Zobrazeno 1 - 10
of 163
pro vyhledávání: '"Wei-Chih Hung"'
Autor:
Yijun Li, Yu-Ting Chang, Deng Cai, Yi-Hsuan Tsai, Wei-Chih Hung, Wenqing Chu, Ming-Hsuan Yang
Publikováno v:
International Journal of Computer Vision. 129:2663-2679
Caricature is an artistic drawing created to abstract or exaggerate facial features of a person. Rendering visually pleasing caricatures is a difficult task that requires professional skills, and thus it is of great interest to design a method to aut
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eda62417047c6676dd902b5dfa047715
https://doi.org/10.1007/s11263-021-01489-1
https://doi.org/10.1007/s11263-021-01489-1
Autor:
Yue-Jing He1 yuejing@ncut.edu.tw, Wei-Chih Hung1 roger1427@yahoo.com.tw, Zhe-Ping Lai1 h50908y@yahoo.com.tw
Publikováno v:
Sensors (14248220). Feb2016, Vol. 16 Issue 2, p192. 13p.
Autor:
Wei-Chih Hung1 philipx9a9@hotmail.com, Jong-Yuh Cherng1 chejyc@ccu.edu.tw
Publikováno v:
Polymers (20734360). 2015, Vol. 7 Issue 10, p2131-S5. 20p. 3 Color Photographs, 2 Diagrams, 10 Graphs.
Autor:
Huang, Cheng-Liang, Hou, Jiun Liang, Pan, Chung-Long, Huang, Chi-Yuen, Peng, Chun-Wei, Wei, Chih-Hung, Huang, Yi-Hong
Publikováno v:
In Journal of Alloys and Compounds 2008 450(1):359-363
Publikováno v:
WACV
Hashing has attracted attention in recent years due to the rapid growth of image and video data on the web. Benefiting from recent advances in deep learning, deep supervised hashing has achieved promising results for image retrieval. However, existin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3d8fb14fb11b5af85c704039dfb9b71a
https://doi.org/10.1109/wacv45572.2020.9093487
https://doi.org/10.1109/wacv45572.2020.9093487
Autor:
Wei-Chih Hung, Yi-Hsuan Tsai, Ming-Hsuan Yang, Qiaosong Wang, Yu-Ting Chang, Robinson Piramuthu
Publikováno v:
CVPR
Existing weakly-supervised semantic segmentation methods using image-level annotations typically rely on initial responses to locate object regions. However, such response maps generated by the classification network usually focus on discriminative o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8851e4545120463707831232268829a5
Publikováno v:
CVPR
Reconstructing 3D models from 2D images is one of the fundamental problems in computer vision. In this work, we propose a deep learning technique for 3D object reconstruction from a single image. Contrary to recent works that either use 3D supervisio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b97373a3f4578f84ce53c43f1e6c1523
Autor:
Yue-Jing He, Wei-Chih Hung
Publikováno v:
IEEE Sensors Journal. 18:178-184
This paper presents a novel geometrical structure of NPs on optical fiber for high-sensitivity biochemical sensors, which comprised a single-mode fiber and a cylindrical metallic nanoparticle array. The sensor performed detection through a metallic n
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dd7ce59a6f262ac15822052615b64b93
https://doi.org/10.1109/jsen.2017.2767562
https://doi.org/10.1109/jsen.2017.2767562
Publikováno v:
CVPR
Parts provide a good intermediate representation of objects that is robust with respect to the camera, pose and appearance variations. Existing works on part segmentation is dominated by supervised approaches that rely on large amounts of manual anno
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c0b2209c19dcaf95f75c7a204b031de4
https://doi.org/10.1109/cvpr.2019.00096
https://doi.org/10.1109/cvpr.2019.00096
Autor:
Maneesh Singh, Wei-Chih Hung, Yi-Hsuan Tsai, Han-Kai Hsu, Ming-Hsuan Yang, Hung-Yu Tseng, Chun-Han Yao
Publikováno v:
WACV
Recent deep learning methods for object detection rely on a large amount of bounding box annotations. Collecting these annotations is laborious and costly, yet supervised models do not generalize well when testing on images from a different distribut
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ce6f2ade39a97b80bdd8a6fd888c9d52