# FineVAU: A Novel Human-Aligned Benchmark for Fine-Grained Video Anomaly Understanding

arXiv: https://arxiv.org/abs/2601.17258 · HTML: https://mlsanity.com/paper/2601.17258/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 22 references that are in the map.
- First posted on arXiv 24 Jan 2026.

## Builds on (most cited first, 13 of 13)

- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024)
- [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)
- [Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision](https://mlsanity.com/paper/2007.04687/) (2020)
- [Benchmarking and Improving Detail Image Caption](https://mlsanity.com/paper/2405.19092/) (2024)
- [Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity](https://mlsanity.com/paper/2412.06171/) (2024)
- [Hawk: Learning to Understand Open-World Video Anomalies](https://mlsanity.com/paper/2405.16886/) (2024)
- [Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges](https://mlsanity.com/paper/2309.13925/) (2023)
- [SurveillanceVQA-589K: A Benchmark for Comprehensive Surveillance Video-Language Understanding with Large Models](https://mlsanity.com/paper/2505.12589/) (2025)
- [Exploring What Why and How: A Multifaceted Benchmark for Causation Understanding of Video Anomaly](https://mlsanity.com/paper/2412.07183/) (2024)

## Built on by (most cited first, 3 of 3)

- [AgenticVAU: Multi-Agent Explore-Verify Reasoning for Video Anomaly Understanding](https://mlsanity.com/paper/2608.03779/) (2026)
- [TAU-Bench: From Anomaly Instance Tracking to Fine-Grained Video Anomaly Understanding](https://mlsanity.com/paper/2608.05699/) (2026)
- [Learning Temporal Evidence Selection for Video Anomaly Understanding](https://mlsanity.com/paper/2610.16299/) (2026)

## Abstract (arXiv)

Video Anomaly Understanding (VAU) is a novel task focused on describing unusual occurrences in videos. Despite growing interest, the evaluation of VAU remains an open challenge. Existing benchmarks rely on n-gram-based metrics (e.g., BLEU, ROUGE-L) or LLM-based evaluation. The first fails to capture the rich, free-form, and visually grounded nature of LVLM responses, while the latter focuses on assessing language quality over factual relevance, often resulting in subjective judgments that are misaligned with human perception. In this work, we address this issue by proposing FineVAU, a new benchmark for VAU that shifts the focus towards rich, fine-grained and domain-specific understanding of anomalous videos. We formulate VAU as a three-fold problem, with the goal of comprehensively understanding key descriptive elements of anomalies in video: events (What), participating entities (Who) and location (Where). Our benchmark introduces a) FVScore, a novel, human-aligned evaluation metric that assesses the presence of critical visual elements in LVLM answers, providing interpretable, fine-grained feedback; and b) FineW3, a novel, comprehensive dataset curated through a structured and fully automatic procedure that augments existing human annotations with high quality, fine-grained visual information. Human evaluation reveals that our proposed metric has a superior alignment with human perception of anomalies in comparison to current approaches. Detailed experiments on FineVAU unveil critical limitations in LVLM's ability to perceive anomalous events that require spatial and fine-grained temporal understanding, despite strong performance on coarse grain, static information, and events with strong visual cues.