no code implementations • WASSA (ACL) 2022 • Hao Lin, Pradeep Nalluri, Lantian Li, Yifan Sun, Yongjun Zhang
We introduce new datasets from Twitter related to anti-Asian hate sentiment before and during the pandemic.
no code implementations • 14 Jan 2025 • Wei Long, Yongjun Zhang, Zhongwei Cui, Yujie Xu, Xuexue Zhang
Based on TAM, we present a threshold attention network (TANet) for semantic segmentation.
1 code implementation • 2 Jan 2025 • Ziyang Chen, Yongjun Zhang, Wenting Li, Bingshu Wang, Yabo Wu, Yong Zhao, C. L. Philip Chen
However, constrained by the low-rank bottleneck and quadratic complexity of attention mechanisms, stereo transformers still fail to demonstrate sufficient nonlinear expressiveness within a reasonable inference time.
no code implementations • 25 Dec 2024 • Qiong Wu, Panwang Xia, Lei Yu, Yi Liu, Mingtao Xiong, Liheng Zhong, Jingdong Chen, Ming Yang, Yongjun Zhang, Yi Wan
Therefore, we propose a novel task: Cross-View Image Set Geo-Localization (Set-CVGL), which gathers multiple images with diverse perspectives as a query set for localization.
2 code implementations • 16 Dec 2024 • Panwang Xia, Lei Yu, Yi Wan, Qiong Wu, Peiqi Chen, Liheng Zhong, Yongxiang Yao, Dong Wei, Xinyi Liu, Lixiang Ru, Yingying Zhang, Jiangwei Lao, Jingdong Chen, Ming Yang, Yongjun Zhang
To address this limitation, we introduce DReSS (Decentrality Related Street-view and Satellite-view dataset), a novel dataset designed to evaluate cross-view geo-localization with a large geographic scope and diverse landscapes, emphasizing the decentrality issue.
no code implementations • 26 Nov 2024 • Chang Li, Yu Wang, Ce Zhang, Yongjun Zhang
Terraced field is a significant engineering practice for soil and water conservation (SWC).
1 code implementation • 19 Nov 2024 • Ziyang Chen, Yongjun Zhang, Wenting Li, Bingshu Wang, Yong Zhao, C. L. Philip Chen
However, learning-based stereo matching methods inherently suffer from the loss of geometric structures in certain feature channels, creating a bottleneck in achieving precise detail matching.
1 code implementation • 21 Oct 2024 • Pengcheng Shi, Shaocheng Yan, Yilin Xiao, Xinyi Liu, Yongjun Zhang, Jiayuan Li
Firstly, one-point RANSAC obtains a consensus set based on length consistency.
no code implementations • 6 Aug 2024 • He Yao, Yongjun Zhang, Huachun Jian, Li Zhang, Ruzhong Cheng
The significance of background information is frequently overlooked in contemporary research concerning channel attention mechanisms.
no code implementations • 16 Jul 2024 • Chang Li, Jiao Guo, Yufei Zhao, Yongjun Zhang
This paper is the first to propose an end-to-end framework of mutually reinforcing images to 3D surface recurrent neural network-like for model-adaptation indoor 3D reconstruction, where multi-view dense matching and point cloud surface optimization are mutually reinforced by a RNN-like structure rather than being treated as a separate issue. The characteristics are as follows:In the multi-view dense matching module, the model-adaptation strategy is used to fine-tune and optimize a Transformer-based multi-view dense matching DNN, so that it has the higher image feature for matching and detail expression capabilities;In the point cloud surface optimization module, the 3D surface reconstruction network based on 3D implicit field is optimized by using model-adaptation strategy, which solves the problem of point cloud surface optimization without knowing normal vector of 3D surface. To improve and finely reconstruct 3D surfaces from point cloud, smooth loss is proposed and added to this module;The MRIo3DS-Net is a RNN-like framework, which utilizes the finely optimized 3D surface obtained by PCSOM to recursively reinforce the differentiable warping for optimizing MVDMM. This refinement leads to achieving better dense matching results, and better dense matching results leads to achieving better 3D surface results recursively and mutually. Hence, model-adaptation strategy can better collaborate the differences between the two network modules, so that they complement each other to achieve the better effect;To accelerate the transfer learning and training convergence from source domain to target domain, a multi-task loss function based on Bayesian uncertainty is used to adaptively adjust the weights between the two networks loss functions of MVDMM and PCSOM;In this multi-task cascade network framework, any modules can be replaced by any state-of-the-art networks to achieve better 3D reconstruction results.
no code implementations • 23 Jun 2024 • Pengfei Zhang, Chang Li, Yongjun Zhang, Rongjun Qin
Besides the aforementioned spectrum noises in semantic segmentation, MUDM is also a self-supervised learning strategy to effectively reduce the edge false change detection from the generated imagery with geometric registration error.
