[Apologies if you receive this more than once]

Call for Participation for CrowdMM 2012 --
International ACM Workshop on Crowdsourcing for Multimedia

CrowdMM 2012
International ACM Workshop on Crowdsourcing for Multimedia
held in conjunction with ACM Multimedia 2012, Oct 29, Nara, Japan

Crowdsourcing for multimedia involves exploiting both human intelligence and the combination of a large number of individual human contributions (i.e., the 'wisdom of the crowd') to develop techniques, systems and data sets that advance the state of the art. The ACM Multimedia 2012 Workshop on Crowdsourcing for Multimedia (CrowdMM 2012) provides a forum presenting crowdsourcing techniques for multimedia, as well as innovative ideas exemplifying how multimedia research can benefit from crowdsourcing. 

We are excited about the variety of papers that are included in the workshop program, which reflect the global momentum in research in this field. The selected works cover several key topics in the crowdsourcing research spectrum, such as how to control the quality of crowd input, how to present complex tasks for a crowd to solve, and how to apply crowdsourcing in a variety of novel applications.  We also like to extend a special word of thanks to Prof. Masataka Goto of the National Institute of Advanced Industrial Science and Technology (AIST), Japan for his keynote speech entitled "PodCastle and Songle: Crowdsourcing-Based Web Services for Spoken Content Retrieval and Active Music Listening".  His keynote discusses how crowdsourcing can be utilized to advance speech-recognition and music-understanding technologies and systems.

We welcome you to CrowdMM 2012 and hope that you enjoy the presentation, interaction and discussions.

Tenatative Program

9:30 - 9:40 Opening Remarks

9:40 - 10:30 Keynote speech 
  PodCastle and Songle: Crowdsourcing-Based Web Services for Spoken Content Retrieval and Active Music Listening
  Speaker: Prof. Masataka Goto, AIST, Japan
10:30 - 11:00 Coffee Break  

11:00 - 11:50 Session 1: Annotation

  Tagging Tagged Images: On the Impact of Existing Annotations on Image Tagging
  Authors: Cesar Moltedo, Hernan Astudillo, Marcelo Mendoza
  Ground Truth Generation in Medical Imaging: A Crowdsourcing based Iterative Approach
  Authors: Antonio Foncubierta Rodriguez, Henning Muller
11:50 - 12:30 Session 2: Short Papers

  Crowdsouring in Emotion Studies across Time and Culture
  Authors: Marwa Mahmoud, Tadas Baltrusaitis, Peter Robinson
  A Closer Look at Photographers' Intentions: a Test Data Set and Automatic Classification
  Authors: Mathias Lux, Mario Taschwer, Oge Marques
  Crowdsourcing User Interactions within Web Video through Pulse Modeling
  Authors: Konstantinos Chorianopoulos, Markos Avlonitis, David Ayman Shamma
  Crowdsourced User Interface Testing for Multimedia Applications
  Authors: Raynor Vliegendhart, Eelco Dolstra, Johan Pouwelse

12:30 - 13:00 Poster Session

13:00 - 14:00 Lunch

14:00 - 15:15 Session 3: Evaluation

  Pushing the Limits of Mechanical Turk: Qualifying the Crowd for Video Geolocation
  Authors: Luke Gottlieb, Jaeyoung Choi, Pascal Kelm, Thomas Sikora, Gerald Friedland
  Crowdsourcing Micro-Level Multimedia Annotations: The Challenges of Evaluation and Interface
  Authors: Sunghyun Park, Gelareh Mohammadi, Ron Artstein, Louis-Philippe Morency
  Crowdsourcing Approach for Evaluation of Privacy Filters in Video Surveillance
  Authors: Pavel Korshunov, Shuting Cai, Touradj Ebrahimi
15:15 - 15:40 Coffee Break
15:40 - 16:30 Session 4: Application

  Tag Suggestion on YouTube by Personalizing Content-based Auto-Annotation
  Authors: Dominik Henter, Damian Borth, Adrian Ulges
  Enhancing Online 3D Products through Crowdsourcing
  Authors: Thi Phuong Nghiem, Axel Carlier, Geraldine Morin, Vincent Charvillat
16:30 - 17:25 Panel Discussion

17:25 - 17:30 Concluding Remarks  


Wei-Ta Chu, National Chung Cheng University, Taiwan
Martha Larson, Delft University of Technology, Netherlands
Wei Tsang Ooi, National University of Singapore, Singapore
Kuan-Ta Chen, Academia Sinica, Taiwan

Program Committee

Omar Alonso, Microsoft Research, US
Paul Bennett, Microsoft Research, US
Stefano Ceri, Politecnico di Milano, Italy
Vincent Charvillat, University of Toulouse, France
Otto Chons, Microtask, Finland
Petros Daras, Informatics and Telematics Institute, Greece 
Arjen de Vries, CWI, Netherlands
Piero Fraternali, Politechnico di Milano, Italy
Daniel Gatica-Perez, Idiap Research Institute and EPFL, Switzerland
Fausto Giunchiglia, University of Trento, Italy
Jiyin He, CWI, Netherlands
Winston Hsu, National Taiwan University, Taiwan
Yu-Gang Jiang, Fudan University, China
Gareth Jones, Dublin City University, Ireland
Irwin King, The Chinese University of Hong Kong, Hong Kong
Yiannis Kompatsiaris, Informatics and Telematics Institute, Greece 
Matt Lease, University of Texas at Austin, US
Jiebo Luo, University of Rochester, US
Jasminko Novak, EIPCM, Germany
Stefanie Nowak, Hella Aglaia Mobile Vision GmbH, Berlin
Mohammad Soleymani, University of Geneva, Switzerland
Yu-An Sun, Xerox Research Center Webster, US
Wanmin Wu, University of California at San Diego, US
Emine Yilmaz, Microsoft Research, UK
Shengdong Zhao, National University of Singapore, Singapore


CrowdMM Website: http://crowdmm.org

For any questions or more information, please contact workshop co-chairs: Wei-Ta Chu ([log in to unmask]), Martha Larson ([log in to unmask]), Wei Tsang Ooi ([log in to unmask]), or Kuan-Ta Chen ([log in to unmask]).

To unsubscribe from the MM-INTEREST list, click the following link: