Long-Term Feature Banks for Detailed Video Understanding

Chao-Yuan Wu, Christoph Feichtenhofer, Haoqi Fan, Kaiming He, Philipp Krahenbuhl, Ross Girshick
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
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
more » ... results on three challenging video datasets: AVA, EPIC-Kitchens, and Charades. Code is available online 1 . Input clip (4 seconds) Target frame
doi:10.1109/cvpr.2019.00037 dblp:conf/cvpr/WuF0HKG19 fatcat:5vp6t547dfb6hcagxvtu5cbd2a