These models are intrinsically invariant to translation and rotation between scene elements, are best-performing on public leaderboards, but scale quadratically with the number of agents and scene elements.
1 code implementation • 29 Nov 2021 • Balakrishnan Varadarajan, Ahmed Hefny, Avikalp Srivastava, Khaled S. Refaat, Nigamaa Nayakanti, Andre Cornman, Kan Chen, Bertrand Douillard, Chi Pang Lam, Dragomir Anguelov, Benjamin Sapp
Predicting the future behavior of road users is one of the most challenging and important problems in autonomous driving.
Ranked #9 on Motion Forecasting on Argoverse CVPR 2020
2 code implementations • 19 Aug 2020 • Hang Zhao, Jiyang Gao, Tian Lan, Chen Sun, Benjamin Sapp, Balakrishnan Varadarajan, Yue Shen, Yi Shen, Yuning Chai, Cordelia Schmid, Cong-Cong Li, Dragomir Anguelov
Our key insight is that for prediction within a moderate time horizon, the future modes can be effectively captured by a set of target states.
Predicting human behavior is a difficult and crucial task required for motion planning.
Ranked #2 on Trajectory Prediction on PAID
Current approaches for fine-grained recognition do the following: First, recruit experts to annotate a dataset of images, optionally also collecting more structured data in the form of part annotations and bounding boxes.
For many structured prediction problems, complex models often require adopting approximate inference techniques such as variational methods or sampling, which generally provide no satisfactory accuracy guarantees.