Long-Term Feature Banks for Detailed Video Understanding

Code

• github.com/facebookresearch/video-long-term-feature-banks
  OfficialIn papercaffe2★ 0
• github.com/open-mmlab/mmaction2
  pytorch★ 4,959
• github.com/wei-tim/YOWO
  pytorch★ 0
• github.com/BoChenUIUC/YOWO
  pytorch★ 0

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.

Tasks

Benchmark Results

Reproductions