Uncertainty inspired underwater image enhancement
A main challenge faced in the deep learning-based Underwater Image Enhancement (UIE)
is that the ground truth high-quality image is unavailable. Most of the existing methods first …
is that the ground truth high-quality image is unavailable. Most of the existing methods first …
Multi-objective diverse human motion prediction with knowledge distillation
H Ma, J Li, R Hosseini… - Proceedings of the …, 2022 - openaccess.thecvf.com
Obtaining accurate and diverse human motion prediction is essential to many industrial
applications, especially robotics and autonomous driving. Recent research has explored …
applications, especially robotics and autonomous driving. Recent research has explored …
Behavior-driven synthesis of human dynamics
A Blattmann, T Milbich… - Proceedings of the …, 2021 - openaccess.thecvf.com
Generating and representing human behavior are of major importance for various computer
vision applications. Commonly, human video synthesis represents behavior as sequences …
vision applications. Commonly, human video synthesis represents behavior as sequences …
Artist: Autoregressive trajectory inpainting and scoring for tracking
One of the core components in online multiple object tracking (MOT) frameworks is
associating new detections with existing tracklets, typically done via a scoring function …
associating new detections with existing tracklets, typically done via a scoring function …
[图书][B] Towards Understanding Human Behavior for Autonomous Driving and Robotics
H Ma - 2023 - escholarship.org
The present era is witnessing a rapid development of intelligent agents that interact with
humans and there is no doubt that such intelligent agents will become an integral part of …
humans and there is no doubt that such intelligent agents will become an integral part of …