# TAU-Bench: From Anomaly Instance Tracking to Fine-Grained Video Anomaly Understanding

arXiv: https://arxiv.org/abs/2608.05699 · HTML: https://mlsanity.com/paper/2608.05699/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 40 references that are in the map.
- First posted on arXiv 6 Aug 2026.

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.06958/) (2025)
- [Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision](https://mlsanity.com/paper/2007.04687/) (2020)
- [Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity](https://mlsanity.com/paper/2412.06171/) (2024)
- [VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perception](https://mlsanity.com/paper/2509.21100/) (2025)
- [VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos](https://mlsanity.com/paper/2411.04923/) (2024)
- [Advancing Video Anomaly Detection: A Concise Review and a New Dataset](https://mlsanity.com/paper/2402.04857/) (2024)
- [Hawk: Learning to Understand Open-World Video Anomalies](https://mlsanity.com/paper/2405.16886/) (2024)
- [A New Comprehensive Benchmark for Semi-supervised Video Anomaly Detection and Anticipation](https://mlsanity.com/paper/2305.13611/) (2023)
- [Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges](https://mlsanity.com/paper/2309.13925/) (2023)
- [UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning](https://mlsanity.com/paper/2509.18094/) (2025)
- [ReWatch-R1: Boosting Complex Video Reasoning in Large Vision-Language Models through Agentic Data Synthesis](https://mlsanity.com/paper/2509.23652/) (2025)
- [Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought](https://mlsanity.com/paper/2505.19877/) (2025)
- [VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2505.23504/) (2025)
- [SurveillanceVQA-589K: A Benchmark for Comprehensive Surveillance Video-Language Understanding with Large Models](https://mlsanity.com/paper/2505.12589/) (2025)
- [SAMTok: Representing Any Mask with Two Words](https://mlsanity.com/paper/2601.16093/) (2026)
- [A Survey of Video Datasets for Grounded Event Understanding](https://mlsanity.com/paper/2406.09646/) (2024)
- [Rethinking Image-to-Video Adaptation: An Object-centric Perspective](https://mlsanity.com/paper/2407.06871/) (2024)
- [Track Any Anomalous Object: A Granular Video Anomaly Detection Pipeline](https://mlsanity.com/paper/2506.05175/) (2025)
- [VAGU & GtS: LLM-Based Benchmark and Framework for Joint Video Anomaly Grounding and Understanding](https://mlsanity.com/paper/2507.21507/) (2025)
- [RoboStream: Weaving Spatio-Temporal Reasoning with Memory in Vision-Language Models for Robotics](https://mlsanity.com/paper/2603.12939/) (2026)
- [CueBench: Advancing Unified Understanding of Context-Aware Video Anomalies in Real-World](https://mlsanity.com/paper/2511.00613/) (2025)
- [Human-centric Behavior Description in Videos: New Benchmark and Model](https://mlsanity.com/paper/2310.02894/) (2023)
- [FineVAU: A Novel Human-Aligned Benchmark for Fine-Grained Video Anomaly Understanding](https://mlsanity.com/paper/2601.17258/) (2026)
- [Text-guided Fine-Grained Video Anomaly Understanding](https://mlsanity.com/paper/2511.00524/) (2025)

## Built on by (most cited first, 1 of 1)

- [Beyond Isolated Entities: Relation-Aware Multi-Entity Modeling for Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2609.31753/) (2026)

## Abstract (arXiv)

Humans understand anomalous events through a coherent perceptual process in which they identify the focal instance, follow its behavior as the event unfolds, and interpret why it violates the expectations of the surrounding scene. Video anomaly understanding (VAU) seeks to endow models with a similar capability, moving beyond deciding whether a video is anomalous toward explaining how the event develops and why it matters. Although recent vision--language models (VLMs) can generate detailed and plausible anomaly descriptions, their semantic fluency does not ensure that these interpretations remain grounded in the correct anomaly instance over time. Existing benchmarks typically evaluate tracking and semantic understanding through separate protocols, leaving such instance--semantic inconsistency largely unmeasured. We therefore introduce TAU-Bench, a track-centric benchmark for jointly evaluating anomaly instance tracking and fine-grained anomaly understanding. TAU-Bench contains 1,118 videos, 1,454 tracks, and 202,438 pixel-level masks spanning 49 event and 45 scene categories, together with track-centric annotations that connect instance-level identification, event-level understanding, and scene-level reasoning. To build TAU-Bench at scale, we developed an automated data engine integrating anomaly suitability filtering, anomaly instance track construction, hierarchical caption annotation, and human quality control. Evaluations across representative VLM families show that models producing plausible anomaly interpretations may still fail to localize and track the correct instance reliably, revealing a persistent gap between semantic reasoning and visual grounding. These findings therefore highlight instance-grounded evaluation as an important step toward more faithful and reliable VAU systems.