no code implementations • Pattern Recognition Letters 2023 • Yasser Boutaleb, Catherine Soladie, Nam-Duong Duong, Amine Kacete, Jérôme Royan, Renaud Seguier
We propose in this paper a new composite DML loss function that, in addition to the intra-class compactness, explicitly implies regulations to enforce the best inter-class separation by mutually equidistantly distributing the centers of the classes.
Ranked #1 on Image Clustering on CUB-200-2011
no code implementations • 16 Sep 2022 • Mathieu Gonzalez, Eric Marchand, Amine Kacete, Jérôme Royan
However they are often unable to estimate the canonical pose of the objects and exhibit a low object tracking accuracy.
no code implementations • 24 Feb 2022 • Mathieu Gonzalez, Eric Marchand, Amine Kacete, Jérôme Royan
Classical visual simultaneous localization and mapping (SLAM) algorithms usually assume the environment to be rigid.
no code implementations • 15 Sep 2021 • Mathieu Gonzalez, Eric Marchand, Amine Kacete, Jérôme Royan
We propose a new SLAM system that uses the semantic segmentation of objects and structures in the scene.
no code implementations • 10 Feb 2021 • Yasser Boutaleb, Catherine Soladie, Nam-Duong Duong, Amine Kacete, Jérôme Royan, Renaud Seguier
Recognizing first-person hand activity is a challenging task, especially when not enough data are available.
Ranked #1 on Skeleton Based Action Recognition on First-Person Hand Action Benchmark (1:1 Accuracy metric)