1 code implementation • 14 Jun 2024 • Junwei Luo, Zhen Pang, Yongjun Zhang, Tingzhu Wang, LinLin Wang, Bo Dang, Jiangwei Lao, Jian Wang, Jingdong Chen, Yihua Tan, Yansheng Li
Remote Sensing Large Multi-Modal Models (RSLMMs) are developing rapidly and showcase significant capabilities in remote sensing imagery (RSI) comprehension.
3 code implementations • 13 Jun 2024 • Yansheng Li, LinLin Wang, Tingzhu Wang, Xue Yang, Junwei Luo, Qi Wang, Youming Deng, Wenbin Wang, Xian Sun, Haifeng Li, Bo Dang, Yongjun Zhang, Yi Yu, Junchi Yan
This paper constructs a large-scale dataset for SGG in large-size VHR SAI with image sizes ranging from 512 x 768 to 27, 860 x 31, 096 pixels, named STAR (Scene graph generaTion in lArge-size satellite imageRy), encompassing over 210K objects and over 400K triplets.
no code implementations • 14 Apr 2024 • Jieyi Tan, Yansheng Li, Sergey A. Bartalev, Shinkarenko Stanislav, Bo Dang, Yongjun Zhang, Liangqi Yuan, Wei Chen
Our framework consists of three modules, including the Global Insight Enhancement (GIE) module, the Essential Feature Mining (EFM) module and the Local-Global Balance (LoGo) module.
no code implementations • 11 Apr 2024 • Yansheng Li, Kun Li, Yongjun Zhang, LinLin Wang, Dingwen Zhang
To fill in the gap of the overhead view dataset, this paper constructs and releases an aerial image urban scene graph generation (AUG) dataset.
1 code implementation • CVPR 2024 • Ziyang Chen, Wei Long, He Yao, Yongjun Zhang, Bingshu Wang, Yongbin Qin, Jia Wu
In addition, edge variations in %potential feature channels of the reconstruction error map also affect details matching, we propose the Reconstruction Error Motif Penalty (REMP) module to further refine the full-resolution disparity estimation.
Ranked #1 on
Stereo Disparity Estimation
on Middlebury 2014
2 code implementations • 24 Feb 2024 • Chunwei Tian, Xuanyu Zhang, Tao Wang, Yongjun Zhang, Qi Zhu, Chia-Wen Lin
The lower network utilizes a symmetric architecture to enhance relations of different layers to mine more structural information, which is complementary with a upper network for image super-resolution.
no code implementations • 8 Feb 2024 • Qianchen Mao, Qiang Li, Bingshu Wang, Yongjun Zhang, Tao Dai, C. L. Philip Chen
To tackle this challenge, we propose SpirDet, a novel approach for efficient detection of infrared small targets.
1 code implementation • 31 Dec 2023 • Run Shao, Cheng Yang, Qiujun Li, Qing Zhu, Yongjun Zhang, Yansheng Li, Yu Liu, Yong Tang, Dapeng Liu, Shizhong Yang, Haifeng Li
To maintain modality autonomy, AllSpark uses modality-specific encoders to extract the tokens of various spatio-temporal modalities.
1 code implementation • CVPR 2024 • Xin Guo, Jiangwei Lao, Bo Dang, Yingying Zhang, Lei Yu, Lixiang Ru, Liheng Zhong, Ziyuan Huang, Kang Wu, Dingxiang Hu, Huimei He, Jian Wang, Jingdong Chen, Ming Yang, Yongjun Zhang, Yansheng Li
Prior studies on Remote Sensing Foundation Model (RSFM) reveal immense potential towards a generic model for Earth Observation.
no code implementations • 5 Dec 2023 • Yansheng Li, Junwei Luo, Yongjun Zhang, Yihua Tan, Jin-Gang Yu, Song Bai
Therefore, to ensure the visibility and integrity of bridges, it is essential to perform holistic bridge detection in large-size very-high-resolution (VHR) RSIs.
