Welcome to the April edition of the IEEE-TCMC (Technical

Committee on Multimedia Computing) monthly mailing. TCMC membership
is officially determined by signing up with the
IEEE Computer Society either with your membership or later through:
TCMC home:
This month's topics include:
The Twelfth International Workshop on Multimedia Data Mining 
(held in conjunction with KDD’12)
International ACM Workshop on Crowdsourcing for Multimedia
 (held in conjunction with ACM Multimedia 2012)
IEEE Trans. on Multimedia SI on Music Data Mining
Multimedia Data Mining 2012 - Call for Paper
The Twelfth International Workshop on Multimedia Data Mining 
(MDMKDD 2012) 
August 12, 2012
Beijing, China
Workshop website:
Mirrored site:
The MDM/KDD 2012 workshop is in conjunction with the 18th 
ACM SIGKDD Conference on Knowledge Discovery and Data Mining 
Important Dates:
• Submission Due: May 13, 2012 (Sunday)
• Acceptance Notification: June 1, 2012 (Friday)
• Camera-ready Due: June 8, 2012 (Friday)
• Workshop Date: August 12, 2012 (Sunday)
Papers accepted for presentation at the workshop will be 
published in the workshop proceedings and at the ACM digital 
Paper submission and reviewing will be handled electronically. 
Authors should consult the workshop Web site for full details 
regarding paper preparation and submission guidelines:
The paper submission site for the MDM/KDD 2012 workshop is:
   *   *   *
Workshop Topics:
MDM/KDD 2012 will bring together experts in the analysis of 
digital media content, multimedia databases, knowledge 
engineers and domain experts from different applied disciplines 
with potential in multimedia data mining.  A new focus in this 
edition of the workshop is the emerging multimedia 
applications on mobile devices. Other major topics of the 
workshop include but are not limited to the following:
• Emerging technology of data mining for mobile applications.
• Emerging technology of data mining on media rich platforms 
and location enhanced environments (location based services
like Foursquare, mobile maps, navigation systems, GIS applications).
• Multimedia data mining across platforms, including web and mobile 
• Mining large datasets of user generated content with a 
geographical dimension.
• Scalable mobile multimedia computing.
• Scalable mobile visual search.
• Predictive and prescriptive multimedia data modeling.
• Privacy preserving data mining.
• Mining multimedia time series.
• Multi-objective multimedia data mining.
• Anomaly and outlier detection in multimedia databases.
• Merging and integration of mining results from different sources 
(e.g, ensembles, fusion techniques, etc.).
• Scalable data mining techniques for large-scale multimedia
• Human-computer interfaces for multimedia data mining.
• Topic and event discovery in large multimedia repositories.
Formatting Requirements for Submitted Papers
All submissions must be in PDF format and must not exceed 10MB in size.
Papers should be no more than 9 pages total in length. The format is the 
standard double-column ACM Proceedings Style. Additional information 
about formatting and style files are available online at:
Papers that do not meet the formatting requirements will be rejected.
For accepted papers, authors will have the opportunity to revise their 
papers in response to the reviewers before final submission for 
publication in the proceedings.
The paper submission site for MDM/KDD 2012 is:
Software demonstrations are welcome. We encourage submissions 
of ‘greenhouse’ work, which present early stages of cutting-edge 
research and development.
Papers accepted for presentation at the workshop will be published 
in the workshop proceedings and at the ACM digital library.
For more information regarding submissions, please visit the following page: 
   *   *   *
Workshop Co-Chairs:
Aaron Baughman (, IBM SME/Research Department
Jiang (John) Gao (, Nokia USA
Tim Pan (, Google USA
Fang Chu (, Google China
Yizhou Wang (, Peking University
International ACM Workshop on Crowdsourcing for Multimedia
held in conjunction with ACM Multimedia 2012, 
Oct 29 - Nov 2 2012, Nara, Japan
CrowdMM 2012 solicits novel contributions to multimedia research 
that make use of human intelligence, but also take advantage of 
human plurality. This workshop especially encourages contributions 
that propose solutions for the key challenges that face widespread 
adoption of crowdsourcing paradigms in the multimedia research 
community. These include: identification of optimal crowd members 
(e.g., user expertise, worker reliability), providing effective 
explanations (i.e., good task design), controlling noise and quality 
in the results, designing incentive structures that do not breed 
cheating, adversarial environments, gathering necessary background 
information about crowd members without violating privacy, 
controlling descriptions of task. Particular emphasis will be put 
on contributions that successfully combine human and automatic 
methods in order to address multimedia research challenges.
