WSLMM 2013 - AAAI 2013 Spring Symposium on Weakly Supervised Learning from Multimedia

What can computers learn about the real world from large quantities of audio-visual data, with minimal human supervision? While weakly supervised learning has been an active research topic in the natural language community, learning from large multimedia collections (and video in particular) is a field that is still in its infancy. Early efforts in this direction include learning models of objects and actions from internet video, humans in images and localizing sounds in audio.
Scaling weakly supervised learning to very large collections (e.g., internet video);
Features and representations;
Weakly supervised learning algorithms and connections to related topics, such as multiple instance learning and semi-supervised learning;
Learning in the presence of significant label noise;
Value of "seeding" weakly supervised learning with small amounts of strongly supervised data;
Datasets to enable direct comparison of approaches, including challenges in obtaining reliable groundtruth annotations;
Transfer learning (e.g., learning from video and testing in the image domain);
Weakly supervised approaches in robotics;
Combining audio/visual content with text;
Challenge problems in audio, image, video and multimodal domains.
Symposium Format
The symposium will consist of presentations from several invited speakers, presentations selected from position papers, an open poster session, and panel discussions about key issues (such as publicly available datasets). The sessions will be organized so as to provide ample opportunities for unstructured discussion.
Submission Requirements
Participants should submit, by email to Rahul Sukthankar , a concise summary of their research interests (limited to 2 pages) that includes pointers to relevant published work. The organizers will select a subset of submissions to supplement the invited talks and will encourage all participants to present a poster about their research.
The symposium will not generate any proceedings; however, participants will be encouraged to submit articles for a journal special issue on this topic.
Primary Contact
Rahul Sukthankar, Google Research and Carnegie Mellon. Email: rahuls-AT-cs.cmu.edu
Organizing Committee
Omid Madani, Google Research
James M. Rehg, Georgia Tech
Rahul Sukthankar, Google Research and Carnegie Mellon