no code implementations • 22 Apr 2023 • Yuxing Chen, Maofan Zhao, Lorenzo Bruzzone
The mechanism of connecting multimodal signals through self-attention operation is a key factor in the success of multimodal Transformer networks in remote sensing data fusion tasks.
no code implementations • 22 Apr 2023 • Yuxing Chen, Lorenzo Bruzzone
In this work, we propose a two-stage approach to unsupervised change detection in satellite image time-series using contrastive learning with feature tracking.
no code implementations • 25 May 2022 • Yuxing Chen, Renshu Gu, Ouhan Huang, Gangyong Jia
The proposed VTP framework integrates the high performance of the transformer with volumetric representations, which can be used as a good alternative to the convolutional backbones.
Ranked #4 on 3D Human Pose Estimation on Panoptic (using extra training data)
no code implementations • 27 Jan 2022 • Yingchao Pan, Ouhan Huang, Qinghao Ye, Zhongjin Li, Wenjiang Wang, Guodun Li, Yuxing Chen
By combining these two attention mechanisms, a video SUMmarization model with Diversified Contextual Attention scheme is developed, namely SUM-DCA.
no code implementations • 18 May 2021 • Yuxing Chen, Lorenzo Bruzzone
To overcome the effects of regular seasonal changes in binary change maps, we also used an uncertainty method to enhance the temporal robustness of the proposed approach.
1 code implementation • 10 Mar 2021 • Yuxing Chen, Lorenzo Bruzzone
In this approach, a pseudo-Siamese network is trained to regress the output between its two branches pre-trained in a contrastive way on a large dataset of multi-temporal homogeneous or heterogeneous image patches.
no code implementations • 9 Mar 2021 • Yuxing Chen, Lorenzo Bruzzone
For the land-cover mapping task, we assign each pixel a land-cover class by the joint use of pre-trained features and spectral information of the image itself.
1 code implementation • 10 Nov 2020 • Lei Ding, Kai Zheng, Dong Lin, Yuxing Chen, Bing Liu, Jiansheng Li, Lorenzo Bruzzone
This CNN architecture can be used as a baseline method for future studies on the semantic segmentation of PolSAR images.
1 code implementation • ACL 2020 • Sebastian Schuster, Yuxing Chen, Judith Degen
Pragmatic inferences often subtly depend on the presence or absence of linguistic features.
1 code implementation • 4 Oct 2019 • Hang Jiang, Haoshen Hong, Yuxing Chen, Vivek Kulkarni
In this work, we propose a model that enables detection of dialectal variation at multiple levels of geographic resolution obviating the need for a-priori definition of the resolution level.