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

• URL: http://arxiv.org/abs/2608.05699v1
• Date: Thu, 06 Aug 2026 07:43:17 GMT
• Title: TAU-Bench: From Anomaly Instance Tracking to Fine-Grained Video Anomaly Understanding
• Abstract summary: Video anomaly understanding (VAU) seeks to endow models with a similar capability.<n>We introduce TAU-Bench, a benchmark for evaluating anomaly instance tracking and fine-grained anomaly understanding.<n>We show that models producing plausible anomaly interpretations may still fail to localize and track the correct instance reliably.
• Score: 24.101948294850107
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• What's the Catch? Evaluating Temporal Consistency in Vision-Language Models [0.11121828451787184]
  Vision-language models (VLMs) achieve strong performance on video and image-sequence benchmarks, yet it remains unclear whether they capture temporal structure.<n>We introduce TimeCatch, where temporal anomalies are created by swapping consecutive frames and frame-level anomalies by replacing a frame with Gaussian noise.<n>Our evaluation reveals a substantial gap between frame-level and temporal anomaly detection.
  arXiv  Detail & Related papers  (2026-08-24T16:40:49Z)
• Structured Evidence Selection for Weakly Supervised Video Anomaly Detection [24.113971346791942]
  Weakly supervised video anomaly detection relies solely on video-level labels for training.<n>We propose a Structured Evidence Selection framework (SESAD) that reformulates anomaly detection as a structured reasoning process.<n>SESAD reorganizes clip representations into semantically structured candidate evidence and performs context-conditioned selection under scene and action constraints.
  arXiv  Detail & Related papers  (2026-07-11T13:01:01Z)
• Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models [154.39583176906893]
  Large language models (MLs) have advanced understanding, they remain highly prone to hallucinations in scenes.<n>We argue this stems from a failure intemporal monitoring, the ability to persistently track object dynamic identities, states, and relations over time.<n>Existing benchmarks obscure this deficit relying on single final-answer queries that can often be resolved via local visual cues or statistical priors.
  arXiv  Detail & Related papers  (2026-05-09T14:32:36Z)
• Out of Context: Reliability in Multimodal Anomaly Detection Requires Contextual Inference [54.774686416991386]
  We argue that multimodal anomaly detection should be reframed as a cross-modal contextual inference problem.<n>This perspective has implications for model design, evaluation protocols, and benchmark construction.
  arXiv  Detail & Related papers  (2026-04-14T19:32:55Z)
• Weakly Supervised Video Anomaly Detection with Anomaly-Connected Components and Intention Reasoning [23.043341269626016]
  We propose a novel framework named LAS-VAD, short for Learning Anomaly Semantics for WS-VAD.<n>Our framework integrates anomaly-connected component mechanism and intention awareness mechanism.<n>It outperforms current state-of-the-art methods with remarkable gains.
  arXiv  Detail & Related papers  (2026-02-28T08:57:33Z)
• VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language Models [29.213430569936943]
  We propose VADER, an LLM-driven framework for Video Anomaly unDErstanding.<n>VADER integrates object features with visual cues to enhance anomaly comprehension from video.<n> Experiments on multiple real-world VAU benchmarks demonstrate that VADER achieves strong results across anomaly description, explanation, and causal reasoning tasks.
  arXiv  Detail & Related papers  (2025-11-10T16:56:11Z)
• A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis [64.42659342276117]
  Most video-anomaly research stops at frame-wise detection, offering little insight into why an event is abnormal.<n>Recent video anomaly localization and video anomaly understanding methods improve explainability but remain data-dependent and task-specific.<n>We propose a unified reasoning framework that bridges the gap between temporal detection, spatial localization, and textual explanation.
  arXiv  Detail & Related papers  (2025-11-02T14:49:08Z)
• CueBench: Advancing Unified Understanding of Context-Aware Video Anomalies in Real-World [23.48765196513229]
  We introduce CueBench, the first of its kind Benchmark devoted to context-aware video anomalies.<n>We propose to unify and benchmark context-aware VAU with various challenging tasks across recognition, temporal grounding, detection, and anticipation.<n>We further develop Cue-R1 based on R1-style reinforcement fine-tuning with verifiable, task-aligned, and hierarchy-refined rewards.
  arXiv  Detail & Related papers  (2025-11-01T16:29:35Z)
• Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images [96.43608872116347]
  AnomReason is a large-scale benchmark with structured annotations as quadruple textbfAnomAgent<n>AnomReason and AnomAgent serve as a foundation for measuring and improving the semantic plausibility of AI-generated images.
  arXiv  Detail & Related papers  (2025-10-11T14:09:24Z)
• Exploring What Why and How: A Multifaceted Benchmark for Causation Understanding of Video Anomaly [12.896651217314744]
  We introduce a benchmark for Exploring the Causation of Video Anomalies (ECVA)<n>Our benchmark is meticulously designed, with each video accompanied by detailed human annotations.<n>We propose AnomEval, a specialized evaluation metric crafted to align closely with human judgment criteria for ECVA.
  arXiv  Detail & Related papers  (2024-12-10T04:41:44Z)
• VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs [64.60035916955837]
  VANE-Bench is a benchmark designed to assess the proficiency of Video-LMMs in detecting anomalies and inconsistencies in videos.<n>Our dataset comprises an array of videos synthetically generated using existing state-of-the-art text-to-video generation models.<n>We evaluate nine existing Video-LMMs, both open and closed sources, on this benchmarking task and find that most of the models encounter difficulties in effectively identifying the subtle anomalies.
  arXiv  Detail & Related papers  (2024-06-14T17:59:01Z)
• Learn Suspected Anomalies from Event Prompts for Video Anomaly Detection [16.77262005540559]
  A novel framework is proposed to guide the learning of suspected anomalies from event prompts. It enables a new multi-prompt learning process to constrain the visual-semantic features across all videos. Our proposed model outperforms most state-of-the-art methods in terms of AP or AUC.
  arXiv  Detail & Related papers  (2024-03-02T10:42:47Z)
• A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video [120.18562044084678]
  Abnormal event detection in video is a complex computer vision problem that has attracted significant attention in recent years. We propose a background-agnostic framework that learns from training videos containing only normal events.
  arXiv  Detail & Related papers  (2020-08-27T18:39:24Z)

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.