3 code implementations • 29 Mar 2024 • Yikang Zhou, Tao Zhang, Shunping Ji, Shuicheng Yan, Xiangtai Li
Modern video segmentation methods adopt object queries to perform inter-frame association and demonstrate satisfactory performance in tracking continuously appearing objects despite large-scale motion and transient occlusion.
2 code implementations • 1 Mar 2024 • Tao Zhang, Xiangtai Li, Haobo Yuan, Shunping Ji, Shuicheng Yan
To enable more effective processing of 3-D point cloud data by Mamba, we propose a novel Consistent Traverse Serialization to convert point clouds into 1-D point sequences while ensuring that neighboring points in the sequence are also spatially adjacent.
1 code implementation • 20 Dec 2023 • Tao Zhang, Xingye Tian, Yikang Zhou, Shunping Ji, Xuebo Wang, Xin Tao, Yuan Zhang, Pengfei Wan, Zhongyuan Wang, Yu Wu
We present the \textbf{D}ecoupled \textbf{VI}deo \textbf{S}egmentation (DVIS) framework, a novel approach for the challenging task of universal video segmentation, including video instance segmentation (VIS), video semantic segmentation (VSS), and video panoptic segmentation (VPS).
Ranked #1 on Video Semantic Segmentation on VSPW
no code implementations • 8 Sep 2023 • Dawen Yu, Shunping Ji
In this paper, we propose a novel supervised long-range correlation method for land-cover classification, called the supervised long-range correlation network (SLCNet), which is shown to be superior to the currently used unsupervised strategies.
1 code implementation • 28 Aug 2023 • Tao Zhang, Xingye Tian, Yikang Zhou, Yu Wu, Shunping Ji, Cilin Yan, Xuebo Wang, Xin Tao, Yuan Zhang, Pengfei Wan
Video instance segmentation is a challenging task that serves as the cornerstone of numerous downstream applications, including video editing and autonomous driving.
1 code implementation • 7 Jun 2023 • Tao Zhang, Xingye Tian, Haoran Wei, Yu Wu, Shunping Ji, Xuebo Wang, Xin Tao, Yuan Zhang, Pengfei Wan
In this report, we successfully validated the effectiveness of the decoupling strategy in video panoptic segmentation.
1 code implementation • ICCV 2023 • Tao Zhang, Xingye Tian, Yu Wu, Shunping Ji, Xuebo Wang, Yuan Zhang, Pengfei Wan
The efficacy of the decoupling strategy relies on two crucial elements: 1) attaining precise long-term alignment outcomes via frame-by-frame association during tracking, and 2) the effective utilization of temporal information predicated on the aforementioned accurate alignment outcomes during refinement.
Ranked #3 on Video Panoptic Segmentation on VIPSeg
no code implementations • 7 Nov 2022 • Shiqing Wei, Tao Zhang, Shunping Ji, Muying Luo, Jianya Gong
Deep learning based methods have significantly boosted the study of automatic building extraction from remote sensing images.
no code implementations • 22 Aug 2022 • Muying Luo, Shunping Ji, Shiqing Wei
In addition, to further improve the generalization ability of a building extraction model, we propose a domain generalization method named batch style mixing (BSM), which can be embedded as an efficient plug-and-play module in the frond-end of a building extraction model, providing the model with a progressively larger data distribution to learn data-invariant knowledge.
1 code implementation • CVPR 2022 • Tao Zhang, Shiqing Wei, Shunping Ji
In this paper, we introduce a novel contour-based method, named E2EC, for high-quality instance segmentation.
Ranked #97 on Instance Segmentation on COCO test-dev
1 code implementation • ICCV 2021 • Jian Gao, Jin Liu, Shunping Ji
Based on the RPC warping, we propose the deep learning based satellite MVS (SatMVS) framework for large-scale and wide depth range Earth surface reconstruction.
1 code implementation • 25 Oct 2020 • Yao Wei, Shunping Ji
Road surface extraction from remote sensing images using deep learning methods has achieved good performance, while most of the existing methods are based on fully supervised learning, which requires a large amount of training data with laborious per-pixel annotation.
1 code implementation • CVPR 2020 • Jin Liu, Shunping Ji
In this paper, we present a synthetic aerial dataset, called the WHU dataset, we created for MVS tasks, which, to our knowledge, is the first large-scale multi-view aerial dataset.