Zobrazeno 1 - 10
of 46
pro vyhledávání: '"Choi, Wongun"'
In this paper, we propose a novel monocular ray-based 3D (Ray3D) absolute human pose estimation with calibrated camera. Accurate and generalizable absolute 3D human pose estimation from monocular 2D pose input is an ill-posed problem. To address this
Externí odkaz:
http://arxiv.org/abs/2203.11471
We present a conceptually simple self-supervised method for saliency detection. Our method generates and uses pseudo-ground truth labels for training. The generated pseudo-GT labels don't require any kind of human annotations (e.g., pixel-wise labels
Externí odkaz:
http://arxiv.org/abs/2203.04478
The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. However, it is not trivial to solve the data-association problem in an end-to-end fashion. In this paper, we propose a n
Externí odkaz:
http://arxiv.org/abs/2103.07889
Autor:
Zhao, Tianyang, Xu, Yifei, Monfort, Mathew, Choi, Wongun, Baker, Chris, Zhao, Yibiao, Wang, Yizhou, Wu, Ying Nian
Accurate prediction of others' trajectories is essential for autonomous driving. Trajectory prediction is challenging because it requires reasoning about agents' past movements, social interactions among varying numbers and kinds of agents, constrain
Externí odkaz:
http://arxiv.org/abs/1904.04776
This paper proposes a novel memory-based online video representation that is efficient, accurate and predictive. This is in contrast to prior works that often rely on computationally heavy 3D convolutions, ignore actual motion when aligning features
Externí odkaz:
http://arxiv.org/abs/1803.10861
Data association problems are an important component of many computer vision applications, with multi-object tracking being one of the most prominent examples. A typical approach to data association involves finding a graph matching or network flow t
Externí odkaz:
http://arxiv.org/abs/1706.08482
Autor:
Lee, Namhoon, Choi, Wongun, Vernaza, Paul, Choy, Christopher B., Torr, Philip H. S., Chandraker, Manmohan
We introduce a Deep Stochastic IOC RNN Encoderdecoder framework, DESIRE, for the task of future predictions of multiple interacting agents in dynamic scenes. DESIRE effectively predicts future locations of objects in multiple scenes by 1) accounting
Externí odkaz:
http://arxiv.org/abs/1704.04394
In CNN-based object detection methods, region proposal becomes a bottleneck when objects exhibit significant scale variation, occlusion or truncation. In addition, these methods mainly focus on 2D object detection and cannot estimate detailed propert
Externí odkaz:
http://arxiv.org/abs/1604.04693
Autor:
Choi, Wongun
In this paper, we focus on the two key aspects of multiple target tracking problem: 1) designing an accurate affinity measure to associate detections and 2) implementing an efficient and accurate (near) online multiple target tracking algorithm. As t
Externí odkaz:
http://arxiv.org/abs/1504.02340
Publikováno v:
In Robotics and Autonomous Systems February 2019 112:178-189
