UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Rate-accuracy trade-off in video classification with deep convolutional neural networks

Abbas, A; Chadha, A; Andreopoulos, Y; Jubran, M; (2018) Rate-accuracy trade-off in video classification with deep convolutional neural networks. In: (Proceedings) 2018 25th IEEE International Conference on Image Processing (ICIP). (pp. pp. 793-797). IEEE: Athens, Greece. Green open access

[img]
Preview
Text
Rate_Accuracy_ICIP2018_Template_v8_accepted_final.pdf - Accepted version

Download (169kB) | Preview

Abstract

Advanced video classification systems decode video frames to derive the necessary texture and motion representations for ingestion and analysis by spatio-temporal deep convolutional neural networks (CNNs). However, when considering visual Internet -of- Things applications, surveillance systems and semantic crawlers of large video repositories, the compressed video content and the CNN-based semantic analysis parts do not tend to be co-located. This necessitates the transport of compressed video over networks and incurs significant overhead in bandwidth and energy consumption, thereby significantly undermining the deployment potential of such systems. In this paper, we investigate the trade-off between the encoding bitrate and the achievable accuracy of CNN-based video classification that ingests AVC/H.264 encoded videos. Instead of entire compressed video bitstreams, we only retain motion vector and selected texture information at significantly reduced bitrates. Based on two CNN architectures and two action recognition datasets, we achieve 38%-59% saving in bitrate with marginal impact in classification accuracy. A simple rate-based selection between the two CNNs shows that even further bitrate savings are possible with graceful degradation in accuracy. This may allow for rate/accuracy-optimized CNN-based video classification over networks.

Type: Proceedings paper
Title: Rate-accuracy trade-off in video classification with deep convolutional neural networks
Event: 2018 25th IEEE International Conference on Image Processing (ICIP)
ISBN-13: 9781479970612
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/ICIP.2018.8451666
Publisher version: https://doi.org/10.1109/ICIP.2018.8451666
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Streaming media , Bit rate , Two dimensional displays , Three-dimensional displays , Standards , Convolutional neural networks , Encoding, Video classification , convolutional neural networks , video streaming
UCL classification: UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng
URI: https://discovery.ucl.ac.uk/id/eprint/10074737
Downloads since deposit
29Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item