End-to-End Learning of Latent Deformable Part-Based Representations for Object Detection

Taylor Mordan (1, 2) , Nicolas Thome (3) , Gilles Henaff (2) , Matthieu Cord (1)

1 MLIA - Machine Learning and Information Access
2 Thales LAS France
3 CEDRIC - Centre d'études et de recherche en informatique et communications

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Apprentissage [cs.LG]; Intelligence artificielle [cs.AI]

Taylor Mordan, Nicolas Thome, Gilles Henaff, Matthieu Cord. End-to-End Learning of Latent Deformable Part-Based Representations for Object Detection. International Journal of Computer Vision, 2018, ⟨10.1007/s11263-018-1109-z⟩. ⟨hal-01842031⟩