Zobrazeno 1 - 10
of 1 429
pro vyhledávání: '"Jun, Hai"'
Autor:
Zhu, Haowei, Tang, Dehua, Liu, Ji, Lu, Mingjie, Zheng, Jintu, Peng, Jinzhang, Li, Dong, Wang, Yu, Jiang, Fan, Tian, Lu, Tiwari, Spandan, Sirasao, Ashish, Yong, Jun-Hai, Wang, Bin, Barsoum, Emad
Diffusion models have achieved remarkable progress in the field of image generation due to their outstanding capabilities. However, these models require substantial computing resources because of the multi-step denoising process during inference. Whi
Externí odkaz:
http://arxiv.org/abs/2410.16942
Autor:
Feng, Yifan, Huang, Jiangang, Du, Shaoyi, Ying, Shihui, Yong, Jun-Hai, Li, Yipeng, Ding, Guiguang, Ji, Rongrong, Gao, Yue
We introduce Hyper-YOLO, a new object detection method that integrates hypergraph computations to capture the complex high-order correlations among visual features. Traditional YOLO models, while powerful, have limitations in their neck designs that
Externí odkaz:
http://arxiv.org/abs/2408.04804
Hand manipulating objects is an important interaction motion in our daily activities. We faithfully reconstruct this motion with a single RGBD camera by a novel deep reinforcement learning method to leverage physics. Firstly, we propose object compen
Externí odkaz:
http://arxiv.org/abs/2405.02676
Autor:
Zhu, Haowei, Yang, Ling, Yong, Jun-Hai, Yin, Hongzhi, Jiang, Jiawei, Xiao, Meng, Zhang, Wentao, Wang, Bin
The scale and quality of a dataset significantly impact the performance of deep models. However, acquiring large-scale annotated datasets is both a costly and time-consuming endeavor. To address this challenge, dataset expansion technologies aim to a
Externí odkaz:
http://arxiv.org/abs/2403.06741
Lightweight creation of 3D digital avatars is a highly desirable but challenging task. With only sparse videos of a person under unknown illumination, we propose a method to create relightable and animatable neural avatars, which can be used to synth
Externí odkaz:
http://arxiv.org/abs/2312.12877
Interactive image segmentation aims at obtaining a segmentation mask for an image using simple user annotations. During each round of interaction, the segmentation result from the previous round serves as feedback to guide the user's annotation and p
Externí odkaz:
http://arxiv.org/abs/2303.11880
Publikováno v:
Discover Oncology, Vol 15, Iss 1, Pp 1-17 (2024)
Abstract Hepatocellular carcinoma (HCC) is a common primary liver cancer with a high incidence and mortality. Members of the growth-arresting-specific 2 (GAS2) family are involved in various biological processes in human malignancies. To date, there
Externí odkaz:
https://doaj.org/article/85a7d0b77d6a4444bf2d19ba746b35ce
Single view-based reconstruction of hand-object interaction is challenging due to the severe observation missing caused by occlusions. This paper proposes a physics-based method to better solve the ambiguities in the reconstruction. It first proposes
Externí odkaz:
http://arxiv.org/abs/2209.10833
Publikováno v:
The Clinical Respiratory Journal, Vol 18, Iss 8, Pp n/a-n/a (2024)
Abstract Background The collaboration between methylation and the lung adenocarcinoma (LUAD) occurrence and development is closes. Long noncoding RNA (lncRNA), as a regulatory factor of various biological functions, can be used for cancer diagnosis.
Externí odkaz:
https://doaj.org/article/d0f5e4008335410d9626199fcf6724c0
RGBD-based real-time dynamic 3D reconstruction suffers from inaccurate inter-frame motion estimation as errors may accumulate with online tracking. This problem is even more severe for single-view-based systems due to strong occlusions. Based on thes
Externí odkaz:
http://arxiv.org/abs/2203.07977