Submission Abstract => December 15, 2013 (unchanged)
Submission Full Paper => Extended to 5th of January 2014
Recent years have seen extensive interest in video search focusing on retrieval of visual shot level units, and linking of multimedia documents clusters faces or other properties assuming someone wants to group those documents. While there has been much progress in developing methods for improved search effectiveness, this research generally focuses on technical aspects of retrieval.
This special session will focus on video search from a user-centric perspective and targets a real-world use-case scenario. We step forward from the search of textual information or of the relevant video content in response to a user search query, and focus on the search through video content that is supported by the navigation in the video collection using inter and cross-item hyperlinks. The search and linking might be based on both spoken and visual content targeting the diversity in the results to satisfy potential variety of user interests.
User studies suggest users interests are multimodal in nature. Successful search and hyperlinking to relevant content thus requires creation and exploitation of multi-modal queries combining visual, audio and textual features. This special session aims to bring together researchers working on video search and hyperlinking to find solutions for tasks motivated by real-world use-case scenarios .
We particularly encourage papers that present methods covering the complete search and hyperlinking use-case across all content modalities.
Ideal submissions will cover some or all of the following aspects in a close connection to the search and hyperlinking use-case:
- Automatic multi-modal query generation
- Models to identify video segments that are usable for linking as source anchors and link targets
- Methods for creation of effective links
- Evaluation of user-centric search and hyperlinking
- User studies related to search and hyperlinking scenarios
Note about anonymity
All papers should be prepared and submitted according to the ICMR’14′ guidelines, which uses a double-blind review process. Authors should not know the names of the reviewers of their papers, and reviewers should not know the name(s) of the authors. Please prepare your paper in a way that preserves anonymity of the authors, e.g.
- Do not put your name(s) under the title.
- Avoid using phrases such as “our previous work” when referring to earlier publications by the authors.
- Remove information that may identify the authors in the acknowledgements (e.g., co-workers and grant IDs).
- Check supplemental material (e.g., titles in the video clips, or supplementary documents) for information that may identify the authors identity.
- Avoid providing links to websites that identify the authors.
Abstract and keywords
The abstract and the keywords form the primary source for assigning
papers to reviewers. So make sure that they form a concise and
complete summary of your paper with sufficient information to let
someone who doesn’t read the full paper know what it is about.
Maximum paper length
Each regular paper should not be longer than 8 pages.
- Maria Eskevich (Dublin City University, Ireland) firstname.lastname@example.org
- Dr. Robin Aly (University of Twente, The Netherlands) email@example.com
- Dr. Roeland Ordelman ( University of Twente, The Netherlands) firstname.lastname@example.org
- Dr. Gareth J.F. Jones (Dublin City University, Ireland) email@example.com
Please submit your work using the EasyChair conference website.