Salvato in:
Dettagli Bibliografici
Autori principali: Zhao, Zihao, Cao, Shengting, Ye, Muchao
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2602.01004
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911413732114432
author Zhao, Zihao
Cao, Shengting
Ye, Muchao
author_facet Zhao, Zihao
Cao, Shengting
Ye, Muchao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_01004
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SRVAU-R1: Enhancing Video Anomaly Understanding via Reflection-Aware Learning
Zhao, Zihao
Cao, Shengting
Ye, Muchao
Computer Vision and Pattern Recognition
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.
title SRVAU-R1: Enhancing Video Anomaly Understanding via Reflection-Aware Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.01004