ORCID Profile
0000-0003-2313-8603
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
In Research Link Australia (RLA), "Research Topics" refer to ANZSRC FOR and SEO codes. These topics are either sourced from ANZSRC FOR and SEO codes listed in researchers' related grants or generated by a large language model (LLM) based on their publications.
Information Systems | Information Systems Not Elsewhere Classified | Information Storage, Retrieval And Management | Curatorial and Related Studies | Computation Theory And Mathematics Not Elsewhere Classified | Other Artificial Intelligence | Computer Software Not Elsewhere Classified | Computational Linguistics | Learning, Memory, Cognition And Language | Health Information Systems (Incl. Surveillance) | Linguistic Processes (Incl. Speech Production And Comprehension) | Library and Information Studies | Text Processing | Mathematical Logic, Set Theory, Lattices And Combinatorics | Museum Studies | Cognitive Science | Data Security | Global Information Systems
Computer software and services not elsewhere classified | Library and related information services | Information services not elsewhere classified | Information processing services | Application tools and system utilities | Application packages | Evaluation of health outcomes | Heritage not elsewhere classified | Education across cultures | Communication services not elsewhere classified | Behavioural and cognitive sciences |
Publisher: Springer International Publishing
Date: 2014
Publisher: IEEE
Date: 09-2017
Publisher: Springer International Publishing
Date: 2016
Publisher: ACM
Date: 12-09-2018
Publisher: ACM
Date: 26-10-2010
Publisher: Springer Berlin Heidelberg
Date: 2000
DOI: 10.1007/10722280_31
Publisher: IEEE Comput. Soc
Date: 2002
Publisher: IEEE
Date: 10-2012
Publisher: Springer Berlin Heidelberg
Date: 2011
Publisher: Elsevier BV
Date: 10-2008
Publisher: Engineering and Technology Publishing
Date: 08-2011
Publisher: International Journal for Digital Art History
Date: 2019
Publisher: IEEE
Date: 04-2010
Publisher: IGI Global
Date: 04-2011
Abstract: This case discusses the architecture and application of privacy and trust issues in the Connected Mobility Digital Ecosystem (CMDE) for the University of Wollongong’s main c us community. The authors describe four mobile location-sensitive, context-aware applications (app(s)) that are designed for iPhones: a public transport passenger information app a route-based private vehicle car-pooling app an on-c us location-based social networking app and a virtual art-gallery tour guide app. These apps are location-based and designed to augment user interactions within their physical environments. In addition, location data provided by the apps can be used to create value-added services and optimize overall system performance. The authors characterize this socio-technical system as a digital ecosystem and explain its salient features. Using the University of Wollongong’s c us and surrounds as the ecosystem’s community for the case studies, the authors present the architectures of these four applications (apps) and address issues concerning privacy, location-identity and uniform standards developed by the Internet Engineering Task Force (IETF).
Publisher: Springer Nature Switzerland
Date: 2023
Publisher: ACM
Date: 12-11-2019
Publisher: World Scientific Pub Co Pte Lt
Date: 04-2008
DOI: 10.1142/S0129054108005723
Abstract: This paper presents the evaluation of a design and architecture for browsing and searching MPEG-7 images. Our approach is novel in that it exploits concept lattices for the representation and navigation of image content. Several concept lattices provide the foundation for the system (called IMAGE-SLEUTH) each representing a different search context, one for image shape, another for color and luminance, and a third for semantic content, namely image browsing based on a metadata ontology. The test collection used for our study is a sub-set of MPEG-7 images created from the popular The Sims 2™ game. The evaluation of the IMAGE-SLEUTH program is based on usability testing among 29 subjects. The results of the study are used to build an improved second generation program – IMAGE-SLEUTH2 – however these results also indicate that image navigation via a concept lattice is a highly successful interface paradigm. Our results provide general insights for interface design using concept lattices that will be of interest to any applied research and development using concept lattices.
Publisher: Springer Berlin Heidelberg
Date: 2008
Publisher: IEEE
Date: 11-2010
Publisher: ACM
Date: 27-10-2009
Publisher: Springer Berlin Heidelberg
Date: 2008
Publisher: IEEE
Date: 2002
Publisher: ACM
Date: 27-06-2020
Publisher: Informa UK Limited
Date: 06-2001
Publisher: Springer Berlin Heidelberg
Date: 2008
Publisher: Springer Berlin Heidelberg
Date: 1998
Publisher: Springer Science and Business Media LLC
Date: 09-06-2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2000
DOI: 10.1109/5254.846281
Publisher: Springer Science and Business Media LLC
Date: 04-11-2021
Publisher: IEEE
Date: 07-2020
Publisher: Informa UK Limited
Date: 11-2012
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-04-2023
DOI: 10.36227/TECHRXIV.20494851
Abstract: Omnidirectional Videos (or 360° videos) are widely used in Virtual Reality (VR) to facilitate immersive and interactive viewing experiences. However, the limited spatial resolution in 360° videos does not allow for each degree of view to be represented with adequate pixels, limiting the visual quality offered in the immersive experience. Deep learning Video Super-Resolution (VSR) techniques used for conventional videos could provide a promising software-based solution however, these techniques do not tackle the distortion present in equirectangular projections of 360° video signals. An additional obstacle is the limited 360° video datasets to study. To address these issues, this paper creates a novel 360° Video Dataset (360VDS) with a study of the extensibility of conventional VSR models to 360° videos. This paper further proposes a novel deep learning model for 360° Video Super-Resolution (360° VSR), called Spherical Signal Super-resolution with a Proportioned Optimisation (S3PO). S3PO adopts recurrent modelling with an attention mechanism, unbound from conventional VSR techniques like alignment. With a purpose-built feature extractor and a novel loss function addressing spherical distortion, S3PO outperforms most state-of-the-art conventional VSR models and 360° specific super-resolution models on 360° video datasets. A step-wise ablation study is presented to understand and demonstrate the impact of the chosen architectural subcomponents, targeted training and optimisation.
Publisher: Springer Berlin Heidelberg
Date: 1998
DOI: 10.1007/BFB0054908
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: MDPI AG
Date: 08-06-2023
DOI: 10.3390/APP13126941
Abstract: Crash fault tolerance describes the capability of a distributed system to maintain its proper function despite the occurrence of crashes or failures in one or more of its components. When a distributed system possesses crash fault tolerance, it can be further fortified to achieve Byzantine fault tolerance. Byzantine fault tolerance empowers a distributed system to establish consensus among participants, even when faced with faulty or malicious behavior. Consensus plays a critical role in various tasks, including determining the accurate value of a shared variable, electing a leader, or validating the integrity of a business transaction. Compared to crash fault tolerance, Byzantine fault tolerance instills greater trust because it enables consensus even in the presence of malicious entities. This paper focuses on the performance evaluation of two blockchain solutions that exhibit Byzantine fault tolerance, in contrast to a blockchain solution that demonstrates crash fault tolerance. Specifically, the paper investigates the additional performance requirements associated with the enhanced trust resulting from Byzantine fault tolerance in e-business trading on both national and transnational scales. We analyze the resources needed to operate a business-to-business/business-to-government (B2B/B2G) compliance framework in two distinct geographic scenarios. The first examines the national scale, using Denmark as an ex le, which is the eleventh largest European country by GDP. The second scenario considers the scale of the European Union (EU) with its 27 member states (plus the United Kingdom).
Publisher: ACM
Date: 28-10-2013
Publisher: Springer Berlin Heidelberg
Date: 2001
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-04-2023
DOI: 10.36227/TECHRXIV.20494851.V2
Abstract: Omnidirectional Videos (or 360° videos) are widely used in Virtual Reality (VR) to facilitate immersive and interactive viewing experiences. However, the limited spatial resolution in 360° videos does not allow for each degree of view to be represented with adequate pixels, limiting the visual quality offered in the immersive experience. Deep learning Video Super-Resolution (VSR) techniques used for conventional videos could provide a promising software-based solution however, these techniques do not tackle the distortion present in equirectangular projections of 360° video signals. An additional obstacle is the limited 360° video datasets to study. To address these issues, this paper creates a novel 360° Video Dataset (360VDS) with a study of the extensibility of conventional VSR models to 360° videos. This paper further proposes a novel deep learning model for 360° Video Super-Resolution (360° VSR), called Spherical Signal Super-resolution with a Proportioned Optimisation (S3PO). S3PO adopts recurrent modelling with an attention mechanism, unbound from conventional VSR techniques like alignment. With a purpose-built feature extractor and a novel loss function addressing spherical distortion, S3PO outperforms most state-of-the-art conventional VSR models and 360° specific super-resolution models on 360° video datasets. A step-wise ablation study is presented to understand and demonstrate the impact of the chosen architectural subcomponents, targeted training and optimisation.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 14-08-2023
DOI: 10.36227/TECHRXIV.23896986.V1
