Log In Sign Up

Memory-augmented Dense Predictive Coding for Video Representation Learning

by   Tengda Han, et al.

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.


page 2

page 21

page 23


Self-supervised Co-training for Video Representation Learning

The objective of this paper is visual-only self-supervised video represe...

PredNet and Predictive Coding: A Critical Review

PredNet, a deep predictive coding network developed by Lotter et al., co...

Learning Invariant World State Representations with Predictive Coding

Self-supervised learning methods overcome the key bottleneck for buildin...

Learning without Prejudice: Avoiding Bias in Webly-Supervised Action Recognition

Webly-supervised learning has recently emerged as an alternative paradig...

Evolving Losses for Unsupervised Video Representation Learning

We present a new method to learn video representations from large-scale ...

Motion-Augmented Self-Training for Video Recognition at Smaller Scale

The goal of this paper is to self-train a 3D convolutional neural networ...

An Emerging Coding Paradigm VCM: A Scalable Coding Approach Beyond Feature and Signal

In this paper, we study a new problem arising from the emerging MPEG sta...

Code Repositories


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

view repo