Special Session Call for Papers

Special Session
on
Machine Learning with Multimedia Data

International Conference on Machine Learning and Applications (ICMLA 2011)
December 18-21, 2011 Honolulu, Hawaii, USA


AIMS AND SCOPE

The web, as well as TV and radio archives and other sources, give access to a growing amount of data in a large variety of formats and media modalities, often containing useful information.
However, much of this information is not easily accessible and usable, be it for users or for automatic systems that could make use of it.

While information extraction from written text has seen great advances and is used by search engines, news aggregators, opinion monitoring systems, mail filters, and many more, access to information in other modalities (audio, images, video, ...) is still a very difficult problem. Machine learning is used with varying success for diverse tasks dealing with multimedia data, but many problems remain, ranging from finding good machine readable representations of the data, extracting higher level (semantic) features to the development of machine learning algorithms capable of dealing with high-dimension spatio-temporal data. An important aspect is also the integration of information obtained from various modalities, and the possibility for cross-modal access to information (e.g. textual querying of video recordings).

One important aim of this session is to bring together researchers working on different types of data, be it music, video, speech, images, and more. These tasks have much in common, and we hope to promote communication between researchers from these different fields.
Topics

This session would solicit original research papers including but not limited to the following:

Low level feature extraction, selection and transformation
High level feature extraction from multimedia/cross-media
Semantic content analysis, classification, and automatic annotation
Machine learning and statistical models for spoken document retrieval
Speech recognition and speaker recognition
User-access pattern monitoring, modeling, and prediction
Learning and relevance feedback in multimedia retrieval
Semi-supervised learning in multimedia data analysis
Transfer or multitask learning in multimedia/cross-media data analysis
Semantic organization/visualization of multimedia and cross-media data

IMPORTANT DATES

Paper Submission Deadline: July 30, 2011 (extended)
Notification of acceptance: September 7, 2011
Camera-ready papers & Pre-registration: October 1, 2011
The ICMLA Conference: December 18-21, 2011

This special session will be held as part of the ICMLA’11 conference. Authors should submit papers through the main conference submission website. Papers must correspond to the requirements detailed in the instructions to authors. All conference submissions will be handled electronically. Detailed instructions for submitting the papers are provided on the conference home page at:
http://www.icmla-conference.org/icmla11/

Accepted papers must be presented by one of the authors to be published in the conference proceeding. If you have any questions, do not hesitate to direct your questions to Jens Grivolla (jens.grivolla@barcelonamedia.org) or any of the other session organizers.

Special Session Organizers:

Jens Grivolla (Barcelona Media Innovation Centre, Speech and Language Processing Group, Spain)
Cyril Laurier (Universitat Pompeu Fabra, Music Technology Group, Spain)