Abstract: Video super-resolution (VSR) is a prominent research topic in low-level computer vision, where deep learning technologies have played a significant role. The rapid progress in deep learning and its applications in VSR has led to a proliferation of tools and techniques in the literature. However, the usage of these methods is often not adequately explained, and decisions are primarily driven by quantitative improvements. Given the significance of VSR's potential influence across multiple domains, it is imperative to conduct a comprehensive analysis of the elements and deep learning methodologies employed in VSR research. This methodical analysis will facilitate the informed development of models tailored to specific application needs. In this paper, we present a comprehensive overview of deep learning-based video super-resolution models, investigating each component and discussing its implications. Furthermore, we provide a synopsis of key components and technologies employed by state-of-the-art and earlier VSR models. By elucidating the underlying methodologies and categorising them systematically, we identified trends, requirements, and challenges in the domain. As a first-of-its-kind comprehensive overview of deep learning-based VSR models, this work also establishes a multi-level taxonomy to guide current and future VSR research, enhancing the maturation and interpretation of VSR practices for various practical applications.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-04-2023
DOI: 10.36227/TECHRXIV.22591426.V1
Abstract: This paper presents a novel approach to video super-resolution (VSR) by focusing on the selection of input frames, a process critical to VSR. VSR methods typically rely on deep learning techniques, those that are able to learn features from a large dataset of low-resolution (LR) and corresponding high-resolution (HR) videos and generate high-quality HR frames from any new LR input frames using the learned features. However, these methods often use as input the immediate neighbouring frames to a given target frame without considering the importance and dynamics of the frames across the temporal dimension of a video. This work aims to address the limitations of the conventional sliding-window mechanisms by developing input frame selection algorithms. By dynamically selecting the most representative neighbouring frames based on content-aware selection measures, our proposed algorithms enable VSR models to extract more informative and accurate features that are better aligned with the target frame, leading to improved performance and higher-quality HR frames. Through an empirical study, we demonstrate that the proposed dynamic content-aware selection mechanism improves super-resolution results without any additional architectural overhead, offering a counter-intuitive yet effective alternative to the long-established trend of increasing architectural complexity to improve VSR results.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 23-08-2022
DOI: 10.36227/TECHRXIV.20494851.V1
Abstract: Omnidirectional Videos (or 360° videos) are widely used in Virtual Reality (VR) to facilitate immersive and interactive viewing experiences. However, the limited spatial resolution in 360° videos does not allow for each degree of view to be represented with adequate pixels, limiting the visual quality offered in the immersive experience. Deep learning Video Super-Resolution (VSR) techniques used for conventional videos could provide a promising software-based solution however, these techniques do not tackle the distortion present in equirecentagular projections of 360° video signals. An additional obstacle is the limited 360° video datasets to study. To address these issues, this paper creates a novel 360° Video Dataset (360VDS) with a study of the extensibility of conventional VSR models to 360° videos. This paper further proposes a novel deep learning model for 360° Video Super-Resolution (360° VSR), called Spherical Signal Super-resolution with Proportioned Optimisation (S3PO). S3PO adopts recurrent modelling with attention mechanism, unbound from conventional VSR techniques like alignment. With a purpose built feature extractor and a novel loss function addressing spherical distortion, S3PO outperforms most state-of-the-art conventional VSR models and 360° specific super-resolution models on 360° video datasets. A step-wise ablation study is presented to understand and demonstrate the impact of the chosen architectural sub-components, targeted training and optimisation.
Publisher: Springer Berlin Heidelberg
Date: 1999
Publisher: Springer Berlin Heidelberg
Date: 2005
DOI: 10.1007/11524564_20
Publisher: Elsevier BV
Date: 05-1999
Publisher: ACM
Date: 04-02-2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 14-08-2023
DOI: 10.36227/TECHRXIV.23896986
Abstract: Video super-resolution (VSR) is a prominent research topic in low-level computer vision, where deep learning technologies have played a significant role. The rapid progress in deep learning and its applications in VSR has led to a proliferation of tools and techniques in the literature. However, the usage of these methods is often not adequately explained, and decisions are primarily driven by quantitative improvements. Given the significance of VSR's potential influence across multiple domains, it is imperative to conduct a comprehensive analysis of the elements and deep learning methodologies employed in VSR research. This methodical analysis will facilitate the informed development of models tailored to specific application needs. In this paper, we present a comprehensive overview of deep learning-based video super-resolution models, investigating each component and discussing its implications. Furthermore, we provide a synopsis of key components and technologies employed by state-of-the-art and earlier VSR models. By elucidating the underlying methodologies and categorising them systematically, we identified trends, requirements, and challenges in the domain. As a first-of-its-kind comprehensive overview of deep learning-based VSR models, this work also establishes a multi-level taxonomy to guide current and future VSR research, enhancing the maturation and interpretation of VSR practices for various practical applications.