This workshop encourages theoretical, experimental, and/or 
methodological developments advancing state-of-the-art knowledge 
of crowdsourcing techniques for multimedia research.  Topics 
include, but are not limited to the use of crowds, wisdom of crowds, 
or human computation in multimedia, in the following areas of research:
Creation: content synthesis, authoring, editing, and collaboration, 
summarization and storytelling
Evaluation: evaluation of multimedia signal processing algorithms, 
multimedia analysis and retrieval algorithms, or multimedia systems 
and applications
Retrieval: analysis of user multimedia queries, evaluating 
multimedia search algorithms and interactive multimedia retrieval
Annotation: generating semantic annotations for multimedia content, 
collecting large-scale input on user affective reactions
Human factors: designing or evaluating user interfaces for 
multimedia systems, usability study, multi-modal environment, 
human recognition and perceptions
Novel applications (e.g., human as an element in the loop of computation)
Effective Learning from crowd-annotated or crowd-augmented datasets
Quality assurance and cheat detection
Economics and incentive structures
Programming languages, tools and platforms providing enhanced support
Inherent biases, limitations and trade-offs of crowd-centered approaches
CrowdMM 2012 welcomes submissions of full papers, as well as short 
papers reporting work-in-progress. Full papers must be no longer than 
6 pages (inclusive of all figures, references and appendices). Short 
papers are 2 pages, and will be presented as Posters in an interactive setting.
All submissions must be written in English and must be formatted according 
to the ACM Proceedings style. They must contain no information 
identifying the author(s) or their organization(s).  Reviews will be 
double-blind.  Papers will be judged on their relevance, technical 
content and correctness, and the clarity of presentation of the research.
Accepted full and short papers will appear in the ACM Multimedia 
2012 Workshop Proceedings and in the ACM Digital Library.
The authors of selected distinguished papers will be invited to 
submit extended versions of their papers with fast-track reviews to the 
special issue "Crowdsourcing for Multimedia" of IEEE Transactions on 
Multimedia which will be published in late 2013.
Call For Papers --- IEEE Transactions on Multimedia
Special Issue on Music Data Mining
During the last few years there has been a dramatic shift in how 
music is produced, distributed and consumed. A combination of 
advances in digital storage, audio compression as well as significant 
increases in network bandwidth has made digital music distribution a 
reality. Portable music players, computers and smart phones frequently 
contain personal collections of thousands of music tracks. Digital stores 
in which users can purchase music contain millions of tracks that can be 
easily downloaded. 
The research area of music data mining has gradually evolved during 
this time period in order to address the challenge of effectively accessing 
and interacting with these increasing large collections of music and 
associated data such as styles, artists, lyrics and music reviews. The 
algorithms and systems developed frequently employ sophisticated 
and advanced data mining and machine learning techniques in their 
attempt to better capture the frequently elusive relevant music information.
Recent advancements in music listening technologies, in particular, 
the Internet-based music communities, radio stations and music stores, 
have introduced several new interesting aspects to the area, such as 
multimodal analysis of music data, community-based labeling of music, 
user-generated music tags, and listening pattern analysis.   The 
introduction has made the area an exciting research ground and there is 
a strong and emergent need to publicize the area in multimedia literature. 
Topic Areas
The topics covered are (but not limited to):
Keyword generation from song lyrics
Multi-modal classification and clustering of songs
Knowledge mining from symbolic (such as MIDI) data
Knowledge discovery from biography and discography
Modeling of music listening patterns
Playlist generation
Similarity queries
Classification of genre/style/mood
Music recommendation
Music summarization
Text/web mining for music analysis
Database systems/indexing/query models for music analysis
Metadata collection/analysis
Submission Guidelines
Submissions should be submitted through the IEEE Trans. on Multimedia 
journal web server 
( Papers should be 
formatted according to the guidelines for authors 
( During 
the submission, the authors should indicate that this is a submission for 
the special issue on “Music Data Mining” (i.e., select the appropriate 
special issue title under the category “Manuscript Type”). All 
submissions will undergo a blind peer review by three expert 
reviewers to ensure a high standard of quality. 
Referees will consider originality, significance, technical soundness, 
clarity of exposition, and relevance to the special issue topics above.
Important Dates
Paper submission due: November 19, 2012
First-round acceptance notification: March 19, 2013
Revision Due: June 19, 2013
Second-round review completed: August 19, 2013
Final manuscript due: October 19, 2013
Tentative Publication date: August 2014
Guest Editors
Tao Li, School of Computer Science, Florida International University, USA, email: (Lead Guest Editor)
Mitsunori Ogihara, Department of Computer Science, University of Miami, USA.  
George Tzanetakis, Department of Computer Science, University of Victoria, Canada.   
Please address all correspondences regarding this special issue to the Guest Editors.