Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Haozhe Wu"'
Publikováno v:
AI Open, Vol 3, Iss , Pp 35-39 (2022)
The aim of human motion modeling is to understand human behaviors and create reasonable human motion like real people given different priors. With the development of deep learning, researchers tend to leverage data-driven methods to improve the perfo
Externí odkaz:
https://doaj.org/article/0fedd31af141430b849321c32a2f4eab
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d69ec917272c5d8664eb22a1057a3456
https://doi.org/10.1109/icassp49357.2023.10095304
https://doi.org/10.1109/icassp49357.2023.10095304
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5b3bbd675ca295f11dd892c9f05dbeaf
https://doi.org/10.1109/icassp49357.2023.10095200
https://doi.org/10.1109/icassp49357.2023.10095200
This work aims to provide a deep-learning solution for the motion interpolation task. Previous studies solve it with geometric weight functions. Some other works propose neural networks for different problem settings with consecutive pose sequences a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7a1382e5ddc6802fda5807c8a788dc78
Autor:
Zixuan Wang, Jia Jia, Haozhe Wu, Junliang Xing, Jinghe Cai, Fanbo Meng, Guowen Chen, Yanfeng Wang
Publikováno v:
Proceedings of the 30th ACM International Conference on Multimedia.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0d31ace1b71b00d2b242a38692896bb4
https://doi.org/10.1145/3503161.3548090
https://doi.org/10.1145/3503161.3548090
Publikováno v:
Proceedings of the 29th ACM International Conference on Multimedia.
People talk with diversified styles. For one piece of speech, different talking styles exhibit significant differences in the facial and head pose movements. For example, the "excited" style usually talks with the mouth wide open, while the "solemn"
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b210a66f139f54897a441a42665badb2
https://doi.org/10.1145/3474085.3475280
https://doi.org/10.1145/3474085.3475280
Autor:
Haozhe Wu, Yong Gao, Gaofeng Guo, Gao Chong, Xin Zhao, En Li, Yang Qiu, Huimin Ma, Tu Yihang, Lin Qin, Jiawei Long, Ji Li, Yunpeng Zhang
Publikováno v:
The Review of scientific instruments. 92(9)
This paper introduces an application of the time-domain gating technique in water content measurement of gas–liquid two-phase flow. According to the principle that water and gas have different absorption effects on microwaves, a sensor with transmi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::973fd22d4f9c38882e2cc72cf79a6970
https://pubmed.ncbi.nlm.nih.gov/34598526
https://pubmed.ncbi.nlm.nih.gov/34598526
Publikováno v:
ACM Multimedia
Dance and music are two highly correlated artistic forms. Synthesizing dance motions has attracted much attention recently. Most previous works conduct music-to-dance synthesis via directly music to human skeleton keypoints mapping. Meanwhile, human
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::93047cfbbddab7c3460f734a47a12d98
http://arxiv.org/abs/2009.07637
http://arxiv.org/abs/2009.07637
Publikováno v:
ICASSP
Facial expression and identity are two independent yet intertwined components for representing a face. For facial expression recognition, identity can contaminate the training procedure by providing tangled but irrelevant information. In this paper,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0ef5bdbcef1f01b1c9d021f82614779e
https://doi.org/10.1109/icassp40776.2020.9053608
https://doi.org/10.1109/icassp40776.2020.9053608
Autor:
Lingxi Xie, Tianyu Zhang, Hengheng Zhang, Haozhe Wu, Zijie Zhuang, Qi Tian, Longhui Wei, Haizhou Ai
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030586096
ECCV (12)
ECCV (12)
The fundamental difficulty in person re-identification (ReID) lies in learning the correspondence among individual cameras. It strongly demands costly inter-camera annotations, yet the trained models are not guaranteed to transfer well to previously
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::95b7e8df067b39bb7503a2b79883e8a6
https://doi.org/10.1007/978-3-030-58610-2_9
https://doi.org/10.1007/978-3-030-58610-2_9