Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Chenjie Cao"'
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 45:2166-2180
We study the problem of shape generation in 3D mesh representation from a small number of color images with or without camera poses. While many previous works learn to hallucinate the shape directly from priors, we adopt to further improve the shape
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::757185a5d2e9a462ef66972bcbd28a4a
https://doi.org/10.1109/tpami.2022.3169735
https://doi.org/10.1109/tpami.2022.3169735
Publikováno v:
International Journal of Intelligent Systems. 37:2266-2292
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fa3db82296f51e276bc3ffa9029bd0a4
https://doi.org/10.1002/int.22773
https://doi.org/10.1002/int.22773
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 31:5178-5191
In this article, we propose a novel entropy and confidence-based undersampling boosting (ECUBoost) framework to solve imbalanced problems. The boosting-based ensemble is combined with a new undersampling method to improve the generalization performan
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::005501989bfee3376538a47827c02724
https://doi.org/10.1109/tnnls.2020.2964585
https://doi.org/10.1109/tnnls.2020.2964585
Publikováno v:
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7a803789122b0073bc30c27d0f17601c
https://doi.org/10.1109/icassp43922.2022.9747428
https://doi.org/10.1109/icassp43922.2022.9747428
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence.
We study the problem of shape generation in 3D mesh representation from a small number of color images with or without camera poses. While many previous works learn to hallucinate the shape directly from priors, we adopt to further improve the shape
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=pmid________::d684eba5614f5367623bff7a886dda91
https://pubmed.ncbi.nlm.nih.gov/35471867
https://pubmed.ncbi.nlm.nih.gov/35471867
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031197833
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e16ff0ab101d69ec9120714a9366c7f0
https://doi.org/10.1007/978-3-031-19784-0_18
https://doi.org/10.1007/978-3-031-19784-0_18
Autor:
Chenjie Cao, Zhe Wang
Publikováno v:
Neural Networks. 118:17-31
In this paper, a new ensemble framework named Cascade Interpolation Learning with Double subspaces and Confidence disturbance (CILDC) is designed for the imbalanced classification problems. Developed from the Cascade Forest of the Deep Forest which i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e3bf6eaf860ef71d821f75152d366ba1
https://doi.org/10.1016/j.neunet.2019.06.003
https://doi.org/10.1016/j.neunet.2019.06.003
Autor:
Chenjie Cao, Yanwei Fu
This paper studies the task of inpainting man-made scenes. It is very challenging due to the difficulty in preserving the visual patterns of images, such as edges, lines, and junctions. Especially, most previous works are failed to restore the object
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bd08ee57e5393ece4db63491c78963d7
http://arxiv.org/abs/2103.15087
http://arxiv.org/abs/2103.15087
Autor:
Yina Patterson, Xinrui Zhang, Yiming Cui, Qipeng Zhao, Yanting Li, He Zhou, Liang Xu, Cong Yu, Hai Hu, Bo Shi, Jun Zeng, Yiwen Zhang, Zuoyu Tian, Lu Li, Cong Yue, Weitang Liu, Qianqian Dong, Zhenzhong Lan, Junyi Li, Chenjie Cao, Zhe Zhao, Yechen Xu, Yin Tian, Kai Sun, Kyle Richardson, Xuanwei Zhang, Zhengliang Yang, Weijian Xie, Yudong Li, Shaoweihua Liu, Dian Yu, Rongzhao Wang
Publikováno v:
COLING
The advent of natural language understanding (NLU) benchmarks for English, such as GLUE and SuperGLUE allows new NLU models to be evaluated across a diverse set of tasks. These comprehensive benchmarks have facilitated a broad range of research and a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6d7ada4afc1e3375c67cb37afa4243ad
Publikováno v:
Applied Soft Computing. 71:1153-1160
Support vector data description (SVDD) is one of the most attractive methods in one-class classification (OCC), especially in solving problems in novelty detection. SVDD helps to deal with the classification with a large amount of target data and few
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0fbda5f0414f919c03912fc0c3c45bd6
https://doi.org/10.1016/j.asoc.2018.02.053
https://doi.org/10.1016/j.asoc.2018.02.053