papers AI Learner
The Github is limit! Click to go to the new site.

Long-Term Feature Banks for Detailed Video Understanding

2019-04-17
Chao-Yuan Wu, Christoph Feichtenhofer, Haoqi Fan, Kaiming He, Philipp Krähenbühl, Ross Girshick

Abstract

To understand the world, we humans constantly need to relate the present to the past, and put events in context. In this paper, we enable existing video models to do the same. We propose a long-term feature bank—supportive information extracted over the entire span of a video—to augment state-of-the-art video models that otherwise would only view short clips of 2-5 seconds. Our experiments demonstrate that augmenting 3D convolutional networks with a long-term feature bank yields state-of-the-art results on three challenging video datasets: AVA, EPIC-Kitchens, and Charades.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1812.05038

PDF

http://arxiv.org/pdf/1812.05038


Similar Posts

Comments