Adrian Muscat

Prof. Adrian Muscat

orcid

Research Focus & Metrics

Academic Career Length

28Years (1999-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 February 2016 in Journal of Artificial Intelligence Research
Verified
Journal Article
Open access
PDF file
RBRaffaella Bernardi
Raffaella Bernardi
RCRuket Cakici
Ruket Cakici
DEDesmond Elliott
Desmond Elliott
AEAykut Erdem
Aykut Erdem
EEErkut Erdem
Erkut Erdem
BPBarbara Plank
Barbara Plank
Automatic description generation from natural images is a challenging problem that has recently received a large amount of interest from the computer vision and natural language processing communities. In this survey, we classify the existing approaches based on how they conceptualize this problem, viz., models that cast description as either generation problem or as a retrieval problem over a visual or multimodal representational space. We provide a detailed review of existing models, highlighting their advantages and disadvantages. Moreover, we give an overview of the benchmark image datasets and the evaluation measures that have been developed to assess the quality of machine-generated image descriptions. Finally we extrapolate future directions in the area of automatic image description generation.

17 March 2020 in Research in Transportation Business & Management
Verified
Journal Article
Closed access
Maria AttardMaria Attard
Maria Attard
MCMichael P.J. Camilleri
Michael P.J. Camilleri
AMAdrian Muscat
Adrian Muscat

15 December 2021 in PLOS ONE
Verified
Journal Article
Open access
PDF file
MTMarc Tanti
Marc Tanti
CBCamille Berruyer
Camille Berruyer
PTPaul Tafforeau
Paul Tafforeau
AMAdrian Muscat
Adrian Muscat
RFReuben Farrugia
Reuben Farrugia
JBJohann A. Briffa
Johann A. Briffa
Propagation Phase Contrast Synchrotron Microtomography (PPC-SRμCT) is the gold standard for non-invasive and non-destructive access to internal structures of archaeological remains. In this analysis, the virtual specimen needs to be segmented to separate different parts or materials, a process that normally requires considerable human effort. In the Automated SEgmentation of Microtomography Imaging (ASEMI) project, we developed a tool to automatically segment these volumetric images, using manually segmented samples to tune and train a machine learning model. For a set of four specimens of ancient Egyptian animal mummies we achieve an overall accuracy of 94–98% when compared with manually segmented slices, approaching the results of off-the-shelf commercial software using deep learning (97–99%) at much lower complexity. A qualitative analysis of the segmented output shows that our results are close in terms of usability to those from deep learning, justifying the use of these techniques.

1 August 2017
Verified
Conference Paper
Closed access
RBRaffaella Bernardi
Raffaella Bernardi
RCRuket Cakici
Ruket Cakici
DEDesmond Elliott
Desmond Elliott
AEAykut Erdem
Aykut Erdem
EEErkut Erdem
Erkut Erdem
BPBarbara Plank
Barbara Plank
Automatic image description generation is a challenging problem that has recently received a large amount of interest from the computer vision and natural language processing communities. In this survey, we classify the known approaches based on how they conceptualise this problem and provide a review of existing models, highlighting their advantages and disadvantages. Moreover, we give an overview of the benchmark image-text datasets and the evaluation measures that have been developed to assess the quality of machine-generated descriptions. Finally we explore future directions in the area of automatic image description.

1 January 2001
Verified
Conference Paper
Closed access
AMAdrian Muscat
Adrian Muscat

30 September 2019 in Physical Review Accelerators and Beams
Verified
Journal Article
Open access
PDF file
GAGabriella Azzopardi
Gabriella Azzopardi
BSBelen Salvachua
Belen Salvachua
GVGianluca Valentino
Gianluca Valentino
SRStefano Redaelli
Stefano Redaelli
AMAdrian Muscat
Adrian Muscat
The Large Hadron Collider has a complex collimation system installed to protect its sensitive equipment from normal and abnormal beam losses. The collimators are set around the beam following a multistage transverse setting hierarchy. The insertion position of each collimator is established using beam-based alignment techniques to determine the local beam position and rms beam size at each collimator. During previous years, collimator alignments were performed semiautomatically, with collimation experts present to oversee and control the alignment. During run II, a new fully automatic alignment tool was developed and used for collimator alignments throughout 2018. This paper discusses the improvements on the alignment software to automate it using machine learning, whilst focusing on the operational results obtained when testing the new software in the LHC. The alignment tests were conducted with both proton and ion beams, and angular alignments were performed with proton beams. This upgraded software successfully decreased the alignment time by a factor of 3 and made the results more reproducible, which is particularly important when performing angular alignments.