Pith. sign in

REVIEW 9 cited by

Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.12235 v2 pith:FMCLJKJV submitted 2024-06-18 cs.CV

Huaxin Zhang , Xiaohao Xu , Xiang Wang , Jialong Zuo , Chuchu Han , Xiaonan Huang , Changxin Gao , Yuehuan Wang
show 1 more author
Nong Sang
This is my paper · ORCID
classification cs.CV
keywords anomalyvideodetectionholmes-vadmodelmultimodaltowardsbenchmark
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Towards open-ended Video Anomaly Detection (VAD), existing methods often exhibit biased detection when faced with challenging or unseen events and lack interpretability. To address these drawbacks, we propose Holmes-VAD, a novel framework that leverages precise temporal supervision and rich multimodal instructions to enable accurate anomaly localization and comprehensive explanations. Firstly, towards unbiased and explainable VAD system, we construct the first large-scale multimodal VAD instruction-tuning benchmark, i.e., VAD-Instruct50k. This dataset is created using a carefully designed semi-automatic labeling paradigm. Efficient single-frame annotations are applied to the collected untrimmed videos, which are then synthesized into high-quality analyses of both abnormal and normal video clips using a robust off-the-shelf video captioner and a large language model (LLM). Building upon the VAD-Instruct50k dataset, we develop a customized solution for interpretable video anomaly detection. We train a lightweight temporal sampler to select frames with high anomaly response and fine-tune a multimodal large language model (LLM) to generate explanatory content. Extensive experimental results validate the generality and interpretability of the proposed Holmes-VAD, establishing it as a novel interpretable technique for real-world video anomaly analysis. To support the community, our benchmark and model will be publicly available at https://holmesvad.github.io.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling

    cs.CV 2025-12 conditional novelty 6.0 of 10

    Scone unifies subject understanding and generation in a two-stage trained model to improve both composition and distinction in multi-subject image generation, outperforming prior open-source models on new benchmarks.

  2. Runtime Failure Hunting for Physics Engine Based Software Systems: How Far Can We Go?

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A new 1,000-video benchmark, PhysiXFails, with a 17-category taxonomy of physics failures, shows prompt-tuned large multimodal models outperform video anomaly detectors at detecting and naming physics rule violations ...

  3. SmartHome-Bench: A Comprehensive Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal Large Language Models

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A new smart-home video anomaly benchmark and a taxonomy-driven reflective LLM chain that improves MLLM anomaly detection accuracy by 11.62 percentage points over zero-shot prompting.

  4. VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning

    cs.CV 2025-05 reject novelty 6.0 of 10

    VAU-R1 uses Group Relative Policy Optimization with accuracy, format, and temporal-IoU rewards to improve video anomaly reasoning on a new LLM-generated benchmark, VAU-Bench.

  5. Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A two-stage trained MLLM with a perception-to-cognition chain-of-thought and a self-verification RL reward outperforms prior models on video anomaly detection and reasoning.

  6. Flashback: Memory-Driven Zero-shot, Real-time Video Anomaly Detection

    cs.CV 2025-05 conditional novelty 6.0 of 10

    An offline LLM builds a pseudo-scene caption memory; online embedding retrieval against that memory yields zero-shot, real-time, explainable video anomaly detection with SOTA scores on UCF-Crime and XD-Violence.

  7. VAGU & GtS: LLM-Based Benchmark and Framework for Joint Video Anomaly Grounding and Understanding

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A new benchmark, a training-free framework, and a joint metric for video anomaly detection that combines temporal grounding with semantic understanding.

  8. MA-CBP: A Criminal Behavior Prediction Framework Based on Multi-Agent Asynchronous Collaboration

    cs.CV 2025-08 unverdicted novelty 4.0 of 10

    MA-CBP is a proposed multi-agent AI system that turns live video into text descriptions and summaries and reasons jointly to warn about potential criminal behavior.

  9. Large Language Models for Crash Detection in Video: A Survey of Methods, Datasets, and Challenges

    cs.CV 2025-07 conditional novelty 3.0 of 10

    A structured survey of 2023-2025 LLM and VLM methods for crash detection in video, with notable internal inconsistencies in reported numbers.

Pith tools