Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Koot, Raivo"'
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
Autor:
Koot, Raivo, Lu, Haiping
Efficient video action recognition remains a challenging problem. One large model after another takes the place of the state-of-the-art on the Kinetics dataset, but real-world efficiency evaluations are often lacking. In this work, we fill this gap a
Externí odkaz:
http://arxiv.org/abs/2107.00451
This report describes the technical details of our submission to the EPIC-Kitchens 2021 Unsupervised Domain Adaptation Challenge for Action Recognition. The EPIC-Kitchens dataset is more difficult than other video domain adaptation datasets due to mu
Externí odkaz:
http://arxiv.org/abs/2106.12023
Autor:
Lu, Haiping, Liu, Xianyuan, Turner, Robert, Bai, Peizhen, Koot, Raivo E, Zhou, Shuo, Chasmai, Mustafa, Schobs, Lawrence
Machine learning is a general-purpose technology holding promises for many interdisciplinary research problems. However, significant barriers exist in crossing disciplinary boundaries when most machine learning tools are developed in different areas
Externí odkaz:
http://arxiv.org/abs/2106.09756