Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Hennerbichler, Markus"'
In video action recognition, transformers consistently reach state-of-the-art accuracy. However, many models are too heavyweight for the average researcher with limited hardware resources. In this work, we explore the limitations of video transformer
Externí odkaz:
http://arxiv.org/abs/2111.09641