Impact of three-dimensional video scalability on multi-view activity recognition using deep learning

Jun Ho Choi, Manri Cheon, Min Su Choi, Jong Seok Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Human activity recognition is one of the important research topics in computer vision and video understanding. It is often assumed that high quality video sequences are available for recognition. However, relaxing such a requirement and implementing robust recognition using videos having reduced data rates can achieve efficiency in storing and transmitting video data. Three-dimensional video scalability, which refers to the possibility of reducing spatial, temporal, and quality resolutions of videos, is an effective way for flexible representation and management of video data. In this paper, we investigate the impact of the video scalability on multiview activity recognition.We employ both a spatiotemporal feature extraction-based method and a deep learning-based method using convolutional and recurrent neural networks. The recognition performance of the two methods is examined, along with in-depth analysis regarding how their performance vary with respect to various scalability combinations. In particular, we demonstrate that the deep learning-based method can achieve significantly improved robustness in comparison to the feature-based method. Furthermore, we investigate optimal scalability combinations with respect to bitrate in order to provide useful guidelines for an optimal operation policy in resource-constrained activity recognition systems.

Original languageEnglish
Title of host publicationThematic Workshops 2017 - Proceedings of the Thematic Workshops of ACM Multimedia 2017, co-located with MM 2017
PublisherAssociation for Computing Machinery, Inc
Pages135-143
Number of pages9
ISBN (Electronic)9781450354165
DOIs
Publication statusPublished - 2017 Oct 23
Event1st International ACM Thematic Workshops, Thematic Workshops 2017 - Mountain View, United States
Duration: 2017 Oct 232017 Oct 27

Publication series

NameThematic Workshops 2017 - Proceedings of the Thematic Workshops of ACM Multimedia 2017, co-located with MM 2017

Other

Other1st International ACM Thematic Workshops, Thematic Workshops 2017
CountryUnited States
CityMountain View
Period17/10/2317/10/27

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computational Theory and Mathematics
  • Theoretical Computer Science

Fingerprint Dive into the research topics of 'Impact of three-dimensional video scalability on multi-view activity recognition using deep learning'. Together they form a unique fingerprint.

  • Cite this

    Choi, J. H., Cheon, M., Choi, M. S., & Lee, J. S. (2017). Impact of three-dimensional video scalability on multi-view activity recognition using deep learning. In Thematic Workshops 2017 - Proceedings of the Thematic Workshops of ACM Multimedia 2017, co-located with MM 2017 (pp. 135-143). (Thematic Workshops 2017 - Proceedings of the Thematic Workshops of ACM Multimedia 2017, co-located with MM 2017). Association for Computing Machinery, Inc. https://doi.org/10.1145/3126686.3126769