Spectral latent variable models for perceptual inference

Atul Kanaujia, Cristian Sminchisescu, Dimitris Metaxas

Research output: Contribution to conferencePaperpeer-review

16 Scopus citations


We propose non-linear generative models referred to as Sparse Spectral Latent Variable Models (SLVM), that combine the advantages of spectral embeddings with the ones of parametric latent variable models: (1) provide stable latent spaces that preserve global or local geometric properties of the modeled data; (2) offer low-dimensional generative models with probabilistic, bi-directional mappings between latent and ambient spaces, (3) are probabilistically consistent (i.e., reflect the data distribution, both jointly and marginally) and efficient to learn and use. We show that SLVMs compare favorably with competing methods based on PCA, GPLVM or GTM for the reconstruction of typical human motions like walking, running, pantomime or dancing in a benchmark dataset. Empirically, we observe that SLVMs are effective for the automatic 3d reconstruction of low-dimensional human motion in movies.

Original languageEnglish (US)
StatePublished - 2007
Event2007 IEEE 11th International Conference on Computer Vision, ICCV - Rio de Janeiro, Brazil
Duration: Oct 14 2007Oct 21 2007


Other2007 IEEE 11th International Conference on Computer Vision, ICCV
CityRio de Janeiro

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Spectral latent variable models for perceptual inference'. Together they form a unique fingerprint.

Cite this