[visionlist] CVPR’21 ActivityNet workshop ActEV SDL Unknown Facility (UF) challenge: Deadline Extended

[Godil, Afzal A. (Fed)]

We have extended the CVPR’21 ActivityNet workshop ActEV SDL UF Challenge submission deadline to May 15th, 2021. We now have more data and annotations available for the public MEVA dataset. Please see below for more details.

Call for Participation: CVPR’21 ActivityNet Workshop Task: ActEV SDL Unknown Facility (UF) Challenge

The extended deadline for system submission is May 15th, 2021


The ActEV SDL Unknown Facility (UF) challenge is a guest task under the CVPR’21 ActivityNet workshop (http://activity-net.org/challenges/2021/challenge.html<https://gcc02.safelinks.protection.outlook.com/?url=http%3A%2F%2Factivity-net.org%2Fchallenges%2F2021%2Fchallenge.html&data=04%7C01%7Cafzal.godil%40nist.gov%7C038662603a5d430e330408d90ab5c19d%7C2ab5d82fd8fa4797a93e054655c61dec%7C1%7C0%7C637552598030923093%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=%2FBcetxsRf%2FSbZc0xtR26hw6LIOYUy6QmPAYaVGnpJXM%3D&reserved=0>).  The challenge participants are invited to submit their runnable activity detection system for Known Activities using an ActEV Command Line Interface (CLI) submission on the Unknown Facility EO video dataset.  Based on the UF CLI submission extended deadline of May 15, 2021, we will invite the top two teams to give oral presentations at the CVPR’21 ActivityNet workshop.



ActEV SDL UF website: https://actev.nist.gov/sdl

CVPR’21 ActivityNet workshop: http://activity-net.org/challenges/2021/challenge.html<https://gcc02.safelinks.protection.outlook.com/?url=http%3A%2F%2Factivity-net.org%2Fchallenges%2F2021%2Fchallenge.html&data=04%7C01%7Cafzal.godil%40nist.gov%7C038662603a5d430e330408d90ab5c19d%7C2ab5d82fd8fa4797a93e054655c61dec%7C1%7C0%7C637552598030933046%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=6YSyS4ROPjt5s0Jm3utynPJcCyOwmatkueKFsbWEVUA%3D&reserved=0>
If you have any question about the SDL evaluation, please email actev-nist at nist.gov


Who

NIST invites all organizations, particularly universities and corporations, to submit their technologies to ActEV SDL UF.  The evaluation is open worldwide. Participation is free. NIST does not provide funds to participants.


Schedule

  *   February 10, 2021: CVPR’21 ActivityNet ActEV SDL UF (with Known Activities) leaderboard opens
  *   May 15, 2021: New deadline for UF CLI submissions to be included in CVPR’21 ActivityNet workshop.

  *   June 05, 2021: Top two teams on the ActEV'21 SDL UF (with Known Activities) leaderboard will be invited to give oral presentations at the CVPR’21 ActivityNet workshop based on the CLI submission deadline (May 15, 2021).

  *   June 13, 2021: Deadline to submit your video presentations (for top two teams)

  *   June 19, 2021: CVPR’21 ActivityNet workshop

Dataset

Training data is from the Multiview Extended Video with Activities (MEVA) dataset [mevadata.org]. The public MEVA dataset includes hundreds of hours of data from the same cameras at the same facility, which can be used for training. If you register for ActEV you can download the MEVA dataset for free; info on how to download the data is on the data tab https://actev.nist.gov/sdl#tab_data]. We now have more data and annotations available<https://gcc02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgitlab.kitware.com%2Fmeva%2Fmeva-data-repo%2Ftree%2Fmaster%2Fannotation%2FDIVA-phase-2%2FMEVA%2Fkitware-meva-training&data=04%7C01%7Cafzal.godil%40nist.gov%7C038662603a5d430e330408d90ab5c19d%7C2ab5d82fd8fa4797a93e054655c61dec%7C1%7C0%7C637552598030933046%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=yTfcbqg0OId%2B89S1l7IUTIdAbYNT6pc70rATddZzkXE%3D&reserved=0> for the public MEVA<https://gcc02.safelinks.protection.outlook.com/?url=http%3A%2F%2Fmevadata.org%2F&data=04%7C01%7Cafzal.godil%40nist.gov%7C038662603a5d430e330408d90ab5c19d%7C2ab5d82fd8fa4797a93e054655c61dec%7C1%7C0%7C637552598030943003%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=Xe%2Ba4DH0Cjo%2FzjhBQiMs5lENzCXs%2FIBrHf9Fb5b0OaI%3D&reserved=0> KF1 dataset.

Unknown Facility Sequestered Test dataset is a large collection of videos exclusively in the EO spectrum.

Please contact us if you need any more information or have any question.

Best wishes,

-Afzal for actev-nist at nist.gov



-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20210429/5ccf41b5/attachment-0001.html>