Towards Adaptive Human-centric Video Anomaly Detection: A Comprehensive Framework and A New Benchmark
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915205910364160 |
|---|---|
| author | Pazho, Armin Danesh Yao, Shanle Noghre, Ghazal Alinezhad Ardabili, Babak Rahimi Katariya, Vinit Tabkhi, Hamed |
| author_facet | Pazho, Armin Danesh Yao, Shanle Noghre, Ghazal Alinezhad Ardabili, Babak Rahimi Katariya, Vinit Tabkhi, Hamed |
| contents | Human-centric Video Anomaly Detection (VAD) aims to identify human behaviors that deviate from normal. At its core, human-centric VAD faces substantial challenges, such as the complexity of diverse human behaviors, the rarity of anomalies, and ethical constraints. These challenges limit access to high-quality datasets and highlight the need for a dataset and framework supporting continual learning. Moving towards adaptive human-centric VAD, we introduce the HuVAD (Human-centric privacy-enhanced Video Anomaly Detection) dataset and a novel Unsupervised Continual Anomaly Learning (UCAL) framework. UCAL enables incremental learning, allowing models to adapt over time, bridging traditional training and real-world deployment. HuVAD prioritizes privacy by providing de-identified annotations and includes seven indoor/outdoor scenes, offering over 5x more pose-annotated frames than previous datasets. Our standard and continual benchmarks, utilize a comprehensive set of metrics, demonstrating that UCAL-enhanced models achieve superior performance in 82.14% of cases, setting a new state-of-the-art (SOTA). The dataset can be accessed at https://github.com/TeCSAR-UNCC/HuVAD. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_14329 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Adaptive Human-centric Video Anomaly Detection: A Comprehensive Framework and A New Benchmark Pazho, Armin Danesh Yao, Shanle Noghre, Ghazal Alinezhad Ardabili, Babak Rahimi Katariya, Vinit Tabkhi, Hamed Computer Vision and Pattern Recognition Artificial Intelligence Human-centric Video Anomaly Detection (VAD) aims to identify human behaviors that deviate from normal. At its core, human-centric VAD faces substantial challenges, such as the complexity of diverse human behaviors, the rarity of anomalies, and ethical constraints. These challenges limit access to high-quality datasets and highlight the need for a dataset and framework supporting continual learning. Moving towards adaptive human-centric VAD, we introduce the HuVAD (Human-centric privacy-enhanced Video Anomaly Detection) dataset and a novel Unsupervised Continual Anomaly Learning (UCAL) framework. UCAL enables incremental learning, allowing models to adapt over time, bridging traditional training and real-world deployment. HuVAD prioritizes privacy by providing de-identified annotations and includes seven indoor/outdoor scenes, offering over 5x more pose-annotated frames than previous datasets. Our standard and continual benchmarks, utilize a comprehensive set of metrics, demonstrating that UCAL-enhanced models achieve superior performance in 82.14% of cases, setting a new state-of-the-art (SOTA). The dataset can be accessed at https://github.com/TeCSAR-UNCC/HuVAD. |
| title | Towards Adaptive Human-centric Video Anomaly Detection: A Comprehensive Framework and A New Benchmark |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2408.14329 |