Loading...
Loading...

Go to the content (press return)

Hierarchical modeling for first-person vision activity recognition

Author
Tadesse, G.; Cavallaro, A.
Type of activity
Journal article
Journal
Neurocomputing
Date of publication
2017-12-06
Volume
267
Number
6
First page
362
Last page
377
DOI
https://doi.org/10.1016/j.neucom.2017.06.015 Open in new window
URL
http://www.sciencedirect.com/science/article/pii/S0925231217310706?via%3Dihub Open in new window
Abstract
We propose a multi-layer framework to recognize ego-centric activities from a wearable camera. We model the activities of interest as hierarchy based on low-level feature groups. These feature groups encode motion magnitude, direction and variation of intra-frame appearance descriptors. Then we exploit the temporal relationships among activities to extract a high-level feature that accumulates and weights past information. Finally, we define a confidence score to temporally smooth the classifica...
Keywords
Activity recognition, First-person vision, Hierarchical modeling, Motion features, Temporal context encoding

Participants

  • Tadesse, Girmaw Abebe  (author)
  • Cavallaro, Andrea  (author)