Video Browser Showdown

New at VBS 2017: This year the VBS will collaborate with TRECVID (in particular with the Ad-Hoc Video Search task) and use the same IACC.3 video data set (600h; please register for TRECVID or contact George Awad at NIST to get access to the data). 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.



The Video Browser Showdown (VBS) is an annual live video search competition, where international researchers evaluate and demonstrate the efficiency of their exploratory video retrieval tools on a shared data set in front of the audience. It is organized as a special session at the International Conference on MultiMedia Modeling (MMM) since 2012. In this special session the participating teams start with a quick presentation of their video search systems and then perform several video retrieval tasks with a moderately large video collection (new in 2017: we will collaborate with the TRECVID Ad-Hoc search task and use the same data set with about 600 hours of video content).

The aim of the Video Browser Showdown is to evaluate video browsing tools for their efficiency at “Known Item Search” (KIS) tasks with a well-defined data set in direct comparison to other tools. For each KIS task the searchers need to interactively find a short video clip (20 secs) in the video collection within a specific time limit. While the video data is distributed before the event, the tasks are presented on-site via a projector (either as a video clip itself, or as a textual description). The videos below show some impressions from previous events.

The next Video Browser Showdown (VBS2017) will be held at MMM 2017 on January 4-6, 2017 in Reykjavik, Iceland.

See VBS2017 Call-for-Papers and the submission guidlines here.

The Video Browser Showdown is supported by the TOSCA-MP project by contributing to the organisation and providing data sets.TOSCA-MP Logo