1 code implementation • NeurIPS 2018 • Guilhem Chéron, Jean-Baptiste Alayrac, Ivan Laptev, Cordelia Schmid
Our model is based on discriminative clustering and integrates different types of supervision as constraints on the optimization.
no code implementations • 28 Jun 2018 • Guilhem Chéron, Anton Osokin, Ivan Laptev, Cordelia Schmid
In order to localize actions in time, we propose a recurrent localization network (RecLNet) designed to model the temporal structure of actions on the level of person tracks.
no code implementations • ICCV 2015 • Guilhem Chéron, Ivan Laptev, Cordelia Schmid
This work targets human action recognition in video.