Zobrazeno 1 - 10
of 860
pro vyhledávání: '"YU, Jingyi"'
Autor:
Liang, Han, Huang, Chengyu, Xu, Yuecheng, Tang, Cheng, Ye, Weicai, Zhang, Juze, Chen, Xin, Yu, Jingyi, Xu, Lan
In the realm of Sign Language Translation (SLT), reliance on costly gloss-annotated datasets has posed a significant barrier. Recent advancements in gloss-free SLT methods have shown promise, yet they often largely lag behind gloss-based approaches i
Externí odkaz:
http://arxiv.org/abs/2412.16524
Autor:
Mu, Jiazuo, Yang, Fuyi, Zhang, Yanshun, Zhang, Junxiong, Luo, Yongjian, Xu, Lan, Shi, Yujiao, Yu, Jingyi, Zhang, Yingliang
We introduce CADSpotting, an efficient method for panoptic symbol spotting in large-scale architectural CAD drawings. Existing approaches struggle with the diversity of symbols, scale variations, and overlapping elements in CAD designs. CADSpotting o
Externí odkaz:
http://arxiv.org/abs/2412.07377
Ring artifacts are prevalent in 3D cone-beam computed tomography (CBCT) due to non-ideal responses of X-ray detectors, severely degrading imaging quality and reliability. Current state-of-the-art (SOTA) ring artifact reduction (RAR) algorithms rely o
Externí odkaz:
http://arxiv.org/abs/2412.05853
Autor:
Wu, Shijie, Zhu, Yihang, Huang, Yunao, Zhu, Kaizhen, Gu, Jiayuan, Yu, Jingyi, Shi, Ye, Wang, Jingya
Diffusion-based policies have shown impressive performance in robotic manipulation tasks while struggling with out-of-domain distributions. Recent efforts attempted to enhance generalization by improving the visual feature encoding for diffusion poli
Externí odkaz:
http://arxiv.org/abs/2412.03142
3D affordance segmentation aims to link human instructions to touchable regions of 3D objects for embodied manipulations. Existing efforts typically adhere to single-object, single-affordance paradigms, where each affordance type or explicit instruct
Externí odkaz:
http://arxiv.org/abs/2412.01550
Autor:
Pan, Bikang, Li, Qun, Tang, Xiaoying, Huang, Wei, Fang, Zhen, Liu, Feng, Wang, Jingya, Yu, Jingyi, Shi, Ye
The emergence of vision-language foundation models, such as CLIP, has revolutionized image-text representation, enabling a broad range of applications via prompt learning. Despite its promise, real-world datasets often contain noisy labels that can d
Externí odkaz:
http://arxiv.org/abs/2412.01256
Autor:
Zhao, Fuqiang, Guo, Yijing, Yang, Siyuan, Chen, Xi, Wang, Luo, Xu, Lan, Zhang, Yingliang, Shi, Yujiao, Yu, Jingyi
High-quality 3D urban reconstruction is essential for applications in urban planning, navigation, and AR/VR. However, capturing detailed ground-level data across cities is both labor-intensive and raises significant privacy concerns related to sensit
Externí odkaz:
http://arxiv.org/abs/2412.00157
Autor:
Yang, Hongdi, Li, Chengyang, Wu, Zhenxuan, Li, Gaozheng, Wang, Jingya, Yu, Jingyi, Su, Zhuo, Xu, Lan
Soccer is a globally renowned sport with significant applications in video games and VR/AR. However, generating realistic soccer motions remains challenging due to the intricate interactions between the human player and the ball. In this paper, we in
Externí odkaz:
http://arxiv.org/abs/2411.16216
Autor:
Shi, Yan, Zhao, Denghui, Yu, Jingyi, Ni, Wei, Li, Pengcheng, Gu, Yun, Miao, Peng, Tong, Shanbao
It is of paramount importance to visualize blood dynamics intraoperatively, as this enables the accurate diagnosis of intraoperative conditions and facilitates informed surgical decision-making. Indocyanine green (ICG) fluorescence imaging represents
Externí odkaz:
http://arxiv.org/abs/2411.16039
The recent popular radiance field models, exemplified by Neural Radiance Fields (NeRF), Instant-NGP and 3D Gaussian Splatting, are designed to represent 3D content by that training models for each individual scene. This unique characteristic of scene
Externí odkaz:
http://arxiv.org/abs/2410.19483