COGNITIVELY-INSPIRED ARCHITECTURES FOR HUMAN MOTION UNDERSTANDING
Abstract
In the last decades, modelling and understanding human motion from videos has gained an increasing importance in several applications, including Human-Machine Interaction, gaming, assisted living and robotics. Although the significant advances of the last years, where as in other domains deep learning techniques has gained momentum [1], the tasks remain among the most challenging, for an intrinsic complexity due to the extreme variability of the dynamic information and its appearance [37], and still a lot of work needs to be done to approaching human performance.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Aug 11, 2021
- Source ID
- FA86552017035
Entities
People
- Nicoletta Noceti
Organizations
- Air Force Office of Scientific Research
- United States Air Force
- University of Genoa