Zobrazeno 1 - 10
of 54
pro vyhledávání: '"Ren, Haibing"'
Autor:
Yang, Xinyi, Yang, Yuxiang, Yu, Chao, Chen, Jiayu, Yu, Jingchen, Ren, Haibing, Yang, Huazhong, Wang, Yu
This paper investigates the multi-agent cooperative exploration problem, which requires multiple agents to explore an unseen environment via sensory signals in a limited time. A popular approach to exploration tasks is to combine active mapping with
Externí odkaz:
http://arxiv.org/abs/2311.00252
Existing matching-based approaches perform video object segmentation (VOS) via retrieving support features from a pixel-level memory, while some pixels may suffer from lack of correspondence in the memory (i.e., unseen), which inevitably limits their
Externí odkaz:
http://arxiv.org/abs/2208.04026
Autor:
Zhao, Yusheng, Chen, Jinyu, Gao, Chen, Wang, Wenguan, Yang, Lirong, Ren, Haibing, Xia, Huaxia, Liu, Si
Vision-language navigation is the task of directing an embodied agent to navigate in 3D scenes with natural language instructions. For the agent, inferring the long-term navigation target from visual-linguistic clues is crucial for reliable path plan
Externí odkaz:
http://arxiv.org/abs/2207.11201
Since context modeling is critical for estimating depth from a single image, researchers put tremendous effort into obtaining global context. Many global manipulations are designed for traditional CNN-based architectures to overcome the locality of c
Externí odkaz:
http://arxiv.org/abs/2204.13892
Autor:
Luo, Junyu, Fu, Jiahui, Kong, Xianghao, Gao, Chen, Ren, Haibing, Shen, Hao, Xia, Huaxia, Liu, Si
3D visual grounding aims to locate the referred target object in 3D point cloud scenes according to a free-form language description. Previous methods mostly follow a two-stage paradigm, i.e., language-irrelevant detection and cross-modal matching, w
Externí odkaz:
http://arxiv.org/abs/2204.06272
Autor:
Feng, Chengjian, Zhong, Yujie, Jie, Zequn, Chu, Xiangxiang, Ren, Haibing, Wei, Xiaolin, Xie, Weidi, Ma, Lin
The goal of this work is to establish a scalable pipeline for expanding an object detector towards novel/unseen categories, using zero manual annotations. To achieve that, we make the following four contributions: (i) in pursuit of generalisation, we
Externí odkaz:
http://arxiv.org/abs/2203.16513
Publikováno v:
In Neurocomputing 14 October 2024 602
Autor:
Chu, Xiangxiang, Tian, Zhi, Wang, Yuqing, Zhang, Bo, Ren, Haibing, Wei, Xiaolin, Xia, Huaxia, Shen, Chunhua
Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their success in these tasks. In this work, we revisit the design of the spat
Externí odkaz:
http://arxiv.org/abs/2104.13840
In this work we present SwiftNet for real-time semisupervised video object segmentation (one-shot VOS), which reports 77.8% J &F and 70 FPS on DAVIS 2017 validation dataset, leading all present solutions in overall accuracy and speed performance. We
Externí odkaz:
http://arxiv.org/abs/2102.04604
Publikováno v:
Gong-kuang zidonghua, Vol 48, Iss 11, Pp 133-138 (2022)
The current fully mechanized mining equipment removal plan during sequencing working face mainly depends on manual preparation. The large workload and low efficiency lead to the extension of the construction period. The quick removal mainly depends o
Externí odkaz:
https://doaj.org/article/b9e3dbf414a94ddb91180419f1475c51