Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity
- URL: http://arxiv.org/abs/2412.06171v1
- Date: Mon, 09 Dec 2024 03:05:34 GMT
- Title: Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity
- Authors: Huaxin Zhang, Xiaohao Xu, Xiang Wang, Jialong Zuo, Xiaonan Huang, Changxin Gao, Shanjun Zhang, Li Yu, Nong Sang,
- Abstract summary: HIVAU-70k is a benchmark for hierarchical video anomaly understanding across any granularity.
We develop a semi-automated annotation engine that efficiently scales high-quality annotations.
For efficient anomaly detection in long videos, we propose the Anomaly-focused Temporal Sampler.
- Score: 35.14762107193339
- License:
- Abstract: How can we enable models to comprehend video anomalies occurring over varying temporal scales and contexts? Traditional Video Anomaly Understanding (VAU) methods focus on frame-level anomaly prediction, often missing the interpretability of complex and diverse real-world anomalies. Recent multimodal approaches leverage visual and textual data but lack hierarchical annotations that capture both short-term and long-term anomalies. To address this challenge, we introduce HIVAU-70k, a large-scale benchmark for hierarchical video anomaly understanding across any granularity. We develop a semi-automated annotation engine that efficiently scales high-quality annotations by combining manual video segmentation with recursive free-text annotation using large language models (LLMs). This results in over 70,000 multi-granular annotations organized at clip-level, event-level, and video-level segments. For efficient anomaly detection in long videos, we propose the Anomaly-focused Temporal Sampler (ATS). ATS integrates an anomaly scorer with a density-aware sampler to adaptively select frames based on anomaly scores, ensuring that the multimodal LLM concentrates on anomaly-rich regions, which significantly enhances both efficiency and accuracy. Extensive experiments demonstrate that our hierarchical instruction data markedly improves anomaly comprehension. The integrated ATS and visual-language model outperform traditional methods in processing long videos. Our benchmark and model are publicly available at https://github.com/pipixin321/HolmesVAU.
Related papers
- Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts [57.01985221057047]
This paper introduces a novel method that learnstemporal prompt embeddings for weakly supervised video anomaly detection and localization (WSVADL) based on pre-trained vision-language models (VLMs)
Our method achieves state-of-theart performance on three public benchmarks for the WSVADL task.
arXiv Detail & Related papers (2024-08-12T03:31:29Z) - Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM [35.06386971859359]
Holmes-VAD is a novel framework that leverages precise temporal supervision and rich multimodal instructions.
We construct the first large-scale multimodal VAD instruction-tuning benchmark, VAD-Instruct50k.
Building upon the VAD-Instruct50k dataset, we develop a customized solution for interpretable video anomaly detection.
arXiv Detail & Related papers (2024-06-18T03:19:24Z) - 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.
Our dataset comprises an array of videos synthetically generated using existing state-of-the-art text-to-video generation models.
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) - Dynamic Erasing Network Based on Multi-Scale Temporal Features for
Weakly Supervised Video Anomaly Detection [103.92970668001277]
We propose a Dynamic Erasing Network (DE-Net) for weakly supervised video anomaly detection.
We first propose a multi-scale temporal modeling module, capable of extracting features from segments of varying lengths.
Then, we design a dynamic erasing strategy, which dynamically assesses the completeness of the detected anomalies.
arXiv Detail & Related papers (2023-12-04T09:40:11Z) - Open-Vocabulary Video Anomaly Detection [57.552523669351636]
Video anomaly detection (VAD) with weak supervision has achieved remarkable performance in utilizing video-level labels to discriminate whether a video frame is normal or abnormal.
Recent studies attempt to tackle a more realistic setting, open-set VAD, which aims to detect unseen anomalies given seen anomalies and normal videos.
This paper takes a step further and explores open-vocabulary video anomaly detection (OVVAD), in which we aim to leverage pre-trained large models to detect and categorize seen and unseen anomalies.
arXiv Detail & Related papers (2023-11-13T02:54:17Z) - Delving into CLIP latent space for Video Anomaly Recognition [24.37974279994544]
We introduce the novel method AnomalyCLIP, the first to combine Large Language and Vision (LLV) models, such as CLIP.
Our approach specifically involves manipulating the latent CLIP feature space to identify the normal event subspace.
When anomalous frames are projected onto these directions, they exhibit a large feature magnitude if they belong to a particular class.
arXiv Detail & Related papers (2023-10-04T14:01:55Z) - Towards Video Anomaly Retrieval from Video Anomaly Detection: New
Benchmarks and Model [70.97446870672069]
Video anomaly detection (VAD) has been paid increasing attention due to its potential applications.
Video Anomaly Retrieval ( VAR) aims to pragmatically retrieve relevant anomalous videos by cross-modalities.
We present two benchmarks, UCFCrime-AR and XD-Violence, constructed on top of prevalent anomaly datasets.
arXiv Detail & Related papers (2023-07-24T06:22:37Z) - Weakly-supervised Video Anomaly Detection with Contrastive Learning of
Long and Short-range Temporal Features [26.474395581531194]
We propose a novel method, named Multi-scale Temporal Network trained with top-K Contrastive Multiple Instance Learning (MTN-KMIL)
Our method outperforms several state-of-the-art methods by a large margin on three benchmark data sets.
arXiv Detail & Related papers (2021-01-25T12:04:00Z) - Robust Unsupervised Video Anomaly Detection by Multi-Path Frame
Prediction [61.17654438176999]
We propose a novel and robust unsupervised video anomaly detection method by frame prediction with proper design.
Our proposed method obtains the frame-level AUROC score of 88.3% on the CUHK Avenue dataset.
arXiv Detail & Related papers (2020-11-05T11:34:12Z)
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.