Memory-augmented Dense Predictive Coding for Video Representation Learning

08/03/2020 ∙ by Tengda Han, et al. ∙ 6

The objective of this paper is self-supervised learning from video, in particular for representations for action recognition. We make the following contributions: (i) We propose a new architecture and learning framework Memory-augmented Dense Predictive Coding (MemDPC) for the task. It is trained with a predictive attention mechanism over the set of compressed memories, such that any future states can always be constructed by a convex combination of the condense representations, allowing to make multiple hypotheses efficiently. (ii) We investigate visual-only self-supervised video representation learning from RGB frames, or from unsupervised optical flow, or both. (iii) We thoroughly evaluate the quality of learnt representation on four different downstream tasks: action recognition, video retrieval, learning with scarce annotations, and unintentional action classification. In all cases, we demonstrate state-of-the-art or comparable performance over other approaches with orders of magnitude fewer training data.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 2

page 21

page 23

Code Repositories

MemDPC

[ECCV'20 Spotlight] Memory-augmented Dense Predictive Coding for Video Representation Learning. Tengda Han, Weidi Xie, Andrew Zisserman.


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.