SADA: Semantic adversarial unsupervised domain adaptation for Temporal Action Localization

arXiv:2312.13377v2 Announce Type: replace
Abstract: Temporal Action Localization (TAL) is a complex task that poses relevant challenges, particularly when attempting to generalize on new -- unseen -- domains in real-world applications. These scenarios, despite realistic, are often neglected in the literature, exposing these solutions to important performance degradation. In this work, we tackle this issue by introducing, for the first time, an approach for Unsupervised Domain Adaptation (UDA) in sparse TAL, which we refer to as Semantic Adversarial unsupervised Domain …

abstract adversarial applications arxiv challenges cs.cv domain domain adaptation domains literature localization performance semantic solutions temporal type unsupervised world