Controllable Attention for Structured Layered Video Decomposition

Jean-Baptiste Alayrac, Joao Carreira, Relja Arandjelovic, Andrew Zisserman; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 5734-5743

Abstract


The objective of this paper is to be able to separate a video into its natural layers, and to control which of the separated layers to attend to. For example, to be able to separate reflections, transparency or object motion. We make the following three contributions: (i) we introduce a new structured neural network architecture that explicitly incorporates layers (as spatial masks) into its design. This improves separation performance over previous general purpose networks for this task; (ii) we demonstrate that we can augment the architecture to leverage external cues such as audio for controllability and to help disambiguation; and (iii) we experimentally demonstrate the effectiveness of our approach and training procedure with controlled experiments while also showing that the proposed model can be successfully applied to real-word applications such as reflection removal and action recognition in cluttered scenes.

Related Material


[pdf]
[bibtex]
@InProceedings{Alayrac_2019_ICCV,
author = {Alayrac, Jean-Baptiste and Carreira, Joao and Arandjelovic, Relja and Zisserman, Andrew},
title = {Controllable Attention for Structured Layered Video Decomposition},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}