Zobrazeno 1 - 10
of 132
pro vyhledávání: '"Luo, Yunhao"'
Autor:
Luo, Yunhao, Du, Yilun
Large video models, pretrained on massive amounts of Internet video, provide a rich source of physical knowledge about the dynamics and motions of objects and tasks. However, video models are not grounded in the embodiment of an agent, and do not des
Externí odkaz:
http://arxiv.org/abs/2411.07223
Publikováno v:
In Proceedings of the 2024 ACM Designing Interactive Systems Conference (pp. 151-167) (2024, July)
Everyday objects, like remote controls or electric toothbrushes, are crafted with hand-accessible interfaces. Expanding on this design principle, extended reality (XR) interfaces for physical tasks could facilitate interaction without necessitating t
Externí odkaz:
http://arxiv.org/abs/2411.05245
Effective motion planning in high dimensional spaces is a long-standing open problem in robotics. One class of traditional motion planning algorithms corresponds to potential-based motion planning. An advantage of potential based motion planning is c
Externí odkaz:
http://arxiv.org/abs/2407.06169
In this paper, we tackle a new problem: how to transfer knowledge from the pre-trained cumbersome yet well-performed CNN-based model to learn a compact Vision Transformer (ViT)-based model while maintaining its learning capacity? Due to the completel
Externí odkaz:
http://arxiv.org/abs/2310.07265
Endeavors have been recently made to transfer knowledge from the labeled pinhole image domain to the unlabeled panoramic image domain via Unsupervised Domain Adaptation (UDA). The aim is to tackle the domain gaps caused by the style disparities and d
Externí odkaz:
http://arxiv.org/abs/2308.05493
In this paper, we strive to answer the question "how to collaboratively learn convolutional neural network (CNN)-based and vision transformer (ViT)-based models by selecting and exchanging the reliable knowledge between them for semantic segmentation
Externí odkaz:
http://arxiv.org/abs/2307.12574
Autor:
Hu, Qingqiao, Wang, Hao, Luo, Jing, Luo, Yunhao, Zhangg, Zhiheng, Kirschke, Jan S., Wiestler, Benedikt, Menze, Bjoern, Zhang, Jianguo, Li, Hongwei Bran
Automated medical image segmentation inherently involves a certain degree of uncertainty. One key factor contributing to this uncertainty is the ambiguity that can arise in determining the boundaries of a target region of interest, primarily due to v
Externí odkaz:
http://arxiv.org/abs/2306.16556
The popular methods for semi-supervised semantic segmentation mostly adopt a unitary network model using convolutional neural networks (CNNs) and enforce consistency of the model's predictions over perturbations applied to the inputs or model. Howeve
Externí odkaz:
http://arxiv.org/abs/2209.02178
Image restoration and enhancement is a process of improving the image quality by removing degradations, such as noise, blur, and resolution degradation. Deep learning (DL) has recently been applied to image restoration and enhancement. Due to its ill
Externí odkaz:
http://arxiv.org/abs/2206.02070
Publikováno v:
In Pattern Recognition February 2025 158
