Full metadata record
DC pole | Hodnota | Jazyk |
---|---|---|
dc.contributor.author | Arad, Yoav | |
dc.contributor.author | Werman, Michael | |
dc.contributor.editor | Skala, Václav | |
dc.date.accessioned | 2024-07-25T19:25:25Z | - |
dc.date.available | 2024-07-25T19:25:25Z | - |
dc.date.issued | 2024 | |
dc.identifier.citation | WSCG 2024: full papers proceedings: 32. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 33-46. | en |
dc.identifier.issn | 2464–4625 (online) | |
dc.identifier.issn | 2464–4617 (print) | |
dc.identifier.uri | http://hdl.handle.net/11025/57375 | |
dc.format | 14 s. | cs |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | en |
dc.publisher | Václav Skala - UNION Agency | en |
dc.rights | © Václav Skala - UNION Agency | en |
dc.subject | detekce anomálie videa | cs |
dc.subject | počítačové vidění | cs |
dc.subject | chytré sledovací systémy | cs |
dc.title | Beyond the Benchmark: Detecting Diverse Anomalies in Videos | en |
dc.type | konferenční příspěvek | cs |
dc.type | conferenceObject | en |
dc.rights.access | openAccess | en |
dc.type.version | publishedVersion | en |
dc.description.abstract-translated | Video Anomaly Detection (VAD) plays a crucial role in modern surveillance systems, aiming to identify various anomalies in real-world situations. However, current benchmark datasets predominantly emphasize simple, single frame anomalies such as novel object detection. This narrow focus restricts the advancement of VAD models. In this research, we advocate for an expansion of VAD investigations to encompass intricate anomalies that extend beyond conventional benchmark boundaries. To facilitate this, we introduce two datasets, HMDB-AD and HMDB Violence, to challenge models with diverse action-based anomalies. These datasets are derived from the HMDB51 action recognition dataset. We further present Multi-Frame Anomaly Detection (MFAD), a novel method built upon the AI-VAD framework. AI-VAD utilizes single-frame features such as pose estimation and deep image encoding, and two-frame features such as object velocity. They then apply a density estimation algorithm to com pute anomaly scores. To address complex multi-frame anomalies, we add deep video encoded features capturing long-range temporal dependencies, and logistic regression to enhance final score calculation. Experimental results confirm our assumptions, highlighting existing models limitations with new anomaly types. MFAD excels in both simple and complex anomaly detection scenarios. | en |
dc.subject.translated | video anomaly detection | en |
dc.subject.translated | computer vision | en |
dc.subject.translated | smart surveillance systems | en |
dc.identifier.doi | https://doi.org/10.24132/10.24132/CSRN.3401.5 | |
dc.type.status | Peer reviewed | en |
Vyskytuje se v kolekcích: | WSCG 2024: Full Papers Proceedings |
Soubory připojené k záznamu:
Soubor | Popis | Velikost | Formát | |
---|---|---|---|---|
A31-2024.pdf | Plný text | 10,85 MB | Adobe PDF | Zobrazit/otevřít |
Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam:
http://hdl.handle.net/11025/57375
Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.