New! The workshop program is online! (see "program" page)

Event

Human Gesture and Behavior Understanding event with two workshops/parts:

  • Workshop on Social Signal Processing (SSPW'11);
  • Workshop on Multimedia Access to 3D Human Objects (MA3HO'11)

Background and Motivations

Modeling, processing, recognizing, searching, and retrieving 3D objects is a well-established research in multimedia. At the same time, a great effort is focusing on human-centric multimedia applications for humans and about humans.

3D humans objects are three-dimensional human-objects, that is body, head and face, modeled in 3D for animation, security, human computer interaction, or arms and hands for gesture, legs and local body features for motion and activity analysis; but they also are three-dimensional objects for humans, such as virtual objects to be manipulated or graphic instruments for augmented, virtual reality applications, 3D advanced interactivity.

3D human objects can now be modeled or automatically acquired, processed for animation, recognized in external world, matched with other 2D and 3D visual data, searched and retrieved in domain specific databases or over the web.

This workshop aims at taking a leap forward in emerging research of multimedia access of 3D human objects, aggregating together basic research in 3D graphics, 3D recognition and retrieval, with experiences in many different multimedia fields where humans are involved such as security surveillance and biometry, animation and entertainment, web and video retrieval, sport analytics, natural interaction, augmented and virtual reality.

The MA3HO Workshop calls for brave and innovative contributions in this emerging field of research and aims to create a multidisciplinary community with converging interests in web access and computer vision, computer graphics, content-based retrieval, gesture modeling and virtual worlds.

The workshop will be held in conjunction with ACM Multimedia 2011 (Nov 28 - Dec 1, Scottsdale, Arizona, USA).

Topics of interest

Topics of interest of MA3HO Workshop include but are not limited to:

  • 3D human objects reconstruction from 2D views
  • 3D pose estimation from local 2D information
  • 2D, 2D1/2 to 3D content-based matching
  • Generative / discriminative approaches in 3D object categorization
  • 3D face and people identification and re-identification
  • Local and global 3D shape descriptors
  • Feature extraction for 3D model decomposition and segmentation
  • Feature extraction for 3D motion detection and behavior classification
  • Partial and many-to-many 3D matching
  • Query interfaces and search modalities
  • 3D object/face similarity matching, indexing, and mining
  • Retrieval with large distributed and heterogeneous 3D datasets
  • Semantics-driven 3D object retrieval and classification
  • 3D Object ontology
  • 3D Social networking
  • 3D Retrieval benchmarking
  • 3D Gesture analysis and natural interface
  • Applications in Multimedia industry, Games industry, Biometrics, Surveillance and Security, Medicine and Biology, Augmented reality, Cultural Heritage

We invite researchers interested in these topics to join the MA3HO workshop, submitting their new ideas, research works on algorithms, systems and solutions, or present working demos and applications that allow efficient, well-tailored multimedia access to every type of 3D human objects.

Program organization and duration

ACM MA3HO Workshop is planned to be a full day workshop.

The program will include a keynote talk by a well-known researcher in the field, 2-3 oral sessions with 4 talks each, one poster session with 10-15 poster presentations, and one demo session with 5-6 demos and open discussion.

Journal special issue associated

A special issue on Multimedia Tools and Application has been already planned with the Journal Editor in Chief, that will collect the six best papers.