2 papers
cs.LG2022
Embodied vision for learning object representations
Arthur Aubret, Céline Teulière, Jochen Triesch
Recent time-contrastive learning approaches manage to learn invariant object representations without supervision. This is achieved by mapping successive views of an object onto clo…
cs.CV2017
Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis from monocular image
Florian Chabot, Mohamed Chaouch, Jaonary Rabarisoa +2
In this paper, we present a novel approach, called Deep MANTA (Deep Many-Tasks), for many-task vehicle analysis from a given image. A robust convolutional network is introduced for…