ViSAGE, a multi-expert framework with adaptive gating and fusion, ranks first on two metrics and outperforms most entries on the others in the NTIRE 2026 video saliency challenge.
Coarse-to-fine semantic align- ment for cross-modal moment localization.IEEE Transac- tions on Image Processing, 30:5933–5943, 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ViSAGE @ NTIRE 2026 Challenge on Video Saliency Prediction
ViSAGE, a multi-expert framework with adaptive gating and fusion, ranks first on two metrics and outperforms most entries on the others in the NTIRE 2026 video saliency challenge.