The Multimedia Event Detection (MED) evaluation track is part of the TRECVID Evaluation. The goal of MED is to assemble core detection technologies into a system that can search multimedia recordings for user-defined events based on pre-computed metadata. The metadata stores developed by the systems are expected to be sufficiently general to permit re-use for subsequent user defined events
For MED 2011, an event:
A user searching for events in multimedia material may be interested in a wide variety of potential events. Since it is an intractable task to build special purpose detectors for each event a priori, technology is needed that can take as input a human-generated definition of the event that a system will use to search a collection of multimedia clips. The MED evaluation series will define events via an event kit which consists of:
The MED task is: given an Event Kit, detect the occurrence of an event within a multimedia clip.
The MED task is a "multimedia" task in that systems will be expected to detect evidence of the event using either or both the audio and video streams (but not human-created textual metadata) of the clips.
Participants must build a system for at least one of the test events in order to participate in the evaluation and TRECVID Conference.
NIST maintains an email discussion list to disseminate information. Send requests to join the list to med_poc at nist dot gov.
MED system performance will be evaluated as specified in the evaluation plan. The evaluation plan contains the rules, protocols, metric definitions, scoring instructions, and submission instructions.
The current version is MED11-EvalpPlan-V03-20110801a
The differences between V03 and V02 (highlighted in the comparison version between V03 and v02) include wording changes Section 1.0 and 2.2.2.
Section 3.3 of the evaluation plan defines the rules for using the testing resources. Both the the structure of the data resources and rules for using the testing resources are complicated. In order to ensure participants properly utilize the data, Section 5.0 "MED Data Use Guidance" of the README from the MED-11 Documentation and Metadata Distribution (from LDC distribution LDC2011E42) contains a description of the MED '11 corpora components and their allowed use.
Additionally, NIST is hosting Q&A telecons to answer questions. Answers to the asked questions can be found in the MED 11 Data Use FAQ. Participants should contact NIST if these resources fail to answer their questions.
A collection of Internet multimedia (i.e., clips containing both audio and video streams) will be provided to registered MED participants. The data, which was collected by the Linguistic Data Consortium, consists of publicly available, user-generated content posted to the various Internet video hosting sites.
Participants will receive the MED '10 data set and new data resources for the MED '11 evaluation. The new resources include the following:
The evaluation plan will specify usage rules of the DEV-T and DEV-O collections in full detail.
Fifteen new events will be defined for the 2011 evaluation. The events will be separated into training events and testing events according to the following table of event names.
|Training Event Names||Testing Event Names|
|Attempting a board trick |
Feeding an animal
Landing a fish
Working on a woodworking project
|Birthday party |
Changing a vehicle tire
Flash mob gathering
Getting a vehicle unstuck
Grooming an animal
Making a sandwich
Repairing an appliance
Working on a sewing project
Event names need to be interpreted in the full context of the event definitions that will be made available as part of the event kits released on March 1st.
Last year, three events were used for the 2010 pilot evaluation. Those events were: "Making a cake", "Batting a run", and "Assembling a shelter". The Linguistic Data Consortium created a web page containing the details of the 2010 Event Kit definitions. The linked examples defined in an event kit are meant to inform discussions only and are not incorporated in the MED-10 distributed data resources.
The video data collection will be released in two parts.
In order to obtain the MED-10 and MED-11 corpora, TRECVID-registered sites must complete an evaluation license with LDC. Each site who requires access to the data, either as part of a team or as a standalone researcher, must complete a license.
To complete the evaluation license follow these steps:
The designated data contact person for each site will receive instructions from LDC about the specific procedures for obtaining the data packages when they are released.
The dry run period for MED will run until July 29, 2011. Dry run submissions will be accepted at any time during the period. The dry run is an opportunity for developers to make sure they are able to generate valid system output that can be scored with the NIST scoring tools. The actual performance of the system is not of interest during the dry run so developers may feel free to use any method to generate their system output, e.g., a random system, training on the dry run data, etc.
The procedure for participating in the dry run is as follows:
Evaluation scripts to support the MED evaluation are within the NIST Framework for Detection Evaluations (F4DE) Toolkit Version 2.3 or later found on the NIST MIG tools page.
The package contains an MED evaluation primer (found in F4DE-2.3/DEVA/doc/TRECVid-MED11-ScoringPrimer.html) of the distribution.
Consult the TRECVID Master schedule.