaboratively construct introspective reflection processes across textual and visual modalities, significantly enhancing their reasoning capability for long-form video understanding. To ensure that REVISOR can learn to accurately review video segments highly relevant to the question during reinforcement learning, we designed the Dual Attribution Decoupled Reward (DADR) mechanism. Integrated into the GRPO training strategy, this mechanism enforces causal alignment between the model's reasoning and the selected video evidence. Notably, the REVISOR framework significantly enhances long-form video understanding capability of MLLMs without requiring supplementary supervised fine-tuning or external models, achieving impressive results on four benchmarks including VideoMME, LongVideoBench, MLVU, and LVBench.
Related papers
- Agentic Video Intelligence: A Flexible Framework for Advanced Video Exploration and Understanding [43.785571875867]
We propose Agentic Video Intelligence (AVI), a flexible and training-free framework that can mirror human video comprehension through system-level design and optimization.<n>AVI introduces three key innovations: (1) a human-inspired three-phase reasoning process (Retrieve-Perceive-Review), (2) a structured video knowledge base organized through entity graphs, and (3) an open-source model ensemble combining reasoning LLMs with lightweight base CV models and VLM.
arXiv Detail & Related papers (2025-11-18T12:43:15Z) - ViSS-R1: Self-Supervised Reinforcement Video Reasoning [84.1180294023835]
We introduce a novel self-supervised reinforcement learning GRPO algorithm (Pretext-GRPO) within the standard R1 pipeline.<n>We also propose the ViSS-R1 framework, which streamlines and integrates pretext-task-based self-supervised learning directly into the MLLM's R1 post-training paradigm.
arXiv Detail & Related papers (2025-11-17T07:00:42Z) - Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models [78.32948112203228]
Video understanding represents the most challenging frontier in computer vision.<n>Recent emergence of Video-Large Multitemporal Models has demonstrated remarkable capabilities in video understanding tasks.<n>Survey aims to provide researchers and practitioners with a unified framework for advancing Video-LMM capabilities.
arXiv Detail & Related papers (2025-10-06T17:10:44Z) - Team of One: Cracking Complex Video QA with Model Synergy [24.75732964829523]
We propose a novel framework for open-ended video question answering that enhances reasoning depth and robustness in complex real-world scenarios.<n>Existing Video-Large Multimodal Models (Video-LMMs) often exhibit limited contextual understanding, weak temporal modeling, and poor generalization to ambiguous or compositional queries.
arXiv Detail & Related papers (2025-07-18T11:12:44Z) - Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency [56.475612147721264]
We propose a dual-reward formulation that supervises both semantic and temporal reasoning through discrete and continuous reward signals.<n>We evaluate our approach across eight representative video understanding tasks, including VideoQA, Temporal Video Grounding, and Grounded VideoQA.<n>Results underscore the importance of reward design and data selection in advancing reasoning-centric video understanding with MLLMs.
arXiv Detail & Related papers (2025-06-02T17:28:26Z) - ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning [68.76048244253582]
We introduce ViaRL, the first framework to leverage rule-based reinforcement learning (RL) for optimizing frame selection in video understanding.<n>ViaRL utilizes the answer accuracy of a downstream model as a reward signal to train a frame selector through trial-and-error.<n>ViaRL consistently delivers superior temporal grounding performance and robust generalization across diverse video understanding tasks.
arXiv Detail & Related papers (2025-05-21T12:29:40Z) - VURF: A General-purpose Reasoning and Self-refinement Framework for Video Understanding [65.12464615430036]
This paper introduces a Video Understanding and Reasoning Framework (VURF) based on the reasoning power of Large Language Models (LLMs)<n>Ours is a novel approach to extend the utility of LLMs in the context of video tasks, leveraging their capacity to generalize from minimal input and output demonstrations within a contextual framework.
arXiv Detail & Related papers (2024-03-21T18:00:00Z) - Video-based Person Re-identification with Long Short-Term Representation
Learning [101.62570747820541]
Video-based person Re-Identification (V-ReID) aims to retrieve specific persons from raw videos captured by non-overlapped cameras.
We propose a novel deep learning framework named Long Short-Term Representation Learning (LSTRL) for effective V-ReID.
arXiv Detail & Related papers (2023-08-07T16:22:47Z)
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.