Weakly-Supervised Spatiotemporal Anomaly Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916010138796032 |
|---|---|
| author | Gianchandani, Urvi Tirupattur, Praveen Shah, Mubarak |
| author_facet | Gianchandani, Urvi Tirupattur, Praveen Shah, Mubarak |
| contents | In this paper, we explore a weakly supervised method for anomaly detection. Since annotating videos is time-consuming, we only look at weak video-level labels during training. This means that given a video, we know that it is either normal or contains an anomaly, but no further annotations are used to train the network. Features are extracted from video clips that are either normal or anomalous. These features are used to determine anomaly scores for spatiotemporal regions of the clips based on a classifier and the implementation of a multiple instance ranking loss (MIL). We represent both anomalous and normal video clips as positive and negative bags, respectively, to apply MIL. Furthermore, since anomalies are usually localized to a part of a frame rather than the whole frame, we chose to explore temporal as well as spatial anomaly detection. We show our results on the UCF Crime2Local Dataset, which contains spatiotemporal annotations for a portion of the UCF Crime Dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_13746 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Weakly-Supervised Spatiotemporal Anomaly Detection Gianchandani, Urvi Tirupattur, Praveen Shah, Mubarak Computer Vision and Pattern Recognition Artificial Intelligence In this paper, we explore a weakly supervised method for anomaly detection. Since annotating videos is time-consuming, we only look at weak video-level labels during training. This means that given a video, we know that it is either normal or contains an anomaly, but no further annotations are used to train the network. Features are extracted from video clips that are either normal or anomalous. These features are used to determine anomaly scores for spatiotemporal regions of the clips based on a classifier and the implementation of a multiple instance ranking loss (MIL). We represent both anomalous and normal video clips as positive and negative bags, respectively, to apply MIL. Furthermore, since anomalies are usually localized to a part of a frame rather than the whole frame, we chose to explore temporal as well as spatial anomaly detection. We show our results on the UCF Crime2Local Dataset, which contains spatiotemporal annotations for a portion of the UCF Crime Dataset. |
| title | Weakly-Supervised Spatiotemporal Anomaly Detection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2605.13746 |