VBS2017 will be part of the International Conference on MultiMedia Modeling 2017 (MMM2017) in Reykjavik, Iceland, and organized as a side event to the Welcome Reception on January 4, 2017. It will be a moderated session where participants solve Known-Item Search (KIS) tasks that are issued as live presentation of scenes of interest, either as a visual 20 seconds clip (randomly selected), or as a textual description of such a random clip. The goal is to find correct segments as fast as possible and submit the segment description (video id and frame number) to the VBS server, which evaluates if the finding was correct. For some tasks there will be only one single correct result, for others there will be a few correct results that should all be found.
VBS2017 will collaborate with TRECVID 2016 (i.e. with the Ad-Hoc Video Search (AVS) Task) and use the same data set, consisting of 4593 Internet Archive videos (144GB, 600 total hours) using videos with durations between 6.5min and 9.5min. Please register for TRECVID or contact George Awad at NIST to get access to the IACC.3 data set.
AVS and KIS Tasks
We plan to test at least 20 search tasks:
- 10 Ad-Hoc Video Search (AVS) tasks, which are a random subset of the 30 AVS tasks of TRECVID 2016. Each AVS task has several/many target shots that should be found.
- 10 Known-Item Search (KIS) tasks, which are selected completely random on site. Each KIS task has only one single 20-seconds long target segment
VBS Server and Testing
The VBS uses an own server application to evaluate found segments for correctness. Therefore, all participants will be connected to the server via a dedicated WiFi network and need to submit found segments to the server via a simple HTTP-like protocol. The server is connected to a beamer and presents the current score of all teams in a live manner.
The server application as well as example tasks from the previous years will be provided on this website for download soon.
Anyone with an exploratory video search tool that allows for retrieval, interactive browsing, exploration, or navigation in a video collection may participate.
Also new in 2017: There will be no restrictions in terms of allowed features, except for presentation screen recording during the competition, which is disallowed. That means in addition to interactive content search you can use any automatic content search as well.
To apply for participation please submit an extended demo paper (4-6 pages in Springer LNCS format) via the MMM 2017 Submission System (please select the “Video Browser Showdown” track) until September 16, 2016. The submission should include a detailed description of the video search tool and how it supports interactive search in video. Submissions will be peer-reviewed to ensure maximum quality. Accepted papers will be published in the proceedings of the MMM conference and should also be presented as poster during the VBS session.
|Demo paper submission deadline||September 25, 2016 (extended)|
|Notification of acceptance||October 10, 2016|
|Camera-ready paper and author registration||November 4, 2016|