SRVAU-R1: 通过反射感知学习增强视频异常理解
SRVAU-R1: Enhancing Video Anomaly Understanding via Reflection-Aware Learning
AI总结:
SRVAU-R1通过引入反射感知学习框架,提升视频异常理解的推理能力和准确性。
摘要:
多模态大语言模型(MLLMs)在推理能力方面取得了显著进展,并在视频异常理解(VAU)任务中表现出有前途的有效性。然而,现有基于MLLM的方法仍然主要集中在异常的表面描述上,缺乏对异常行为的深入推理,如显式的自我反思和自我修正。为了解决这一问题,我们提出了Self-Reflection-Enhanced Reasoning for Video Anomaly Understanding(SRVAU-R1),一种结合反射的感知学习框架,该框架在MLLM推理中引入了反射。具体而言,SRVAU-R1引入了首个面向VAU的反射导向的链式思考数据集,为VAU提供了结构化的监督,包括初始推理、自我反思和修订推理。基于此,它包含一种新的反射感知学习范式,包括监督微调和强化微调,以增强多模态推理用于VAU。在多个视频异常基准上的广泛实验表明,SRVAU-R1在多个视频异常基准上表现优异, consistently 超过了现有方法,在时间异常定位准确性和推理质量方面实现了显著提升。
英文摘要:
Multi-modal large language models (MLLMs) have demonstrated significant progress in reasoning capabilities and shown promising effectiveness in video anomaly understanding (VAU) tasks. However, existing MLLM-based approaches remain largely focused on surface-level descriptions of anomalies, lacking deep reasoning over abnormal behaviors like explicit self-reflection and self-correction. To address that, we propose Self-Reflection-Enhanced Reasoning for Video Anomaly Understanding (SRVAU-R1), a reflection-aware learning framework that incorporates reflection in MLLM reasoning. Specifically, SRVAU-R1 introduces the first reflection-oriented Chain-of-Thought dataset tailored for VAU, providing structured supervision with initial reasoning, self-reflection, and revised reasoning. Based on that, it includes a novel reflection-aware learning paradigm with supervised fine-tuning and reinforcement fine-tuning to enhance multi-modal reasoning for VAU. Extensive experiments on multiple video anomaly benchmarks demonstrate that SRVAU-R1 consistently outperforms existing methods, achieving significant improvements in both temporal anomaly localization accuracy and reasoning quality.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。