Activities such as those involved in food preparation involve interactions between hands, tools and multiple manipulated objects that affect them in visually complex ways making recognition of their constituent actions challenging. We describe a system that classifies action classes in such a setting based on discriminative spatio-temporal superpixel groups. The entire system operates sequentially enabling online action recognition. We obtain state-of-the-art results whilst employing a compact, interpretable representation.
|Number of pages
|Published - 6 Sept 2018
|2018 IEEE International Conference on Image Processing - Athens, Greece
Duration: 7 Oct 2018 → 10 Oct 2018
Conference number: 25
|2018 IEEE International Conference on Image Processing
|7/10/18 → 10/10/18