Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Zequn, Qin"'
Publikováno v:
ACM Transactions on Multimedia Computing, Communications, and Applications. 19:1-23
Gait recognition has a rapid development in recent years. However, current gait recognition focuses primarily on ideal laboratory scenes, leaving the gait in the wild unexplored. One of the main reasons is the difficulty of collecting in-the-wild gai
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a286febcbf514f003228555289d3ef92
https://doi.org/10.1145/3517199
https://doi.org/10.1145/3517199
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 44:6011-6023
Dynamic routing networks, aimed at finding the best routing paths in the networks, have achieved significant improvements to neural networks in terms of accuracy and efficiency. In this paper, we see dynamic routing networks in a fresh light, formula
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::07dd0f0e436c30919d5c88bd1957404e
https://doi.org/10.1109/tpami.2021.3084680
https://doi.org/10.1109/tpami.2021.3084680
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 33:1066-1078
Many CNN-based segmentation methods have been applied in lane marking detection recently and gain excellent success for a strong ability in modeling semantic information. Although the accuracy of lane line prediction is getting better and better, lan
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::269bc61c8192f337abdf853c10dcd00f
https://doi.org/10.1109/tnnls.2020.3039675
https://doi.org/10.1109/tnnls.2020.3039675
Publikováno v:
IEEE Transactions on Industrial Electronics. 68:1684-1694
Dimensionality reduction has attracted much research interest in the past few decades. Existing dimensionality reduction methods like linear discriminant analysis and principal component analysis have achieved promising performance, but the single an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::887c1e089b0d942296c642671d25768f
https://doi.org/10.1109/tie.2020.2969072
https://doi.org/10.1109/tie.2020.2969072
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d9d6bcaa013a93a6ad4ad8b6fd8cce92
https://doi.org/10.1109/iccv48922.2021.00458
https://doi.org/10.1109/iccv48922.2021.00458
Publikováno v:
IEEE Transactions on Image Processing. :1-1
Gait recognition aims at identifying the pedestrians at a long distance by their biometric gait patterns. It is inherently challenging due to the various covariates and the properties of silhouettes (textureless and colorless), which result in two ki
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fccf0373f5b91a42310254061013dc0f
https://doi.org/10.1109/tip.2022.3164543
https://doi.org/10.1109/tip.2022.3164543
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585853
ECCV (24)
ECCV (24)
Modern methods mainly regard lane detection as a problem of pixel-wise segmentation, which is struggling to address the problem of challenging scenarios and speed. Inspired by human perception, the recognition of lanes under severe occlusion and extr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ba1dee21e1e2ccbd7f412bf3f90b9caa
https://doi.org/10.1007/978-3-030-58586-0_17
https://doi.org/10.1007/978-3-030-58586-0_17
Publikováno v:
IEEE transactions on neural networks and learning systems. 30(4)
Spectral clustering has been widely used in various aspects, especially the machine learning fields. Clustering with similarity matrix and low-dimensional representation of data is the main reason of its promising performance shown in spectral cluste
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e47c9540eb726c258a3296e2ca88e11b
https://pubmed.ncbi.nlm.nih.gov/30130239
https://pubmed.ncbi.nlm.nih.gov/30130239
Publikováno v:
IJCAI
Scopus-Elsevier
Scopus-Elsevier
Representing high-volume and high-order data is an essential problem, especially in machine learning field. Although existing two-dimensional (2D) discriminant analysis achieves promising performance, the single and linear projection features make it
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2b210daaf184e9ec9e7e475858d63c24
https://doi.org/10.24963/ijcai.2017/408
https://doi.org/10.24963/ijcai.2017/408