Robust Video Saliency Prediction (VSP) leveraging a multi-expert ensemble framework. Temporal Modulation + Multi-Scale Fusion experts for explicit spatial priors and adaptive data-driven perception.
Feb 12, 2026: We proposed OmniCustom, a novel framework to deal with sync audio-video customization. Feb 14, 2026: The inference code and the model checkpoint are ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results