Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Hoang Ngan Le"'
HAtt-Flow: Hierarchical Attention-Flow Mechanism for Group-Activity Scene Graph Generation in Videos
Publikováno v:
Sensors, Vol 24, Iss 11, p 3372 (2024)
Group-activity scene graph (GASG) generation is a challenging task in computer vision, aiming to anticipate and describe relationships between subjects and objects in video sequences. Traditional video scene graph generation (VidSGG) methods focus on
Externí odkaz:
https://doaj.org/article/ef9797f768064c289ed8da20cbcc2866
Publikováno v:
International Journal of Customer Relationship Marketing and Management. 13:1-16
This study was conducted to investigate the relationship between corporate social responsibility and customers’ loyalty. The study first reviewed previous research and developed hypotheses related to the research survey data sets collected through
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::02ca693bb25f5891714b0fbf2ea26df0
https://doi.org/10.4018/ijcrmm.304909
https://doi.org/10.4018/ijcrmm.304909
Publikováno v:
International Journal of Computer Vision. 127:957-971
This paper presents a novel Subject-dependent Deep Aging Path (SDAP), which inherits the merits of both Generative Probabilistic Modeling and Inverse Reinforcement Learning to model the facial structures and the longitudinal face aging process of a g
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3dc2a77cebc1af8df5e35ff9404d655c
https://doi.org/10.1007/s11263-019-01165-5
https://doi.org/10.1007/s11263-019-01165-5
Publikováno v:
Medical Image Analysis
Medical Image Analysis, Elsevier, 2021, 73, pp.102193. ⟨10.1016/j.media.2021.102193⟩
Medical Image Analysis, 2021, 73, pp.102193. ⟨10.1016/j.media.2021.102193⟩
Medical Image Analysis, Elsevier, 2021, 73, pp.102193. ⟨10.1016/j.media.2021.102193⟩
Medical Image Analysis, 2021, 73, pp.102193. ⟨10.1016/j.media.2021.102193⟩
International audience; Deep reinforcement learning (DRL) augments the reinforcement learning framework, which learns a sequence of actions that maximizes the expected reward, with the representative power of deep neural networks. Recent works have d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0e1328a139924fce68068c25ec4fd659
https://pubmed.ncbi.nlm.nih.gov/34371440
https://pubmed.ncbi.nlm.nih.gov/34371440
Publikováno v:
BIOIMAGING
Medical image segmentation is one of the most challenging tasks in medical image analysis and has been widely developed for many clinical applications. Most of the existing metrics have been first designed for natural images and then extended to medi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ef524840806bcde564de90b5a209f3c4
Autor:
Khoa Luu, Thanh-Dat Truong, Chi Nhan Duong, Kyle Sadler, T. Hoang Ngan Le, Kha Gia Quach, Marios Savvides
Publikováno v:
Applications of Hybrid Metaheuristic Algorithms for Image Processing ISBN: 9783030409760
Active Contour (AC)-based segmentation has been widely used to solve many image processing problems, specially image segmentation. While these AC-based methods offer object shape constraints, they typically look for strong edges or statistical modeli
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b73a52b619d71e344a2ff5cc790ddafc
https://doi.org/10.1007/978-3-030-40977-7_11
https://doi.org/10.1007/978-3-030-40977-7_11
Publikováno v:
Pattern Recognition. 66:229-238
This paper presents a Grammar-aware Driver Parsing (GDP) algorithm, with deep features, to provide a novel driver behavior situational awareness system (DB-SAW). A deep model is first trained to extract highly discriminative features of the driver. T
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f4290a05baefc21a0af9e8f436c48125
https://doi.org/10.1016/j.patcog.2016.11.028
https://doi.org/10.1016/j.patcog.2016.11.028
Publikováno v:
Image and Vision Computing. 58:214-223
This paper presents a robust, fully automatic and semi self-training system to detect and segment facial beard/moustache simultaneously in challenging facial images. Based on the observation that some certain facial areas, e.g. cheeks, do not typical
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c7bbeaf4e9908503c1ad80b5edb16f09
https://doi.org/10.1016/j.imavis.2016.07.009
https://doi.org/10.1016/j.imavis.2016.07.009
A novel Shape Constrained Feature-based Active Contour model for lips/mouth segmentation in the wild
Autor:
Marios Savvides, T. Hoang Ngan Le
Publikováno v:
Pattern Recognition. 54:23-33
In this paper, we propose a novel joint formulation of feature-based active contour (FAC) and prior shape constraints (CS) for lips/mouth segmentation in the wild. Our proposed SC-FAC model is able to robustly segment the lips/mouth that belongs to a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::21c294836bcdab5ed41ee12200e15b77
https://doi.org/10.1016/j.patcog.2015.11.009
https://doi.org/10.1016/j.patcog.2015.11.009