Zobrazeno 1 - 10
of 3 642
pro vyhledávání: '"Li, Zhiyong"'
Autor:
Yang, Fan, Chen, Wenrui, Yang, Kailun, Lin, Haoran, Luo, DongSheng, Tang, Conghui, Li, Zhiyong, Wang, Yaonan
To enable robots to use tools, the initial step is teaching robots to employ dexterous gestures for touching specific areas precisely where tasks are performed. Affordance features of objects serve as a bridge in the functional interaction between ag
Externí odkaz:
http://arxiv.org/abs/2407.00614
Autor:
Li, Siyu, Lin, Jiacheng, Shi, Hao, Zhang, Jiaming, Wang, Song, Yao, You, Li, Zhiyong, Yang, Kailun
Temporal information plays a pivotal role in Bird's-Eye-View (BEV) driving scene understanding, which can alleviate the visual information sparsity. However, the indiscriminate temporal fusion method will cause the barrier of feature redundancy when
Externí odkaz:
http://arxiv.org/abs/2405.05518
Autor:
Zeng, Kang, Shi, Hao, Lin, Jiacheng, Li, Siyu, Cheng, Jintao, Wang, Kaiwei, Li, Zhiyong, Yang, Kailun
LiDAR-based Moving Object Segmentation (MOS) aims to locate and segment moving objects in point clouds of the current scan using motion information from previous scans. Despite the promising results achieved by previous MOS methods, several key issue
Externí odkaz:
http://arxiv.org/abs/2404.12794
Autor:
Lin, Jiacheng, Chen, Jiajun, Peng, Kunyu, He, Xuan, Li, Zhiyong, Stiefelhagen, Rainer, Yang, Kailun
This paper introduces the task of Auditory Referring Multi-Object Tracking (AR-MOT), which dynamically tracks specific objects in a video sequence based on audio expressions and appears as a challenging problem in autonomous driving. Due to the lack
Externí odkaz:
http://arxiv.org/abs/2402.18302
Leveraging the rich information extracted from light field (LF) cameras is instrumental for dense prediction tasks. However, adapting light field data to enhance Salient Object Detection (SOD) still follows the traditional RGB methods and remains und
Externí odkaz:
http://arxiv.org/abs/2401.16712
Autor:
Pan, Chenxinyu, Tong, Yuanbiao, Qian, Haoliang, Krasavin, Alexey V., Li, Jialin, Zhu, Jiajie, Zhang, Yiyun, Cui, Bowen, Li, Zhiyong, Wu, Chenming, Wang, Zhenxin, Liu, Lufang, Li, Linjun, Guo, Xin, Zayats, Anatoly V., Tong, Limin, Wang, Pan
Publikováno v:
Nature Commun. 15 (2024) 2840-2849
Two-dimensional single-crystal metals are highly sought after for next-generation technologies. Here, we report large-area (>10^4 {\mu}m2), single-crystal two-dimensional gold with thicknesses down to a single-nanometer level, employing an atomic-lev
Externí odkaz:
http://arxiv.org/abs/2311.07858
Autor:
Liu, Jie, Pang, Zufeng, Li, Zhiyong, Wen, Guilin, Su, Zhoucheng, He, Junfeng, Liu, Kaiyue, Jiang, Dezheng, Li, Zenan, Chen, Shouyan, Tian, Yang, Xie, Yi Min, Wang, Zhenpei, Liu, Zhuangjian
Origami-inspired robots with multiple advantages, such as being lightweight, requiring less assembly, and exhibiting exceptional deformability, have received substantial and sustained attention. However, the existing origami-inspired robots are usual
Externí odkaz:
http://arxiv.org/abs/2310.00033
Recently, transformer-based methods have shown exceptional performance in monocular 3D object detection, which can predict 3D attributes from a single 2D image. These methods typically use visual and depth representations to generate query points on
Externí odkaz:
http://arxiv.org/abs/2309.00928
Audio-guided Video Object Segmentation (A-VOS) and Referring Video Object Segmentation (R-VOS) are two highly-related tasks, which both aim to segment specific objects from video sequences according to user-provided expression prompts. However, due t
Externí odkaz:
http://arxiv.org/abs/2308.04162
The recently rising markup-to-image generation poses greater challenges as compared to natural image generation, due to its low tolerance for errors as well as the complex sequence and context correlations between markup and rendered image. This pape
Externí odkaz:
http://arxiv.org/abs/2308.01147