most citedZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection

1 citations · 1 across the 1 of their papers we have counts for

collaborators

1 paper

cs.CV2023★ 1 cited

ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection

Thinh Phan, Khoa Vo, Duy Le +3

Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos. While standard TAD follows fully supervised learning with…