VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation

Bibliografski detalji

Izdano u:	arXiv.org (Dec 1, 2024), p. n/a
Glavni autor:	Ren, Weiming
Daljnji autori:	Yang, Huan, Min, Jie, Cong, Wei, Chen, Wenhu
Izdano:	Cornell University Library, arXiv.org
Teme:	Datasets Data augmentation Video data Synthesis Spatiotemporal data Benchmarks High resolution Effectiveness
Online pristup:	Citation/Abstract Full text outside of ProQuest
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!