Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Pengzhen Ren"'
Autor:
PENGZHEN REN1 pzhren@foxmail.com, YUN XIAO1 yxiao@nwu.edu.cn, XIAOJUN CHANG2 xiaojun.chang@rmit.edu.au, PO-YAO HUANG3 poyaoh@andrew.cmu.edu, ZHIHUI LI4 zhihuilics@gmail.com, GUPTA, BRIJ B.5, XIAOJIANG CHEN1, XIN WANG1
Publikováno v:
ACM Computing Surveys. Dec2022, Vol. 54 Issue 9, p1-40. 40p.
Autor:
PENGZHEN REN1 pzhren@foxmail.com, YUN XIAO1 yxiao@nwu.edu.cn, XIAOJUN CHANG2 cxj273@gmail.com, PO-YAO HUANG3, ZHIHUI LI4, XIAOJIANG CHEN1, XIN WANG1
Publikováno v:
ACM Computing Surveys. May2022, Vol. 54 Issue 4, p1-34. 34p.
Recently, a surge of interest in visual transformers is to reduce the computational cost by limiting the calculation of self-attention to a local window. Most current work uses a fixed single-scale window for modeling by default, ignoring the impact
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ab12b3d4b93032305712d2727cf6d8ed
http://arxiv.org/abs/2203.12856
http://arxiv.org/abs/2203.12856
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 31:3801-3813
In the real world, the duality of high-dimensional data is widespread. The coclustering method has been widely used because they can exploit the co-occurring structure between samples and features. In fact, most of the existing coclustering methods c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2c39d5106ebe80a69157634f46789921
https://doi.org/10.1109/tnnls.2019.2946329
https://doi.org/10.1109/tnnls.2019.2946329
Publikováno v:
Knowledge-Based Systems. 254:109623
In the field of computer vision, the use of pyramid features can significantly improve network performance. However, the misalignment of semantic information and the scale limitation of small-scale features lead to an imbalance of feature contributio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bdbe7de554ce231a754000d01eee17da
https://doi.org/10.1016/j.knosys.2022.109623
https://doi.org/10.1016/j.knosys.2022.109623
Publikováno v:
IJCAI
Person search has drawn increasing attention due to its real-world applications and research significance. Person search aims to find a probe person in a gallery of scene images with a wide range of applications, such as criminals search, multicamera
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7170e88e674bdfd7f2839ac7e1956929
https://doi.org/10.24963/ijcai.2021/613
https://doi.org/10.24963/ijcai.2021/613
Deep learning has made breakthroughs and substantial in many fields due to its powerful automatic representation capabilities. It has been proven that neural architecture design is crucial to the feature representation of data and the final performan
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::82412613700d256a561f5b8618eb17f3
https://hdl.handle.net/10453/154209
https://hdl.handle.net/10453/154209
Publikováno v:
AAAI
Spectral clustering has been widely adopted because it can mine structures between data clusters. The clustering performance of spectral clustering depends largely on the quality of the constructed affinity graph, especially when the data has noise.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::007bd1a98e2a5dcba5a5d072c75e1385
https://doi.org/10.1609/aaai.v33i01.33015482
https://doi.org/10.1609/aaai.v33i01.33015482
Scene graph is a structured representation of a scene that can clearly express the objects, attributes, and relationships between objects in the scene. As computer vision technology continues to develop, people are no longer satisfied with simply det
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9ae5e129e480b4424b0593c810f214ec
http://arxiv.org/abs/2104.01111
http://arxiv.org/abs/2104.01111
Publikováno v:
IJCAI
Multi-view clustering has played a vital role in real-world applications. It aims to cluster the data points into different groups by exploring complementary information of multi-view. A major challenge of this problem is how to learn the explicit cl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0a07d3b91c4daf094f02ad8339d2dd96
https://doi.org/10.24963/ijcai.2018/367
https://doi.org/10.24963/ijcai.2018/367