000176215 001__ 176215
000176215 005__ 20190812205609.0
000176215 020__ $$a978-1-4673-1228-8
000176215 02470 $$2ISI$$a000309166202052
000176215 037__ $$aCONF
000176215 245__ $$aA Constrained Latent Variable Model
000176215 269__ $$a2012
000176215 260__ $$bIeee$$c2012$$aNew York
000176215 300__ $$a8
000176215 336__ $$aConference Papers
000176215 490__ $$aIEEE Conference on Computer Vision and Pattern Recognition
000176215 520__ $$aLatent variable models provide valuable compact representations for learning and inference in many computer vision tasks. However, most existing models cannot directly encode prior knowledge about the specific problem at hand. In this paper, we introduce a constrained latent variable model whose generated output inherently accounts for such knowledge. To this end, we propose an approach that explicitly imposes equality and inequality constraints on the model's output during learning, thus avoiding the computational burden of having to account for these constraints at inference. Our learning mechanism can exploit non-linear kernels, while only involving sequential closed-form updates of the model parameters. We demonstrate the effectiveness of our constrained latent variable model on the problem of non-rigid 3D reconstruction from monocular images, and show that it yields qualitative and quantitative improvements over several baselines.
000176215 700__ $$0242713$$g179178$$aVarol, Aydin
000176215 700__ $$0(EPFLAUTH)119864$$g119864$$aSalzmann, Mathieu
000176215 700__ $$g112366$$aFua, Pascal$$0240252
000176215 700__ $$aUrtasun, Raquel$$g137775$$0241534
000176215 7112_ $$dJune 16-21, 2012$$cProvidence, Rhode Island, USA$$aIEEE Conference on Computer Vision and Pattern Recognition
000176215 773__ $$tA Constrained Latent Variable Model
000176215 8564_ $$zn/a$$yn/a$$uhttps://infoscience.epfl.ch/record/176215/files/0774.pdf$$s5217659
000176215 909C0 $$xU10659$$pCVLAB$$0252087
000176215 909CO $$ooai:infoscience.tind.io:176215$$qGLOBAL_SET$$pconf$$pIC
000176215 917Z8 $$x179178
000176215 917Z8 $$x179178
000176215 937__ $$aEPFL-CONF-176215
000176215 973__ $$rNON-REVIEWED$$sACCEPTED$$aEPFL
000176215 980__ $$aCONF