Výsledky vyhledávání - "Philip T. Jackson"

Not Half Bad: Exploring Half-Precision in Graph Convolutional Neural Networks

Autor: Boguslaw Obara, Andrew Stephen McGough, Amir Atapour-Abarghouei, Stephen Bonner, Philip T. Jackson, John Brennan

Publikováno v: IEEE BigData

With the growing significance of graphs as an effective representation of data in numerous applications, efficient graph analysis using modern machine learning is receiving a growing level of attention. Deep learning approaches often operate over the

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::80b69e699d8dec242875a434a1115dae
http://arxiv.org/abs/2010.12635

Zobrazit plný text záznamu

Camera Bias in a Fine Grained Classification Task

Autor: Philip T. Jackson, Boguslaw Obara, Christopher J. Holder, Ning Jia, Jon Stonehouse, Stephen Bonner

Publikováno v: IJCNN

We show that correlations between the camera used to acquire an image and the class label of that image can be exploited by convolutional neural networks (CNN), resulting in a model that “cheats” at an image classification task by recognizing whi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6a9da2ffd731a11358830ae2ffdd455a
http://arxiv.org/abs/2007.08574

Zobrazit plný text záznamu

Multi-Scale Segmentation and Surface Fitting for Measuring 3-D Macular Holes

Autor: Amar Vijai Nasrulloh, Boguslaw Obara, Philip T. Jackson, Maged Habib, Caspar Geenen, Chris G. Willcocks, David H. W. Steel

Publikováno v: IEEE transactions on medical imaging, 2018, Vol.37(2), pp.580-589 [Peer Reviewed Journal]

Macular holes are blinding conditions where a hole develops in the central part of retina, resulting in reduced central vision. The prognosis and treatment options are related to a number of variables including the macular hole size and shape. High-r

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3f3fa99f5d8849461ed2f35269553de4
https://doi.org/10.1109/tmi.2017.2767908

Zobrazit plný text záznamu

Interactive GPU active contours for segmenting inhomogeneous objects

Autor: Boguslaw Obara, Carl J. Nelson, Chris G. Willcocks, Amar Vijai Nasrulloh, Philip T. Jackson

Publikováno v: Journal of real-time image processing, 2019, Vol.16(6), pp.2305-2318 [Peer Reviewed Journal]

We present a segmentation software package primarily targeting medical and biological applications, with a high level of visual feedback and several usability enhancements over existing packages. Specifically, we provide a substantially faster GPU im

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::88f8da77e1a8b43cb16561912022ff2a
http://dro.dur.ac.uk/23575/1/23575.pdf

Zobrazit plný text záznamu

Sequential graph-based extraction of curvilinear structures

Autor: Philip T. Jackson, Boguslaw Obara, Shuaa S. Alharbi, Haifa F. Alhasson, Chris G. Willcocks

Publikováno v: Signal, image and video processing, 2019, Vol.13(5), pp.941-949 [Peer Reviewed Journal]

In this paper, a new approach is proposed to extract an ordered sequence of curvilinear structures in images, capturing the largest and most influential paths first and then progressively extracting smaller paths until a prespecified size is reached.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::288acbc0df544791e38233a8abb1f5ec
https://doi.org/10.1007/s11760-019-01431-6

Zobrazit plný text záznamu

Phenotypic Profiling of High Throughput Imaging Screens with Generic Deep Convolutional Features

Autor: Yinhai Wang, Martin R. Brown, Hongming Chen, Thierry Dorval, Boguslaw Obara, Philip T. Jackson, Sinead Knight, Claus Bendtsen

Publikováno v: MVA

While deep learning has seen many recent applications to drug discovery, most have focused on predicting activity or toxicity directly from chemical structure. Phenotypic changes exhibited in cellular images are also indications of the mechanism of a

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5c873b7d2a0257790cd634f53a2b6293

Zobrazit plný text záznamu

Temporal neighbourhood aggregation: predicting future links in temporal graphs via recurrent variational graph convolutions

Autor: Philip T. Jackson, Georgios Theodoropoulos, Amir Atapour-Abarghouei, John Brennan, Andrew Stephen McGough, Stephen Bonner, Ibad Kureshi, Boguslaw Obara

Publikováno v: 2019 IEEE International Conference on Big Data (Big Data). Piscataway, NJ: IEEE, pp. 5336-5345
IEEE BigData

Graphs have become a crucial way to represent large, complex and often temporal datasets across a wide range of scientific disciplines. However, when graphs are used as input to machine learning models, this rich temporal information is frequently di

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::48f0732225a05ded0c93e9d10d5bd1cd
https://doi.org/10.1109/BigData47090.2019.9005545

Zobrazit plný text záznamu

Combining Mathematical Morphology and the Hilbert Transform for Fully Automatic Nuclei Detection in Fluorescence Microscopy

Autor: Carl J. Nelson, Philip T. Jackson, Boguslaw Obara

Publikováno v: Lecture Notes in Computer Science ISBN: 9783030208660
ISMM

Accurate and reliable nuclei identification is an essential part of quantification in microscopy. A range of mathematical and machine learning approaches are used but all methods have limitations. Such limitations include sensitivity to user paramete

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fd34b50989ada6832a844e682f1743b5
https://doi.org/10.1007/978-3-030-20867-7_41

Zobrazit plný text záznamu

Extracting 3D parametric curves from 2D images of Helical objects

Autor: Chris G. Willcocks, Carl J. Nelson, Boguslaw Obara, Philip T. Jackson

Publikováno v: IEEE transactions on pattern analysis and machine intelligence, 2016, Vol.39(9), pp.1757-1769 [Peer Reviewed Journal]

Helical objects occur in medicine, biology, cosmetics, nanotechnology, and engineering. Extracting a 3D parametric curve from a 2D image of a helical object has many practical applications, in particular being able to extract metrics such as tortuosi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::de7e7941c5e8f56ddd2101f1bc55f547
https://eprints.gla.ac.uk/165308/1/165308.pdf

Zobrazit plný text záznamu

Avoiding over-detection : towards combined object detection and counting

Autor: Boguslaw Obara, Philip T. Jackson

Publikováno v: (2017). Artificial intelligence and soft computing : 16th International Conference, ICAISC 2017, Zakopane, Poland, June 11-15, 2017. Proceedings. Part I. Cham: Springer, pp. 75-85, Lecture notes in computer science(10245)
Artificial Intelligence and Soft Computing ISBN: 9783319590622
ICAISC (1)

Existing object detection frameworks in the deep learning field generally over-detect objects, and use non-maximum suppression (NMS) to filter out excess detections, leaving one bounding box per object. This works well so long as the ground-truth bou

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0f1716353afe14cf87666f061bb4b638
https://doi.org/10.1007/978-3-319-59063-9_7

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání