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

facebooktwittermailshare

Graph Regularization Network with Semantic Affinity for Weakly-supervised Temporal Action Localization

Abstract: 

This paper presents a novel deep architecture for weakly-supervised temporal action localization that predicts temporal boundaries with graph regularization. Our model not only generates segment-level action responses but also propagates segment-level responses to
neighborhood in a form of graph Laplacian regularization. Specifically, our approach consists of two sub-modules; a class activation
module to estimate the action score map over time through the action classifiers, and a graph regularization module to refine the
estimated action score map by solving a quadratic programming problem with the predicted segment-level semantic affinities. Since
these two modules are integrated with fully differentiable layers, the proposed network can be jointly trained in an end-to-end manner. Experimental results on Thumos14 and ActivityNet1.2 demonstrate that the proposed method provides outstanding performances in
weakly-supervised temporal action localization.

up
0 users have voted:

Paper Details

Authors:
Jungin Park, Jiyoung Lee, Sangryul Jeon, Seungryong Kim, Kwanghoon Sohn
Submitted On:
20 September 2019 - 7:59pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Jungin Park
Paper Code:
3614

Document Files

Park_Oral_ICIP_2019.pdf

(9)

Subscribe

[1] Jungin Park, Jiyoung Lee, Sangryul Jeon, Seungryong Kim, Kwanghoon Sohn, "Graph Regularization Network with Semantic Affinity for Weakly-supervised Temporal Action Localization", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4797. Accessed: Oct. 20, 2019.
@article{4797-19,
url = {http://sigport.org/4797},
author = {Jungin Park; Jiyoung Lee; Sangryul Jeon; Seungryong Kim; Kwanghoon Sohn },
publisher = {IEEE SigPort},
title = {Graph Regularization Network with Semantic Affinity for Weakly-supervised Temporal Action Localization},
year = {2019} }
TY - EJOUR
T1 - Graph Regularization Network with Semantic Affinity for Weakly-supervised Temporal Action Localization
AU - Jungin Park; Jiyoung Lee; Sangryul Jeon; Seungryong Kim; Kwanghoon Sohn
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4797
ER -
Jungin Park, Jiyoung Lee, Sangryul Jeon, Seungryong Kim, Kwanghoon Sohn. (2019). Graph Regularization Network with Semantic Affinity for Weakly-supervised Temporal Action Localization. IEEE SigPort. http://sigport.org/4797
Jungin Park, Jiyoung Lee, Sangryul Jeon, Seungryong Kim, Kwanghoon Sohn, 2019. Graph Regularization Network with Semantic Affinity for Weakly-supervised Temporal Action Localization. Available at: http://sigport.org/4797.
Jungin Park, Jiyoung Lee, Sangryul Jeon, Seungryong Kim, Kwanghoon Sohn. (2019). "Graph Regularization Network with Semantic Affinity for Weakly-supervised Temporal Action Localization." Web.
1. Jungin Park, Jiyoung Lee, Sangryul Jeon, Seungryong Kim, Kwanghoon Sohn. Graph Regularization Network with Semantic Affinity for Weakly-supervised Temporal Action Localization [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4797