An ensemble of an efficient ViNet decoder and a SlowFast action-localization encoder achieves top results on most of nine video saliency datasets at high speed.
A gated fusion network for dynamic saliency prediction,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Minimalistic Video Saliency Prediction via Efficient Decoder & Spatio Temporal Action Cues
An ensemble of an efficient ViNet decoder and a SlowFast action-localization encoder achieves top results on most of nine video saliency datasets at high speed.