Please use this identifier to cite or link to this item:
Title: Local fusion networks with chained residual pooling for video action recognition
Authors: He, Feixiang
Liu, Fayao
Yao, Rui
Lin, Guosheng
Keywords: Engineering::Computer science and engineering
Issue Date: 2018
Source: He, F., Liu, F., Yao, R., & Lin, G. (2019). Local fusion networks with chained residual pooling for video action recognition. Image and Vision Computing, 81, 34-41. doi:10.1016/j.imavis.2018.12.002
Journal: Image and Vision Computing 
Abstract: Action recognition is an important yet challenging problem. We here present a novel method, multistage local fusion networks with residual connections, to boost the performance of video action recognition. In realistic videos, an action instance may have a long time span and some frames may suffer from deteriorated object appearance due to motion blur or video defocus. Our method enhances the per-frame representation by capturing information from neighboring frames. We propose a local fusion block which considers neighboring frames to capture appearance and local motion information for generating per-frame representation. Our local fusion is performed in a multistage manner allowing feature fusion from varying neighborhood sizes in the temporal dimension. We employ residual connections in the fusion blocks to enable effective gradient propagation through the whole network allowing effective end-to-end training. We achieve competitive results on two challenging and public available datasets, namely HMDB51 and UCF101, which shows the effectiveness of the proposed method.
ISSN: 0262-8856
DOI: 10.1016/j.imavis.2018.12.002
Rights: © 2019 Elsevier B.V. All rights reserved. This paper was published in Image and Vision Computing and is made available with permission of Elsevier B.V.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Journal Articles

Files in This Item:
File Description SizeFormat 
Local fusion networks with chained residual pooling for video action recognition.pdf2.73 MBAdobe PDFThumbnail

Citations 50

Updated on Mar 24, 2023

Web of ScienceTM
Citations 50

Updated on Mar 23, 2023

Page view(s)

Updated on Mar 29, 2023

Download(s) 50

Updated on Mar 29, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.