Not logged in.

Contribution Details

Type Conference or Workshop Paper
Scope Discipline-based scholarship
Published in Proceedings Yes
Title Gesture of Interest: Gesture Search for Multi-Person, Multi-Perspective TV Footage
Organization Unit
  • Mahnaz Parian
  • Claire Walzer
  • Luca Rossetto
  • Silvan Heller
  • Stephane Dupont
  • Heiko Schuldt
Presentation Type paper
Item Subtype Original Work
Refereed Yes
Status Published in final form
  • English
ISBN 978-1-6654-4220-6
Page Range 1 - 6
Event Title 2021 International Conference on Content-Based Multimedia Indexing (CBMI)
Event Type conference
Event Location Lille, France
Event Start Date July 28 - 2021
Event End Date July 30 - 2021
Publisher IEEE
Abstract Text In real-world datasets, specifically in TV recordings, videos are often multi-person and multi-angle, which poses significant challenges for gesture recognition and retrieval. In addition to being of interest to linguists, gesture retrieval is a novel and challenging application for multimedia retrieval. In this paper, we propose a novel method for spatio-temporal gesture retrieval based on visual and pose information which can retrieve similar gestures in multi-person scenes through continuous shots. The attention-aware features, extracted from human pose key-points, together with a sophisticated pre-processing module, alleviate the susceptibility of gesture retrieval to background noise and occlusion. We have evaluated our method on a subset of the NewsScape Dataset. Our experimental results demonstrate the effectiveness of the proposed method in retrieving similar results in occluded scenes as measured by the quality of the top 5 results.
Related URLs
Digital Object Identifier 10.1109/CBMI50038.2021.9461887
Other Identification Number merlin-id:21246
PDF File Download from ZORA
Export BibTeX