Zobrazeno 1 - 10
of 118
pro vyhledávání: '"Xuequan Lu"'
Publikováno v:
Computational Visual Media, Vol 9, Iss 4, Pp 657-685 (2023)
Abstract In the past ten years, research on face recognition has shifted to using 3D facial surfaces, as 3D geometric information provides more discriminative features. This comprehensive survey reviews 3D face recognition techniques developed in the
Externí odkaz:
https://doaj.org/article/497e7c47e2ef4d7688dd2531b29d0a7e
Publikováno v:
Computational Visual Media, Vol 9, Iss 2, Pp 249-263 (2023)
Abstract While a popular representation of 3D data, point clouds may contain noise and need filtering before use. Existing point cloud filtering methods either cannot preserve sharp features or result in uneven point distributions in the filtered out
Externí odkaz:
https://doaj.org/article/c802737c86c549c4895f875200258d08
Publikováno v:
IEEE Access, Vol 9, Pp 65140-65149 (2021)
Impressive progress has been recently witnessed on deep unsupervised clustering and feature disentanglement. In this paper, we propose a novel method on top of one recent architecture with a novel explanation of Gaussian mixture model (GMM) membershi
Externí odkaz:
https://doaj.org/article/80b428e8a49d45938c01486b60571e71
Publikováno v:
Computational Visual Media, Vol 6, Iss 2, Pp 135-145 (2020)
Abstract In this paper we address the problem of geometric multi-model fitting using a few weakly annotated data points, which has been little studied so far. In weak annotating (WA), most manual annotations are supposed to be correct yet inevitably
Externí odkaz:
https://doaj.org/article/f7cdfbfe0761476ea52f429f6c5c8d1a
Publikováno v:
IEEE Access, Vol 8, Pp 159077-159088 (2020)
Well-known corner or local extrema feature based detectors such as FAST and DoG have achieved noticeable successes. However, detecting keypoints in the presence of blur has remained to be an unresolved issue. As a matter of fact, various kinds of blu
Externí odkaz:
https://doaj.org/article/ed2a0d003510421c9d2998f18c93b092
Publikováno v:
IEEE Access, Vol 7, Pp 84967-84979 (2019)
Indoor image features extraction is a fundamental problem in multiple fields such as image processing, pattern recognition, robotics, and so on. Nevertheless, most of the existing feature extraction methods, which extract features based on pixels, co
Externí odkaz:
https://doaj.org/article/e3fee1b6516644168d9b17bd6e9d6e53
Publikováno v:
International Journal of Computer Games Technology, Vol 2013 (2013)
We present a novel model called A2R—“Adaptive-AR”—based on a well-known continuum-based model called AR Aw and Rascle (2000) for the simulation of vehicle traffic flows. However, in the standard continuum-based model, vehicles usually follow
Externí odkaz:
https://doaj.org/article/6f64542d285c4bf7bd50140bd7498fc2
Autor:
Qianyu Zhou, Zhengyang Feng, Qiqi Gu, Jiangmiao Pang, Guangliang Cheng, Xuequan Lu, Jianping Shi, Lizhuang Ma
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 33:804-817
Unsupervised domain adaptation (UDA) aims to adapt a model of the labeled source domain to an unlabeled target domain. Existing UDA-based semantic segmentation approaches always reduce the domain shifts in pixel level, feature level, and output level
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2e7f23317e66f804ab050438fbe32a02
https://doi.org/10.1109/tcsvt.2022.3206476
https://doi.org/10.1109/tcsvt.2022.3206476
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. :1-14
Domain adaptation aims to bridge the domain shifts between the source and the target domain. These shifts may span different dimensions such as fog, rainfall, etc. However, recent methods typically do not consider explicit prior knowledge about the d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::588adc2048851e6bbbb61bbcd13f6a9e
https://doi.org/10.1109/tpami.2023.3238727
https://doi.org/10.1109/tpami.2023.3238727
Publikováno v:
IEEE Transactions on Multimedia. :1-14
For pursuing accurate skeleton-based action recognition, most prior methods use the strategy of combining Graph Convolution Networks (GCNs) with attention-based methods in a serial way. However, they regard the human skeleton as a complete graph, res
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d6f21d91f5b45dd85a0ec0f8a7020738
https://doi.org/10.1109/tmm.2023.3239751
https://doi.org/10.1109/tmm.2023.3239751