Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Zhenshan Tan"'
Publikováno v:
ISPRS International Journal of Geo-Information, Vol 13, Iss 10, p 347 (2024)
Improving the performance and reducing the training cost of road extraction models in the absence of samples is important for updating road maps. Despite the success of recent road extraction models on standard datasets, they often fail to perform wh
Externí odkaz:
https://doaj.org/article/b6be41b8c65044beaeafc59d83ee30d8
Publikováno v:
Journal of Imaging Science & Technology; Mar/Apr2024, Vol. 68 Issue 2, p1-11, 11p
Publikováno v:
Neural Networks. 152:434-449
Image-text bidirectional retrieval is a significant task within cross-modal learning field. The main issue lies on the jointly embedding learning and accurately measuring image-text matching score. Most prior works make use of either intra-modality m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6ae24abb5a46c2c9c3c6f4d97a3f974a
https://doi.org/10.1016/j.neunet.2022.05.008
https://doi.org/10.1016/j.neunet.2022.05.008
Autor:
Zhenshan Tan, Xiaodong Gu
Publikováno v:
Digital Signal Processing. 133:103841
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e0c311f0883469769b48c91988cb35f3
https://doi.org/10.1016/j.dsp.2022.103841
https://doi.org/10.1016/j.dsp.2022.103841
Autor:
Xiaodong Gu, Zhenshan Tan
Publikováno v:
Applied Intelligence. 51:5775-5792
Convolutional Neural Networks (CNNs) have played an important role in saliency detection. How to detect a salient object as a whole is a key issue. However, most existing learning-based methods are not accurate enough to detect salient objects in com
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0db615d8a332bddbb897a73eba4ed163
https://doi.org/10.1007/s10489-020-02150-z
https://doi.org/10.1007/s10489-020-02150-z
Autor:
Zhenshan Tan, Xiaodong Gu
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031159183
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8eee0d770a39528041df7752c020e544
https://doi.org/10.1007/978-3-031-15919-0_2
https://doi.org/10.1007/978-3-031-15919-0_2
Visual Dialog aims to answer multi-round, interactive questions based on the dialog history and image content. Existing methods either consider answer ranking and generating individually or only weakly capture the relation across the two tasks implic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ac23ca74cd2bc0bb8fa5b9e11771ef31
Autor:
Zhenshan Tan, Xiaodong Gu
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031159367
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::96050950c20916fdeacf95d9c71b7c40
https://doi.org/10.1007/978-3-031-15937-4_6
https://doi.org/10.1007/978-3-031-15937-4_6
Autor:
Zhenshan Tan, Xiaodong Gu
Publikováno v:
Knowledge-Based Systems. 252:109356
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::09176b238975433dd047fe603ef40ab1
https://doi.org/10.1016/j.knosys.2022.109356
https://doi.org/10.1016/j.knosys.2022.109356
Publikováno v:
Signal processing. Image communication
Color transfer in image processing usually suffers from misleading color mapping and loss of details. This paper presents a novel directive local color transfer method based on dynamic look-up table (D-DLT) to solve these problems in two steps. First
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::505c3bb76e9f08444d2df18a7366c92a
https://doi.org/10.1016/j.image.2019.06.010
https://doi.org/10.1016/j.image.2019.06.010