Zobrazeno 1 - 10
of 48
pro vyhledávání: '"Miao, Yunqi"'
Although diffusion models are rising as a powerful solution for blind face restoration, they are criticized for two problems: 1) slow training and inference speed, and 2) failure in preserving identity and recovering fine-grained facial details. In t
Externí odkaz:
http://arxiv.org/abs/2403.12760
Unsupervised person re-identification (ReID) aims to train a feature extractor for identity retrieval without exploiting identity labels. Due to the blind trust in imperfect clustering results, the learning is inevitably misled by unreliable pseudo l
Externí odkaz:
http://arxiv.org/abs/2211.11921
Near infrared (NIR) to Visible (VIS) face matching is challenging due to the significant domain gaps as well as a lack of sufficient data for cross-modality model training. To overcome this problem, we propose a novel method for paired NIR-VIS facial
Externí odkaz:
http://arxiv.org/abs/2211.06408
Visible-infrared person re-identification (VI-ReID) has been challenging due to the existence of large discrepancies between visible and infrared modalities. Most pioneering approaches reduce intra-class variations and inter-modality discrepancies by
Externí odkaz:
http://arxiv.org/abs/2201.03859
Publikováno v:
In International Journal of Pediatric Otorhinolaryngology April 2024 179
While the performance of crowd counting via deep learning has been improved dramatically in the recent years, it remains an ingrained problem due to cluttered backgrounds and varying scales of people within an image. In this paper, we propose a Shall
Externí odkaz:
http://arxiv.org/abs/2006.09853
Publikováno v:
In Information Fusion March 2023 91:396-411
Publikováno v:
In Neurocomputing July 2023
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Hao, Yu, Jiang, Menglu, Miao, Yunqi, Li, Xu, Hou, Can, Zhang, Xiaofan, Chen, Hui, Zhong, Xiaorong, Li, Jiayuan *
Publikováno v:
In Obesity Research & Clinical Practice September-October 2021 15(5):439-448