Best Paper Award @ ACM Multimedia 2015 (Brisbane)

Xavier Alameda-Pineda, Yan Yan, Elisa Ricci, Oswald Lanz and Nicu Sebe

I happily announce that we received the Best Paper Award for

Analyzing free-standing conversational groups: a multimodal approach

at ACM International Conference in Multimedia 2015 (Brisbane, Australia) [1].

Abstract During natural social gatherings, humans tend to organize themselves in the so-called free-standing conversational groups. In this context, robust head and body pose estimates can facilitate the higher-level description of the ongoing interplay. Importantly, visual information typically obtained with a distributed camera network might not suffice to achieve the robustness sought. In this line of thought, recent advances in wearable sensing technology open the door to multimodal and richer information flows. In this paper we propose to cast the head and body pose estimation problem into a matrix completion task. We introduce a framework able to fuse multimodal data emanating from a combination of distributed and wearable sensors, taking into account the temporal consistency, the head/body coupling and the noise inherent to the scenario. We report results on the novel and challenging SALSA dataset [2], containing visual, auditory and infrared recordings of 18 people interacting in a regular indoor environment. We demonstrate the soundness of the proposed method and the usability for higher-level tasks such as the detection of F-formations and the discovery of social attention attractors.

Link to the supplementary material (derivation of the CADMM equations) and demo video:


  1. X. Alameda-Pineda, Y. Yan, E. Ricci, O. Lanz, and N. Sebe, “Analyzing Free-standing Conversational Groups: A Multimodal Approach,” in ACM International Conference on Multimedia, Brisbane, Australia, 2015, pp. 4-15. [ bib pdf ] Award Best Paper Award
      author = {Xavier Alameda-Pineda and Yan Yan and Elisa Ricci and Oswald Lanz and Nicu Sebe},
      title = {Analyzing Free-standing Conversational Groups: A Multimodal Approach}, 
      booktitle = {ACM International Conference on Multimedia},
      year = {2015},
      award = {Best Paper Award},
      pages = {4--15},
      address = {Brisbane, Australia},
  2. X. Alameda-Pineda, J. Staiano, R. Subramanian, L. M. Batrinca, E. Ricci, B. Lepri, O. Lanz, and N. Sebe, “SALSA: A Novel Dataset for Multimodal Group Behavior Analysis,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, iss. 8, pp. 1707-1720, 2016. [ bib pdf data arxiv ]
      author    = {Xavier Alameda-Pineda and
                   Jacopo Staiano and
                   Ramanathan Subramanian and
                   Ligia Maria Batrinca and
                   Elisa Ricci and
                   Bruno Lepri and
                   Oswald Lanz and
                   Nicu Sebe},
      title     = {{SALSA:} {A} Novel Dataset for Multimodal Group Behavior Analysis},
      journal   = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
      year      = {2016},
      data    = {},
      arxiv = {},

Category: Research

No responses yet.

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>