Zobrazeno 1 - 10
of 345
pro vyhledávání: '"Wang Yongcai"'
This paper investigates the 3D domain generalization (3DDG) ability of large 3D models based on prevalent prompt learning. Recent works demonstrate the performances of 3D point cloud recognition can be boosted remarkably by parameter-efficient prompt
Externí odkaz:
http://arxiv.org/abs/2410.20406
View-based methods have demonstrated promising performance in 3D shape understanding. However, they tend to make strong assumptions about the relations between views or learn the multi-view correlations indirectly, which limits the flexibility of exp
Externí odkaz:
http://arxiv.org/abs/2409.09254
Detecting locally, non-overlapping, near-clique densest subgraphs is a crucial problem for community search in social networks. As a vertex may be involved in multiple overlapped local cliques, detecting locally densest sub-structures considering h-c
Externí odkaz:
http://arxiv.org/abs/2408.14022
Autor:
Wang, Shuo, Wang, Yongcai, Xu, Zhimin, Guo, Yongyu, Li, Wanting, Huang, Zhe, Bai, Xuewei, Li, Deying
For interacting with mobile objects in unfamiliar environments, simultaneously locating, mapping, and tracking the 3D poses of multiple objects are crucially required. This paper proposes a Tracklet Graph and Query Graph-based framework, i.e., GSLAMO
Externí odkaz:
http://arxiv.org/abs/2408.09191
Autor:
Cai, Xudong, Wang, Yongcai, Luo, Lun, Wang, Minhang, Li, Deying, Xu, Jintao, Gu, Weihao, Ai, Rui
Image matching aims at identifying corresponding points between a pair of images. Currently, detector-free methods have shown impressive performance in challenging scenarios, thanks to their capability of generating dense matches and global receptive
Externí odkaz:
http://arxiv.org/abs/2408.03598
Publikováno v:
Proceedings of the 32nd ACM International Conference on Multimedia (MM '24), October 28-November 1, 2024, Melbourne, VIC, Australia
Collaborative autonomous driving with multiple vehicles usually requires the data fusion from multiple modalities. To ensure effective fusion, the data from each individual modality shall maintain a reasonably high quality. However, in collaborative
Externí odkaz:
http://arxiv.org/abs/2408.00257
Multi-object tracking (MOT) on static platforms, such as by surveillance cameras, has achieved significant progress, with various paradigms providing attractive performances. However, the effectiveness of traditional MOT methods is significantly redu
Externí odkaz:
http://arxiv.org/abs/2407.09051
The availability of city-scale Lidar maps enables the potential of city-scale place recognition using mobile cameras. However, the city-scale Lidar maps generally need to be compressed for storage efficiency, which increases the difficulty of direct
Externí odkaz:
http://arxiv.org/abs/2402.15961
This paper presents a parameter-efficient prompt tuning method, named PPT, to adapt a large multi-modal model for 3D point cloud understanding. Existing strategies are quite expensive in computation and storage, and depend on time-consuming prompt en
Externí odkaz:
http://arxiv.org/abs/2402.15823
Autor:
Wang, Linlin, Wang, Shixin, Wang, Peng, Wang, Wei, Wang, Dezhao, Wang, Yongcai, Wang, Shanwen
In the realm of intelligent transportation systems, accurate and reliable traffic monitoring is crucial. Traditional devices, such as cameras and lidars, face limitations in adverse weather conditions and complex traffic scenarios, prompting the need
Externí odkaz:
http://arxiv.org/abs/2402.09422