VideoLINCS_ProposersDayAnnouncement_C_4 JAN 23.pdf
PDF 75 KB Posted
- Attached to
- Proposer's Day- VideoLINCS Proposers Day
- Solicitation number
- Not on record
About this file
This notice announces a proposers' day for the Video Linking and Intelligence from Non-Collaborative Sensors (Video LINCS) program. The proposers' day meeting will be held on February 7, 2024 in Linthicum, MD from 9:30am to 4:30pm EST, with a virtual attendance option, to introduce potential proposers to the Video LINCS program objectives of developing capabilities for autonomous re-identification of objects across diverse video sensor collections and mapping objects to a common reference frame. Initial technologies will focus on re-identifying people and vehicles across video, with the ultimate goal of re-identifying any object class without prior knowledge of object types or sensor information. The Intelligence Advanced Research Projects Activity seeks approaches to facilitate autonomous re-identification in open-world settings without preexisting knowledge of sensors, scenes, content, or video collection geometries. Participants must register by February 1, 2024 at noon EST, with limited in-person spots available and a maximum of two attendees per organization.
View the file
Other files
| File | Type | Posted |
|---|---|---|
| VideoLINCS_BAA_TechSection_Draft_2024_01_25_C.pdf |
On GovTribe
Work with this file
- Download the original file
- Contacts named in this file
- Similar government files
- Ask GovTribe AI about this file
Text version
OVERVIEW
The IARPA Video Linking and Intelligence from Non-Collabora�ve Sensors (Video LINCS) Proposers’ Day mee�ng will be held on Wednesday, February 7, 2024, from 9:30 a.m. to 4:30 p.m. EST in Linthicum, MD, to introduce the Video LINCS program to poten�al proposers and to provide informa�on on technical requirements and program objec�ves. A virtual atendance op�on will also be available.
The Video LINCS program aims to develop novel capabili�es to autonomously re-iden�fy objects across diverse video sensor collec�ons and map all objects to a common reference frame. Re-iden�fica�on (reID) is the process of matching the same object across a video collec�on, to determine where the object appears throughout the video. IARPA seeks technical approaches that will facilitate autonomous reID in an open-world se�ng where there is no advance knowledge of the sensors, scene, content or video collec�on geometries. ReID technologies will ini�ally be developed for specific object classes that are known in advance, such as people and vehicles, and ul�mately extent to all objects in the video footage without advance knowledge of specific object types. The capability to autonomously remap object loca�ons from individual camera reference frames to a single common reference frame will also be developed.
REGISTRATION
Par�cipants must register by Thursday, February 1, 2024, at noon EST. Same day registra�ons will not be accepted. Limited spots are available for in-person atendance and early registra�on is encouraged. Only two atendees per organiza�on or research group will be permited to atend in person. The link to register is: htps://www.client-mee�ng.net/videolincs-proposers-day.
Ques�ons about this announcement can be emailed to dni-iarpa-videolincs-proposersday@iarpa.gov.
File details come from the government source that posted it. Updated .