Recent years have witnessed an explosive growth of multimedia content driven by the wide availability of massive storage devices, high-resolution video cameras and fast networks. Stimulated by recent progress in scalable machine learning, feature indexing and multi-modal analysis techniques, researchers are becoming increasingly interested in exploring challenges and new opportunities for developing much larger scale approaches for multimedia retrieval and mining. Many of these computationally-intensive ideas are now becoming practical because of the broader availability of high-speed clusters and the advent of cloud computing.

This workshop aims to bring together researchers and industrial practitioners interested in large-scale multimedia retrieval and mining. The workshop will provide a venue for the participants to explore a variety of aspects and applications on how advanced multimedia analysis techniques can be leveraged to address the challenges in large-scale data collections. Pivotal to many tasks is the availability of a sufficiently large dataset and its corresponding ground truth. Currently available datasets for multimedia research are either too small such as the Corel or Pascal datasets, too specific like the TRECVID dataset, or without ground truth, such as the several recent efforts by MIT and MSRA that gathered millions of web images for testing. While it is relatively easy to crawl and store a huge amount of data, the creation of ground-truth necessary to systematically train, test, evaluate and compare the performance of various algorithms and systems is a major problem. For this reason, more and more research groups are individually putting efforts into the creation of such corpus in order to carry out research on Web-scale dataset. The workshop will provide a forum to consolidate key factors related to research on very large scale multimedia dataset such as the construction of datasets, creation of ground truth, sharing and extension of such resources in terms of ground truth, features, algorithms and tools, etc.

All papers should address important issues in large-scale multimedia analysis, and demonstrate approaches that can scale to sufficiently large multimedia collections (e.g., hundreds of thousands of images, or hundreds of hours of video or audio content).
The list of possible topics includes:

* Indexing and retrieval for large multimedia collections (including images, video, audio and other multi-modal data)
* Large-scale copy detection and near-duplicate detection
* Video event and temporal analysis over large-scale multimedia sources
* Web-scale social-network and content-network analysis
* Machine tagging, semantic annotation, object recognition and ontology management on massive multimedia collections
* Collaborative image and video annotation for distributed users
* Interfaces for exploring, browsing and visualizing large multimedia collections
* Scalable and distributed machine learning and data mining methods for multimedia
* Scalable and distributed systems for multimedia content analysis
* Construction and evaluation of large-scale multimedia collections


Submission Information

Submit a 4 page extended abstract in English, in PDF, by email to alex AT cs DOT cmu DOT edu by April 1, 2010. The extended abstracts (PDF) should be anonymous. Include in your email the name(s) of the author(s), institutional affiliation, complete mailing address, international phone and fax numbers. The papers presented at the workshop will be published in the workshop notes, for distribution to the participants and linked to the workshop webpage (http://LSMM2010.org) after the workshop.
Important Dates

Submission Deadline
April 12, 2010 [NEW EXTENDED DEADLINE]

Acceptance Notification
May 1, 2010

Revised Abstract Deadline
June 1, 2010
Registration Information

On-line registration of workshops will be available via the ICPR 2010 web page.
It is not necessary to register for the full conference to attend the workshop.


Organizers

Alexander Hauptmann
Carnegie Mellon University, USA
E-mail: alex AT cs DOT cmu DOT edu

Rong Yan
Facebook Inc, USA
E-mail address: yanrong AT gmail DOT com

Qi Tian
University of Texas at San Antonio，USA
Email: qitian AT cs DOT utsa DOT edu

Rahul Sukthankar
Intel Labs and Carnegie Mellon University, USA
Email: rahuls AT cs DOT cmu DOT edu

Additional information is available at http://www.lsmm2010.org/
A PDF version of this CFP is available at:
http://www.lsmm2010.org/LSMM-ICPR2010.pdf