1 code implementation • 30 Nov 2023 • Yongjun Zhang
First, the longformer model was fine-tuned using the Dynamic of Collective Action (DoCA) Corpus.
no code implementations • 28 Mar 2023 • Yameng Wang, Yi Wan, Yongjun Zhang, Bin Zhang, Zhi Gao
The present multi-modal methods usually map high-dimensional features to low-dimensional spaces as a preprocess before feature extraction to address the nonnegligible domain gap, which inevitably leads to information loss.
no code implementations • 16 Mar 2023 • Yansheng Li, Bo Dang, Wanchun Li, Yongjun Zhang
Global surface water detection in very-high-resolution (VHR) satellite imagery can directly serve major applications such as refined flood mapping and water resource assessment.
1 code implementation • 1 Mar 2023 • Jiayuan Li, Pengcheng Shi, Qingwu Hu, Yongjun Zhang
Multimodal image matching is an important prerequisite for multisource image information fusion.
no code implementations • CVPR 2023 • Haoliang Zhao, Huizhou Zhou, Yongjun Zhang, Jie Chen, Yitong Yang, Yong Zhao
In the field of binocular stereo matching, remarkable progress has been made by iterative methods like RAFT-Stereo and CREStereo.
no code implementations • 22 Nov 2022 • Bo Dang, Yansheng Li, Yongjun Zhang, Jiayi Ma
Semi-supervised semantic segmentation focuses on the exploration of a small amount of labeled data and a large amount of unlabeled data, which is more in line with the demands of real-world image understanding applications.
no code implementations • 21 Nov 2022 • Wei Chen, Yansheng Li, Bo Dang, Yongjun Zhang
This paper presents EHSNet, a new end-to-end segmentation network designed for the holistic learning of large-size remote sensing image semantic segmentation (LRISS).
no code implementations • 14 Mar 2022 • Youming Deng, Yansheng Li, Yongjun Zhang, Xiang Xiang, Jian Wang, Jingdong Chen, Jiayi Ma
After the autonomous partition of coarse and fine predicates, the model is first trained on the coarse predicates and then learns the fine predicates.
no code implementations • 21 Feb 2022 • Yongjun Zhang, Siyuan Zou, Xinyi Liu, Xu Huang, Yi Wan, Yongxiang Yao
Next, we propose a riverbed enhancement function to optimize the cost volume of the LiDAR projection points and their homogeneous pixels to improve the matching robustness.
1 code implementation • 15 Jan 2022 • Weiwei Song, Zhi Gao, Renwei Dian, Pedram Ghamisi, Yongjun Zhang, Jón Atli Benediktsson
In this paper, we propose a novel deep hashing method, named asymmetric hash code learning (AHCL), for RSIR.
no code implementations • CVPR 2022 • Dong Wei, Yi Wan, Yongjun Zhang, Xinyi Liu, Bin Zhang, Xiqi Wang
In this paper, we propose an efficient line segment reconstruction method called ELSR.
1 code implementation • 1 Nov 2021 • Ling Chen, Jun Cui, Xing Tang, Chaodu Song, Yuntao Qian, Yansheng Li, Yongjun Zhang
Therefore, neighbor aggregation-based representation learning (NARL) models are proposed, which encode the information in the neighbors of an entity into its embeddings.
1 code implementation • 27 Aug 2021 • Ling Chen, Jiahui Xu, Binqing Wu, Yuntao Qian, Zhenhong Du, Yansheng Li, Yongjun Zhang
The model constructs a city graph and a city group graph to model the spatial and latent dependencies between cities, respectively.
no code implementations • 6 Oct 2020 • Yansheng Li, Song Ouyang, Yongjun Zhang
As one kind of architecture from the deep learning family, deep semantic segmentation network (DSSN) achieves a certain degree of success on the semantic segmentation task and obviously outperforms the traditional methods based on hand-crafted features.
Segmentation Of Remote Sensing Imagery
Semantic Segmentation
no code implementations • 26 Jun 2019 • Ruoxiang Li, Dianxi Shi, Yongjun Zhang, Kaiyue Li, Ruihao Li
The proposed G-SAE maintenance algorithm and corner candidate selection algorithm greatly enhance the real-time performance for corner detection, while the corner candidate refinement algorithm maintains the accuracy of performance by using an improved event-based Harris detector.