Publisher: Elsevier BV
Date: 07-2003
Publisher: Springer Berlin Heidelberg
Date: 2006
DOI: 10.1007/11787181_15
Publisher: Springer Berlin Heidelberg
Date: 2002
Publisher: Springer International Publishing
Date: 2015
Publisher: MDPI AG
Date: 20-07-2021
DOI: 10.3390/APP11146636
Abstract: Standardized approaches to relevance classification in information retrieval use generative statistical models to identify the presence or absence of certain topics that might make a document relevant to the searcher. These approaches have been used to better predict relevance on the basis of what the document is “about”, rather than a simple-minded analysis of the bag of words contained within the document. In more recent times, this idea has been extended by using pre-trained deep learning models and text representations, such as GloVe or BERT. These use an external corpus as a knowledge-base that conditions the model to help predict what a document is about. This paper adopts a hybrid approach that leverages the structure of knowledge embedded in a corpus. In particular, the paper reports on experiments where linked data triples (subject-predicate-object), constructed from natural language elements are derived from deep learning. These are evaluated as additional latent semantic features for a relevant document classifier in a customized news-feed website. The research is a synthesis of current thinking in deep learning models in NLP and information retrieval and the predicate structure used in semantic web research. Our experiments indicate that linked data triples increased the F-score of the baseline GloVe representations by 6% and show significant improvement over state-of-the art models, like BERT. The findings are tested and empirically validated on an experimental dataset and on two standardized pre-classified news sources, namely the Reuters and 20 News groups datasets.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2023
Publisher: Springer Berlin Heidelberg
Date: 2005
DOI: 10.1007/11528784_13
Publisher: IEEE
Date: 2002
Publisher: Springer Berlin Heidelberg
Date: 2000
Publisher: Springer Berlin Heidelberg
Date: 2006
DOI: 10.1007/11671404_20
Publisher: MDPI AG
Date: 26-06-2023
DOI: 10.20944/PREPRINTS202306.1738.V1
Abstract: The use of visual signals in horticulture has attracted significant attention and encompassed a wide range of data types such as 2D images, videos, hyperspectral images, and 3D point clouds. These visual signals have proven to be valuable in developing cutting-edge computer vision systems for various applications in horticulture, enabling plant growth monitoring, pest and disease detection, quality and yield estimation, and automated harvesting. However, unlike other sectors, developing deep learning computer vision systems for horticulture encounters unique challenges due to the limited availability of high-quality training and evaluation datasets necessary for deep learning models. This paper investigates the current status of vision systems and available data in order to identify the high-quality data requirements specific to horticultural applications. We analyse the impact of the quality of visual signals on the information content and features that can be extracted from these signals. To address the identified data quality requirements, we explore the usage of a deep learning-based super-resolution model for generative quality enhancement of visual signals. Furthermore, we discuss how these can be applied to meet the growing requirements around data quality for learning-based vision systems. We also present a detailed analysis of the competitive quality generated by the proposed solution compared to cost-intensive hardware-based alternatives. This work aims to guide the development of efficient computer vision models in horticulture by overcoming existing data challenges and paving a pathway forward for contemporary data acquisition.
