Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Domain Agnostic Video Prediction from Motion Selective Kernels

Abstract: 

Existing conditional video prediction approaches train a network from large databases and generalise to previously unseen data. We take the opposite stance, and introduce a model that learns from the first frames of a given video and extends its content and motion, to, \eg double its length. To this end, we propose a dual network that can use in a flexible way both dynamic and static convolutional motion kernels, to predict future frames. We demonstrate experimentally the robustness of our approach on challenging videos in-the-wild and show that it is competitive related baselines.

up
0 users have voted:

Paper Details

Authors:
Submitted On:
19 September 2019 - 11:54pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Da Li
Paper Code:
3335
Document Year:
2019
Cite

Document Files

prinet-icip2019-presentation-onlineversion.pdf

(6)

Keywords

Subscribe

[1] , "Domain Agnostic Video Prediction from Motion Selective Kernels", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4756. Accessed: Oct. 18, 2019.
@article{4756-19,
url = {http://sigport.org/4756},
author = { },
publisher = {IEEE SigPort},
title = {Domain Agnostic Video Prediction from Motion Selective Kernels},
year = {2019} }
TY - EJOUR
T1 - Domain Agnostic Video Prediction from Motion Selective Kernels
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4756
ER -
. (2019). Domain Agnostic Video Prediction from Motion Selective Kernels. IEEE SigPort. http://sigport.org/4756
, 2019. Domain Agnostic Video Prediction from Motion Selective Kernels. Available at: http://sigport.org/4756.
. (2019). "Domain Agnostic Video Prediction from Motion Selective Kernels." Web.
1. . Domain Agnostic Video Prediction from Motion Selective Kernels [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4756