ViSAGE @ NTIRE 2026 Challenge on Video Saliency Prediction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915929464504320 |
|---|---|
| author | Wang, Kun Hu, Yupeng Li, Zhiran Liu, Hao Xiang, Qianlong Nie, Liqiang |
| author_facet | Wang, Kun Hu, Yupeng Li, Zhiran Liu, Hao Xiang, Qianlong Nie, Liqiang |
| contents | In this report, we present our champion solution for the NTIRE 2026 Challenge on Video Saliency Prediction held in conjunction with CVPR 2026. To exploit complementary inductive biases for video saliency, we propose Video Saliency with Adaptive Gated Experts (ViSAGE), a multi-expert ensemble framework. Each specialized decoder performs adaptive gating and modulation to refine spatio-temporal features. The complementary predictions from different experts are then fused at inference. ViSAGE thereby aggregates diverse inductive biases to capture complex spatio-temporal saliency cues in videos. On the Private Test set, ViSAGE ranked first on two out of four evaluation metrics, and outperformed most competing solutions on the other two metrics, demonstrating its effectiveness and generalization ability. Our code has been released at https://github.com/iLearn-Lab/CVPRW26-ViSAGE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_08613 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ViSAGE @ NTIRE 2026 Challenge on Video Saliency Prediction Wang, Kun Hu, Yupeng Li, Zhiran Liu, Hao Xiang, Qianlong Nie, Liqiang Computer Vision and Pattern Recognition In this report, we present our champion solution for the NTIRE 2026 Challenge on Video Saliency Prediction held in conjunction with CVPR 2026. To exploit complementary inductive biases for video saliency, we propose Video Saliency with Adaptive Gated Experts (ViSAGE), a multi-expert ensemble framework. Each specialized decoder performs adaptive gating and modulation to refine spatio-temporal features. The complementary predictions from different experts are then fused at inference. ViSAGE thereby aggregates diverse inductive biases to capture complex spatio-temporal saliency cues in videos. On the Private Test set, ViSAGE ranked first on two out of four evaluation metrics, and outperformed most competing solutions on the other two metrics, demonstrating its effectiveness and generalization ability. Our code has been released at https://github.com/iLearn-Lab/CVPRW26-ViSAGE. |
| title | ViSAGE @ NTIRE 2026 Challenge on Video Saliency Prediction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.08613 |