Zobrazeno 1 - 10
of 67
pro vyhledávání: '"Xing, Yinghui"'
Autor:
Zhang, Shizhou, Kong, Dexuan, Xing, Yinghui, Lu, Yue, Ran, Lingyan, Liang, Guoqiang, Wang, Hexu, Zhang, Yanning
Camouflaged object detection (COD) aims to segment camouflaged objects which exhibit very similar patterns with the surrounding environment. Recent research works have shown that enhancing the feature representation via the frequency information can
Externí odkaz:
http://arxiv.org/abs/2409.12421
Autor:
Zhang, Shizhou, Luo, Wenlong, Cheng, De, Yang, Qingchun, Ran, Lingyan, Xing, Yinghui, Zhang, Yanning
In this paper, we construct a large-scale benchmark dataset for Ground-to-Aerial Video-based person Re-Identification, named G2A-VReID, which comprises 185,907 images and 5,576 tracklets, featuring 2,788 distinct identities. To our knowledge, this is
Externí odkaz:
http://arxiv.org/abs/2408.07500
Existing prompt-tuning methods have demonstrated impressive performances in continual learning (CL), by selecting and updating relevant prompts in the vision-transformer models. On the contrary, this paper aims to learn each task by tuning the prompt
Externí odkaz:
http://arxiv.org/abs/2406.05658
Semantic segmentation of remote sensing images is a challenging and hot issue due to the large amount of unlabeled data. Unsupervised domain adaptation (UDA) has proven to be advantageous in incorporating unclassified information from the target doma
Externí odkaz:
http://arxiv.org/abs/2403.02784
Fusion of a panchromatic (PAN) image and corresponding multispectral (MS) image is also known as pansharpening, which aims to combine abundant spatial details of PAN and spectral information of MS. Due to the absence of high-resolution MS images, ava
Externí odkaz:
http://arxiv.org/abs/2401.05153
Autor:
Zhang, Shizhou, Yang, Qingchun, Cheng, De, Xing, Yinghui, Liang, Guoqiang, Wang, Peng, Zhang, Yanning
In this work, we construct a large-scale dataset for Ground-to-Aerial Person Search, named G2APS, which contains 31,770 images of 260,559 annotated bounding boxes for 2,644 identities appearing in both of the UAVs and ground surveillance cameras. To
Externí odkaz:
http://arxiv.org/abs/2308.12712
Autor:
Xing, Yinghui, Kong, Dexuan, Zhang, Shizhou, Chen, Geng, Ran, Lingyan, Wang, Peng, Zhang, Yanning
Camouflaged object detection (COD), aiming to segment camouflaged objects which exhibit similar patterns with the background, is a challenging task. Most existing works are dedicated to establishing specialized modules to identify camouflaged objects
Externí odkaz:
http://arxiv.org/abs/2307.10685
Multispectral pedestrian detection is an important task for many around-the-clock applications, since the visible and thermal modalities can provide complementary information especially under low light conditions. Most of the available multispectral
Externí odkaz:
http://arxiv.org/abs/2302.00290
Autor:
Xing, Yinghui1 (AUTHOR) xingyh0125@163.com, Wang, Fuyun2 (AUTHOR) wangfylxg@163.com, Zhang, Miaomiao3 (AUTHOR) mmzhang@cau.edu.cn, Li, Li2 (AUTHOR) sxaulili@sxau.edu.cn, Zhao, Ercheng1 (AUTHOR) eczhao@126.com
Publikováno v:
Agronomy. Aug2024, Vol. 14 Issue 8, p1809. 12p.
Autor:
Xing, Yinghui, Wu, Qirui, Cheng, De, Zhang, Shizhou, Liang, Guoqiang, Wang, Peng, Zhang, Yanning
Publikováno v:
IEEE Transactions on Multimedia 2023
With the emergence of large pre-trained vison-language model like CLIP, transferable representations can be adapted to a wide range of downstream tasks via prompt tuning. Prompt tuning tries to probe the beneficial information for downstream tasks fr
Externí odkaz:
http://arxiv.org/abs/2208.08340