Реклама

TF-CADE: Foreground-Concentrated Text-Video Alignment for Zero-Shot Temporal Action Detection

#TF-CADE #Foreground-Concentrated #Text-Video #Alignment #Zero-Shot

arXiv:2608.17422v1 Announce Type: new Abstract: Zero-Shot Temporal Action Detection (ZSTAD) aims to lo- calize and recognize action instances from unseen action categories in untrimmed videos. Although existing meth- ods have shown effectiveness by advancing architectural text-video alignment, they…