• IEEE WASPAA’17 paper on Joint Diarization an… June 30th, 2017IEEE WASPAA'17 paper on Joint Diarization and Separation
    Dionyssos Kounades-Bastian, Laurent Girin, Xavier Alameda-Pineda, Radu Horaud and Sharon Gannot . Abstract: Natural conversations are spontaneous exchanges involving two or more people speaking in an intermittent manner. Therefore one expects such conversation to have intervals where some ...
  • Paper @ IROS 2017: Tracking a Varying Number of Pe… June 17th, 2017Paper @ IROS 2017: Tracking a Varying Number of People with a Visually-Controlled Robotic Head
    Yutong Ban, Xavier Alameda-Pineda, Fabien Badeig, Sileye Ba and Radu and Horaud . Abstract: Multi-person tracking with a robotic platform is one of the cornerstones of human-robot interaction. Challenges arise from occlusions, appearance changes and ...
  • Workshop at ACM MM’2017: Multimodal Understa… April 4th, 2017Workshop at ACM MM'2017: Multimodal Understanding of Social, Affective and Subjective Attributes
    Xavier Alameda-Pineda, Miriam Redi, Mohammad Soleymani, Nicu Sebe, Shih-Fu Chang and Samuel D. Gosling Traditionally, the recognition of tangible properties of data, such as objects and scenes, have overwhelmingly covered the spectra of applications in multimedia, computer vision and signal processing. In the recent past and partly fostered by social media, the understanding of social, affective and subjective attributes of ...
  • Area Chair @ ICCV’17 January 23rd, 2017Area Chair @ ICCV'17
    I am appointed to serve as Area Chair for the International Conference on Computer Vision 2017. ICCV will take place in Venice (Italy) in October 22nd-29th, 2017. It is my pleasure to serve the community, it has always been, and I am extremely enthusiastic and motivated to do my best helping select the highest quality ...
  • The Integrated-Cascaded Gaussian Mixture Regressor… January 21st, 2017The Integrated-Cascaded Gaussian Mixture Regressor @ TASLP and LVA-ICA'2017
    Laurent Girin, Thomas Hueber and Xavier Alameda-Pineda . Abstract: This article addresses the adaptation of an acoustic-articulatory inversion model of a reference speaker to the voice of another source speaker, using a limited amount of audio-only data. ...
  • Beyond semantics: multi-modal understand of subjec… December 22nd, 2016Beyond semantics: multi-modal understand of subjective properties, a special session @ ICMR'17
    We are pleased to announce a special session at ACM ICMR’17 with the title: Beyond semantics: multi-modal understanding of subjective properties This Special Session aims to gather high-quality contributions on the latest systems and applications of multimedia analysis for subjective property (SP) understanding, detection and retrieval. In a nutshell, the focus of the special session is on ...
  • ICASSP’17 paper on sound source joint separa… December 19th, 2016ICASSP'17 paper on sound source joint separation and diarization
    Dionyssos Kounades-Bastian, Laurent Girin, Xavier Alameda-Pineda, Sharon Gannot and Radu Horaud . Abstract: We present a statistical model for joint source separation and diarization of multichannel convolutive speech mixtures. We build ...
  • Best Scientific Paper Award at IAPR ICPR’16 December 15th, 2016Best Scientific Paper Award at IAPR ICPR'16
    Dan Xu, Jingkuan Song, Xavier Alameda-Pineda, Elisa Ricci and Nicu Sebe I happily announce that we received the Best Scientific Paper Award for Multi-paced dictionary learning for cross-domain retrieval and recognition at IAPR International Conference on Pattern Recognition 2016 (Cancun, Mexico) . Abstract Several applications benefit from learning coupled representations able to describe data from ...
  • BMVC’16 paper: Projective Unsupervised Flexi… September 2nd, 2016BMVC'16 paper: Projective Unsupervised Flexible Embedding with Optimal Graph
    Wei Wang, Yan Yan, Feiping Nie, Xavier Alameda-Pineda, Shuicheng Yan and Nicu Sebe . Abstract: Graph based dimensionality reduction techniques have been successfully applied to clustering and classification tasks. The fundamental basis of these algorithms is the constructed graph ...
  • Multi-person tracking with variational Bayes model… August 23rd, 2016Multi-person tracking with variational Bayes models
    Silèye Ba, Xavier Alameda-Pineda, Alessio Xompero and Radu Horaud Abstract: Object tracking is an ubiquitous problem that appears in many applications such as remote sensing, audio processing, computer vision, ...