Open Access System for Information Sharing

Login Library

 

Article
Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

First Person Action Recognition via Two-stream ConvNet with Long-term Fusion Pooling

Title
First Person Action Recognition via Two-stream ConvNet with Long-term Fusion Pooling
Authors
Kwon, HeeseungKim, YeonhoLee, Jin S.Cho, Minsu
Date Issued
Sep-2018
Publisher
ELSEVIER SCIENCE BV
Abstract
First person action recognition is an active research area with increasingly popular wearable devices. Action classification for first person video (FPV) is more challenging than conventional action classification due to strong egocentric motions, frequent changes of viewpoints, and diverse global motion patterns. To tackle these challenges, we introduce a two-stream convolutional neural network that improves action recognition via long-term fusion pooling operators. The proposed method effectively captures the temporal structure of actions by leveraging a series of frame-wise features of both appearance and motion in actions. Our experiments validate the effect of the feature pooling operators, and show that the proposed method achieves state-of-the-art performance on standard action datasets. (c) 2018 Elsevier B.V. All rights reserved.
URI
http://oasis.postech.ac.kr/handle/2014.oak/95671
ISSN
0167-8655
Article Type
Article
Citation
PATTERN RECOGNITION LETTERS, vol. 112, page. 161 - 167, 2018-09
Files in This Item:
There are no files associated with this item.

qr_code

  • mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher

 CHO, MINSU
Dept of Computer Science & Enginrg
Read more

Views & Downloads

Browse