Prize Challenges

Activities in Extended Video (ActEV) Prize Challenge

Can you develop an algorithm that watches hours of video of a parking lot and automatically detects if someone walks onto the scene? Can your algorithm detect that the person entered a car? Can it detect if they were carrying something heavy? The Activities in Extended Video Prize Challenge invites participants from around the world to create innovative solutions to automatically detect and localize a set of 18 different types of activities in extended video scenes.

Who We Are: The Intelligence Advanced Research Projects Activity, within the Office of the Director of National Intelligence, focuses on high-risk, high-payoff research programs to tackle difficult challenges of the agencies and disciplines in the intelligence community. IARPA is partnering with the National Institute of Standards and Technology to run this public prize challenge.

What We’re Doing: ActEV-PC invites participants from across the globe and across disciplines – with or without experience in video analysis – to create algorithms that detect and localize activities in video. Challenge participants will develop activity detection and temporal localization algorithms for 18 types of activities to be found in extended videos. These videos contain lengthy spans without any activities and intervals with potentially multiple concurrent activities. Representative sample video, with selected activity annotations, will be provided.

ActEV-PC will contain two stages:

  • an open leaderboard evaluation qualifying stage where all eligible solutions will be evaluated
  • an independent evaluation stage, where the top 8 solutions from the leaderboard will be tested on sequestered data by NIST

Why We’re Doing This: The volume of video data collected from security cameras has grown dramatically in recent years. However, there has not been a commensurate increase in the capabilities of automated analytics for real-time alerting, triaging or forensic analysis of video. Operators of camera networks are typically overwhelmed with the volume of video they must monitor, and cannot afford to view or analyze even a small fraction of their video footage. Automated methods that identify and localize activities in extended video are necessary to alleviate the current, manual process of monitoring by human operators. Automated methods would also provide the capability to alert and triage video that can scale as the number of cameras continues to grow. IARPA is conducting this challenge to invite the broader research community of industry and academia, with or without experience in computer vision, to participate in a convenient, efficient and non-contractual way. IARPA’s use of a crowdsourcing approach to stimulate breakthroughs in science and technology also supports the White House’s efforts to promote emerging technology and empower innovation, as well as government transparency and efficiency.

Who Should Participate: Researchers in the fields of deep learning, computer vision, machine learning and data science are encouraged to participate. Individuals or teams from private industry, academia, or without affiliation, both domestic and international, are eligible to participate and win prizes. The ActEV-PC team believes success in this challenge can prove to be a strong addition to any computer vision or data science practitioner’s portfolio. Certain individuals and groups with existing agreements with IARPA may not be eligible for cash prizes but may be able to compete for standing on the leaderboard and other non-monetary incentives. IARPA’s Deep Intermodal Video Analytics program performers, government partners, and their affiliates are welcome to participate in the challenge, but will need to forego the monetary prizes. See the full rules and challenge eligibility details at

Why Should You Participate: The developers of the activity detection and localization methods with the greatest demonstrated accuracy will be eligible to win cash prizes from a total prize purse of $50,000 and present their work at a the Computer Vision and Pattern Recongition conference, ActivityNet workshop. Throughout the challenge, an online leaderboard will display participants’ rankings, giving them the opportunity to have their accomplishments recognized by stakeholders from industry, government and academic communities.

When does registration begin? December 4, 2018
When does the leaderboard begin? December 4, 2018
Where to learn more about the challenge, including rules, criteria and eligibility requirements:
Where do participants register?
How do I stay connected to get information about the challenge? Join NIST’s mailing list at!forum/trecvid.actev
When does the challenge end?

The open leaderboard closes February 28, 2019.
The post-deadline leaderboard closes April 30, 2019
Winners will be announced in May 2018 and present at the CVPR conference, ActivityNet workshop in June 2019.

Related Program(s):