Dual Guidance Semi-Supervised Action Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909709995343872 |
|---|---|
| author | Singh, Ankit Gavves, Efstratios Snoek, Cees G. M. Kuehne, Hilde |
| author_facet | Singh, Ankit Gavves, Efstratios Snoek, Cees G. M. Kuehne, Hilde |
| contents | Semi-Supervised Learning (SSL) has shown tremendous potential to improve the predictive performance of deep learning models when annotations are hard to obtain. However, the application of SSL has so far been mainly studied in the context of image classification. In this work, we present a semi-supervised approach for spatial-temporal action localization. We introduce a dual guidance network to select better pseudo-bounding boxes. It combines a frame-level classification with a bounding-box prediction to enforce action class consistency across frames and boxes. Our evaluation across well-known spatial-temporal action localization datasets, namely UCF101-24 , J-HMDB-21 and AVA shows that the proposed module considerably enhances the model's performance in limited labeled data settings. Our framework achieves superior results compared to extended image-based semi-supervised baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_21247 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dual Guidance Semi-Supervised Action Detection Singh, Ankit Gavves, Efstratios Snoek, Cees G. M. Kuehne, Hilde Computer Vision and Pattern Recognition Semi-Supervised Learning (SSL) has shown tremendous potential to improve the predictive performance of deep learning models when annotations are hard to obtain. However, the application of SSL has so far been mainly studied in the context of image classification. In this work, we present a semi-supervised approach for spatial-temporal action localization. We introduce a dual guidance network to select better pseudo-bounding boxes. It combines a frame-level classification with a bounding-box prediction to enforce action class consistency across frames and boxes. Our evaluation across well-known spatial-temporal action localization datasets, namely UCF101-24 , J-HMDB-21 and AVA shows that the proposed module considerably enhances the model's performance in limited labeled data settings. Our framework achieves superior results compared to extended image-based semi-supervised baselines. |
| title | Dual Guidance Semi-Supervised Action Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.21247 |