Special Sessions

ICMR 2012 will include two Special Sessions:

[Accepted papers to the two special sessions are listed in the main conference program]

1. Social Events in Web Multimedia
Organizers:
Vasileios Mezaris (Centre for Research and Technology Hellas, Greece)
Raphael Troncy (Eurecom, France)
Lexing Xie (Australian National University, Australia)
Benoit Huet (Eurecom, France)

2. Socio-Video Semantics
Organizers:
Cees Snoek (University of Amsterdam, The Netherlands)
Yu-Gang Jiang (Fudan University, China)
 

1. Social Events in Web Multimedia

Session Abstract:
The modeling, detection, and processing of events is an area that has started to receive considerable attention by the multimedia community. This Special Session aims to attract and present the latest developments and results on the discovery of social events from web multimedia content, and on techniques for the detection and retrieval of media items that are related to such social events. By social events, we refer to events that are planned by people, are attended by people, and are represented by multimedia and in general social media content that is captured by people. A lot of the multimedia content out there on the Web has been captured during such an event (e.g. a concert, a football game, an uprising) or is otherwise related to and conveys information about a social event. However, this content is often scattered, i.e., is disassociated from the related events. This, together with the observation that humans often think in terms of events, generate the need for automatically detecting such events from multimedia content. Furthermore, they generate the need for automatically establishing the event-media associations that will allow multimedia browsing and search, as well as social media understanding, in a way that is more complete and more natural to the users.

2. Socio-Video Semantics

Session Abstract:
All of a sudden video became social. In just five years, individual and mostly inactive consumers transformed into active and connected prosumers, revolutionaries even, who create, share, and comment on massive amounts of video artifacts all over the world wide web 2.0. Pronounced manifestations of social video on the Internet include industry initiatives like YouTube, Vimeo, WikiPedia, and Flickr, who manage to attract millions of users, daily. It has been predicted that soon 91 percent of Internet data will be video, where smartphones will only accelerate the unstoppable momentum. In order to make sense of the massive amounts of video content, online social platforms rely on what other people say is in the image, which is known to be ambiguous, overly personalized, and limited. Hence, the lack of semantics currently associated with online video is seriously hampering retrieval, repurposing, and usage. In contrast to social video platforms, academic video sensemaking approaches rely on an analysis of the multimedia content. Such content-driven image search is important, if only to verify what people have said is factually in the video, or for (professional) archives which cannot be shared for crowdsourcing. Despite good progress, automated multimedia analysis of video content is still seriously hampered by the semantic gap, or the lack of correspondence between the low-level audiovisual features that machines extract from video and the high-level conceptual interpretations a human gives to multimedia data. For sensemaking, exploiting the social multimedia context of video has largely been ignored in the multimedia community. This special session provides a unique opportunity for high-quality papers connecting the social context of online video to video sensemaking.