Multi-stream pose convolutional neural networks for human interaction recognition in images

Tanisik G., ZALLUHOĞLU C., İKİZLER CİNBİŞ N.

SIGNAL PROCESSING-IMAGE COMMUNICATION, vol.95, 2021 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 95
  • Publication Date: 2021
  • Doi Number: 10.1016/j.image.2021.116265
  • Journal Name: SIGNAL PROCESSING-IMAGE COMMUNICATION
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Aerospace Database, Applied Science & Technology Source, Communication Abstracts, Computer & Applied Sciences, INSPEC, Metadex, Civil Engineering Abstracts
  • Hacettepe University Affiliated: Yes

Abstract

Recognizing human interactions in still images is quite a challenging task since compared to videos, there is only a glimpse of interaction in a single image. This work investigates the role of human poses in recognizing human-human interactions in still images. To this end, a multi-stream convolutional neural network architecture is proposed, which fuses different levels of human pose information to recognize human interactions better. In this context, several pose-based representations are explored. Experimental evaluations in an extended benchmark dataset show that the proposed multi-stream pose Convolutional Neural Network is successful in discriminating a wide range of human-human interactions and human poses when used in conjunction with the overall context provides discriminative cues about human-human interactions.