Zobrazeno 1 - 10
of 43
pro vyhledávání: '"Jieying Zheng"'
Publikováno v:
IET Image Processing, Vol 18, Iss 4, Pp 914-925 (2024)
Abstract Video‐based emotion recognition has been a long‐standing research topic for computer scientists and psychiatrists. In contrast to traditional discrete emotional models, emotion recognition based on continuous emotional models can better
Externí odkaz:
https://doaj.org/article/9b5fb798f95d45e08bb23be88d852450
Publikováno v:
IEEE Access, Vol 8, Pp 146754-146769 (2020)
Face sketch synthesis for photos is an applied research topic and it is critical for criminal investigation. However, sketch synthesis remains some challenges because of the blur and artifacts in the generated face sketches. To mitigate these problem
Externí odkaz:
https://doaj.org/article/e26bca1860524592a365c0eb79622707
Publikováno v:
IEEE Access, Vol 7, Pp 8646-8659 (2019)
This paper proposes a learning-based image interpolation method based on weighted direct nonlinear regression. It attempts to learn the nonlinear relationship between the low-resolution patches and their corresponding high-resolution patches by using
Externí odkaz:
https://doaj.org/article/6f6784b558a441138704c4dbc46e4258
Publikováno v:
IEEE Access, Vol 7, Pp 8508-8518 (2019)
Person re-identification has gradually become a popular research topic in many fields such as security, criminal investigation, and video analysis. This paper aims to learn a discriminative and robust spatial–temporal representation for video-based
Externí odkaz:
https://doaj.org/article/31e82dcae7e5470892fbaad77227d73c
Publikováno v:
IEEE Access, Vol 7, Pp 122684-122696 (2019)
Recently, person re-identification has become one of the research hotspots in the field of computer vision and has received extensive attention in the academic community. Inspired by the part-based research of image ReID, this paper presents a novel
Externí odkaz:
https://doaj.org/article/2dcca853fce94e86bc3a8db5f989b9eb
Publikováno v:
IEEE Access, Vol 7, Pp 154971-154985 (2019)
Face photo-sketch synthesis often suffers from many problems, such as low clarity, facial distortion, contents loss, texture missing and color inconsistency in the synthesized images. To alleviate these problems, we propose a feature Encoder Guided G
Externí odkaz:
https://doaj.org/article/215435f6fdf2400cad1342b42bbcb7c9
Publikováno v:
Organic & Biomolecular Chemistry. 20:339-344
An efficient method to construct isoindolo[2,1-b]isoquinolin-5(7H)-ones via a Rh(iii)-catalyzed direct C–H oxidative annulation of isoquinolones with allyl alcohols has been developed.
Diabetes is a common complication that happened in pregnant women, and it often leads to many serious consequences for fetuses and gravidas. Accurate diagnosis of gestational diabetes mellitus (GDM) is the key to providing prompt and precise treatmen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::57e49db347ba4b31b609c68f1d3c86ef
https://doi.org/10.21203/rs.3.rs-2461259/v1
https://doi.org/10.21203/rs.3.rs-2461259/v1
Publikováno v:
2022 IEEE International Conference on Image Processing (ICIP).
Publikováno v:
Applied Intelligence. 52:3559-3576
Many existing low-light image enhancement methods produce unnatural, low-contrast and color-distorted results. This paper presents a non-reference two-pathway network to solve the above problems. First, the frequency decomposition block is designed t