• Presentation of Recurrent Face Aging @ CVPR’… June 28th, 2016 Presentation of Recurrent Face Aging @ CVPR'16 (Las Vegas)I presented a paper with the title: Recurrent Face Aging at CVPR’16, because Wei and Nicu could not make it to Las Vegas. Someone actually recorded the talk, so while waiting for the official videos, you can get part of the oral presentation here:
  • Seminar: Multimodal behavioral analysis in the wil… May 28th, 2016 Seminar: Multimodal behavioral analysis in the wild -- Télécom ParisTechI will be giving a seminar at Télécom ParisTech on June the 7th the abstract of which reads below. The automated analysis of human behavior in unstructured scenarios has many potential applications in health care, conflict and people management, sociology, marketing and surveillance. It is therefore  unsurprising that many researchers invested efforts into developing computational approaches ...
  • Seminar: Matrix completion, a vision-oriented pers… May 15th, 2016 Seminar: Matrix completion, a vision-oriented perspective.I will be giving a seminar at INRIA, CMU and IRI on computer vision applications of matrix completion. Matrix completion is a generic framework aiming to recover a matrix from a limited number of (possibly noisy) entries. In this content, low-rank regularizers are often imposed so as to find matrix estimators that are robust to noise ...
  • The separation of moving sound sources @ WASPAA &#… May 14th, 2016 The separation of moving sound sources @ WASPAA & TASLP Dionyssos Kounades-Bastian, Laurent Girin, Xavier Alameda-Pineda, Sharon Gannot and Radu Horaud The separation of moving sound sources is a challenging task mainly because it is extremely complex to devise algorithms that robustly discriminate those signal variations due to the intrinsic variation of the sound source from those signal variations due to the time-varying ...
  • Non-Linear Matrix Completion @ CVPR’16 (Las … April 11th, 2016 Non-Linear Matrix Completion @ CVPR'16 (Las Vegas) Xavier Alameda-Pineda, Elisa Ricci, Yan Yan and Nicu Sebe Advanced computer vision and machine learning techniques tried to automatically categorize the emotions elicited by abstract paintings with limited success. Since the annotation of the emotional content is highly resource-consuming, datasets of abstract paintings are either constrained in size or partially annotated. Consequently, it is natural to ...
  • 2.5x @ IEEE CVPR 2016 (Las Vegas) March 10th, 2016 2.5x @ IEEE CVPR 2016 (Las Vegas) We’ve got two papers accepted at IEEE CVPR 2016: Remote heart-rate estimation with self-adaptive matrix completion . Recognize emotions from abstract paintings with non-linear matrix completion Additionally I presented a paper on Recurrent Face Aging from the group. References
  • Weighted-data GMM @ IEEE TPAMI January 25th, 2016 Weighted-data GMM @ IEEE TPAMI Israel-Dejene Gebru, Xavier Alameda-Pineda, Florence Forbes and Radu Horaud We recently got a paper accepted at TPAMI! We had this crazy idea of mixture models that are trained with weighted-data. Imagine you want to train a GMM, and each data point comes with a weight denoting the relevance of the data point for the ...
  • Low-rank inverse-gamma @ IEEE ICASSP 2016 (Shangai… January 20th, 2016 Low-rank inverse-gamma @ IEEE ICASSP 2016 (Shangai) Dionyssis Kounades-Bastian, Laurent Girin, Xavier Alameda-Pineda, Sharon Gannot and Radu Horaud Our low-rank parametrization of inverse-gamma distributions for speech modeling has been accepted at IEEE ICASSP 2016. The main idea is to parametrize the power-spectral density with an NMF-like model in which, even if the parameters are low-rank, the PSD is not. Indeed, ...
  • The SALSA dataset December 12th, 2015 The SALSA dataset Xavier Alameda-Pineda, Jacopo Staiano, Ramanathan Subramanian, Ligia Batrinca, Elisa Ricci, Bruno Lepri, Oswald Lanz and Nicu Sebe Keywords: Multimodal group behavior analysis, Free-standing conversational groups, multimodal social data sets, Tracking, Head and body pose estimation, Personality traits. Synergetic sociAL Scene Analysis (SALSA) contains uninterrupted recordings of an indoor social event involving 18 subjects over 60 minutes. It serves as a rich ...
  • Variational EM and non-convex optimization for mul… December 4th, 2015 Next december 22nd I will be giving a seminar at the Robot-Action-Perception team of LAAS/CNRS, whose abstract reads below. In this talk I describe the mathematical foundations we used in the recent past to address four different multi–sensor scene analysis tasks, namely: audio-visual speaker detection and localization, separation of moving sound sources, geometric sound source localization ...