The deadline for submitting entries to the ROAD Challenge on Event Detection for Situation Awareness in Autonomous Driving, co-located with ICCV 2021, is ***September 30 2021***
https://sites.google.com/view/roadchallangeiccv2021/challenge The Challenge leverages our recently released ROad event Awareness Dataset for autonomous driving (ROAD): https://lnkd.in/gjr9M5Z to propose three video-level detection tasks: (1) agent detection, (2) action detection and (3) road event detection, intended as a triplet (agent, action, location). All tasks consist in regressing ‘tubes’ of temporally linked bounding boxes and the associated label(s). Researchers active in object detection or action detection are very much encouraged to participate! The dataset is composed of 22 long duration (8-minute-long) videos in diverse weather conditions, making the above detection tasks extremely challenging even for state of the art detectors. The authors of the top entry in each Challenge task will be given the chance to give an oral presentation at the ROAD @ ICCV 2021 workshop: https://lnkd.in/gsBU5wU Submission take place via our Eval.ai platform: https://eval.ai/web/challenges/challenge-page/1059/overview For any questions about the ROAD dataset or the challenge please inquire with Gurkirt Singh gurkirt.si...@vision.ee.ethz.ch Reza Alitappeh rezajavanmar...@gmail.com Fabio Cuzzolin fabio.cuzzo...@brookes.ac.uk
_______________________________________________ uai mailing list uai@engr.orst.edu https://it.engineering.oregonstate.edu/mailman/listinfo/uai
