Zobrazeno 1 - 10
of 179
pro vyhledávání: '"Hefei Ling"'
Autor:
Yulin Peng, Yingchun Luo, Junyi Yan, Wenjuan Li, Yimin Liao, Lingyu Yan, Hefei Ling, Can Long
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-12 (2024)
Abstract This study aims at suggesting an end-to-end algorithm based on a U-net-optimized generative adversarial network to predict anterior neck lower jaw angles (ANLJA), which are employed to define fetal head posture (FHP) during nuchal translucen
Externí odkaz:
https://doaj.org/article/deffc59ef56b4fa2960bbc75343f4272
Publikováno v:
IEEE Access, Vol 7, Pp 36489-36499 (2019)
Recently, the convolutional neural network (CNN)-based hashing method has achieved its promising performance for image retrieval. However, tackling the discrepancy between quantization error minimization and discriminability maximization of the netwo
Externí odkaz:
https://doaj.org/article/fe07fbdceb4d49bc84f664ba77586fc1
Publikováno v:
IEEE Access, Vol 7, Pp 55159-55168 (2019)
Discriminative feature embedding is of essential importance in the field of large scale face recognition. In this paper, we propose a self residual attention-based convolutional neural network (SRANet) for discriminative face feature embedding, which
Externí odkaz:
https://doaj.org/article/f6705372af774eb0a2c0eecd97335029
Publikováno v:
IEEE Access, Vol 6, Pp 57583-57596 (2018)
This paper proposes a novel spatial-temporal deep neural network (STDNN) that is applied to multi-view gait recognition. The STDNN comprises a temporal feature network (TFN) and a spatial feature network (SFN). In TFN, a feature sub-network is adopte
Externí odkaz:
https://doaj.org/article/2f7ec073e1114ca09a063a9cdf19a6c2
Publikováno v:
IET Computer Vision, Vol 11, Iss 6, Pp 479-487 (2017)
In existing local and global consistency (LGC) framework, the cost functions related to classifying functions adopt the sum of each row of weight matrix as an important factor. Some of these classifying functions are successfully applied to saliency
Externí odkaz:
https://doaj.org/article/5287e57f349441c4820ae3445464a6e7
Publikováno v:
International Journal of Computational Intelligence Systems, Vol 8, Iss 4 (2015)
Currently, researches on content based image copy detection mainly focus on robust feature extraction. However, most of existing approaches use only a single feature to represent an image for copy detection, which is often insufficient to characteriz
Externí odkaz:
https://doaj.org/article/722ee031e3d54b9cb768bd62468aad4c
Autor:
Runsheng Wang, Yuxuan Shi, Hefei Ling, Zongyi Li, Ping Li, Boyuan Liu, Hanqing Zheng, Qian Wang
Publikováno v:
IEEE Transactions on Biometrics, Behavior, and Identity Science. 5:183-195
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7b66337e9e143046fde49afe68ff1734
https://doi.org/10.1109/tbiom.2023.3244206
https://doi.org/10.1109/tbiom.2023.3244206
Publikováno v:
IEEE Transactions on Cognitive and Developmental Systems. 14:892-901
Few-shot learning aims at heuristically resolving new tasks with limited labeled data; most of the existing approaches are affected by knowledge learned from similar experiences. However, inter-class barriers and new samples insufficiency limit the t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d057af144309b4b2a8ee567395fb9d0d
https://doi.org/10.1109/tcds.2021.3075280
https://doi.org/10.1109/tcds.2021.3075280
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:1527-1535
Person re-identifcation (Re-ID) based on unsupervised domain adaptation (UDA) aims to transfer the pre-trained model from one labeled source domain to an unlabeled target domain. Existing methods tackle this problem by using clustering methods to gen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9453f714e49aa4c9aeefbc16f473572f
https://doi.org/10.1609/aaai.v36i2.20043
https://doi.org/10.1609/aaai.v36i2.20043
Publikováno v:
Neurocomputing. 486:237-249
Occluded person re-identification is a challenging task since the available data often suffers from information incompleteness and spatial misalignment. Most state-of-the-art occluded models rely on the external model to provide additional semantic i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f686dab984ec28c7cb127ef6ee512c50
https://doi.org/10.1016/j.neucom.2021.11.038
https://doi.org/10.1016/j.neucom.2021.11.038