Publisher: IEEE
Date: 2005
Publisher: Springer Berlin Heidelberg
Date: 2010
Publisher: Springer Berlin Heidelberg
Date: 2006
DOI: 10.1007/11671404_14
Publisher: Springer International Publishing
Date: 2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2021
Publisher: Springer Berlin Heidelberg
Date: 2001
Publisher: Springer Berlin Heidelberg
Date: 1999
Publisher: IEEE
Date: 06-2009
Publisher: IGI Global
Date: 2013
DOI: 10.4018/978-1-4666-3619-4.CH008
Abstract: This case discusses the architecture and application of privacy and trust issues in the Connected Mobility Digital Ecosystem (CMDE) for the University of Wollongong’s main c us community. The authors describe four mobile location-sensitive, context-aware applications (app(s)) that are designed for iPhones: a public transport passenger information app a route-based private vehicle car-pooling app an on-c us location-based social networking app and a virtual art-gallery tour guide app. These apps are location-based and designed to augment user interactions within their physical environments. In addition, location data provided by the apps can be used to create value-added services and optimize overall system performance. The authors characterize this socio-technical system as a digital ecosystem and explain its salient features. Using the University of Wollongong’s c us and surrounds as the ecosystem’s community for the case studies, the authors present the architectures of these four applications (apps) and address issues concerning privacy, location-identity and uniform standards developed by the Internet Engineering Task Force (IETF).
Publisher: Chapman and Hall/CRC
Date: 06-05-2009
Publisher: Springer Berlin Heidelberg
Date: 1999
Publisher: IEEE
Date: 11-2014
Publisher: Springer Berlin Heidelberg
Date: 2008
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 17-05-2023
DOI: 10.36227/TECHRXIV.21500235
Abstract: Recurrent Neural Networks (RNN) are widespread for Video Super-Resolution (VSR) because of their proven ability to learn spatiotemporal inter-dependencies across the temporal dimension. Despite RNN’s ability to propagate memory across longer sequences of frames, vanishing gradient and error accumulation remain major obstacles to unidirectional RNNs in VSR. Several bi-directional recurrent models are suggested in the literature to alleviate this issue however, these models are only applicable to offline use cases due to heavy demands for computational resources and the number of frames required per input. This paper proposes a novel unidirectional recurrent model for VSR, namely “Replenished Recurrency with Dual-Duct” (R2D2), that can be used in an online application setting. R2D2 incorporates a recurrent architecture with a sliding-window-based local alignment resulting in a recurrent hybrid architecture. It also uses a dual-duct residual network for concurrent and mutual refinement of local features along with global memory for full utilisation of the information available at each timest . With novel modelling and sophisticated optimisation, R2D2 demonstrates competitive performance and efficiency despite the lack of information available at each time-st compared to its offline (bi-directional) counterparts. Ablation analysis confirms the additive benefits of the proposed sub-components of R2D2 over baseline RNN models.The PyTorch-based code for the R2D2 model will be released at R2D2 GitRepo.
Publisher: Springer Berlin Heidelberg
Date: 2007
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2021
Publisher: IEEE
Date: 09-2007
DOI: 10.1109/DEXA.2007.59
Publisher: Springer Berlin Heidelberg
Date: 2007
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: Springer Berlin Heidelberg
Date: 2000
DOI: 10.1007/10722280_28
Publisher: Springer Berlin Heidelberg
Date: 1996
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-04-2023
DOI: 10.36227/TECHRXIV.22591426
Abstract: This paper presents a novel approach to video super-resolution (VSR) by focusing on the selection of input frames, a process critical to VSR. VSR methods typically rely on deep learning techniques, those that are able to learn features from a large dataset of low-resolution (LR) and corresponding high-resolution (HR) videos and generate high-quality HR frames from any new LR input frames using the learned features. However, these methods often use as input the immediate neighbouring frames to a given target frame without considering the importance and dynamics of the frames across the temporal dimension of a video. This work aims to address the limitations of the conventional sliding-window mechanisms by developing input frame selection algorithms. By dynamically selecting the most representative neighbouring frames based on content-aware selection measures, our proposed algorithms enable VSR models to extract more informative and accurate features that are better aligned with the target frame, leading to improved performance and higher-quality HR frames. Through an empirical study, we demonstrate that the proposed dynamic content-aware selection mechanism improves super-resolution results without any additional architectural overhead, offering a counter-intuitive yet effective alternative to the long-established trend of increasing architectural complexity to improve VSR results.
Publisher: Elsevier BV
Date: 02-2020
Publisher: Cambridge University Press (CUP)
Date: 03-1994
DOI: 10.1017/S0269888900006561
Abstract: The inheritance problem can be simply stated: for any instantiation of an inheritance network, say a specific hierarchy Γ, find a conclusion set for Γ. In other words, find out what is logically entailed by Γ. This can be done in two ways: either by defining a deductive or proof theoretic definition to determine what paths are entailed by a network or by translating the in idual links in the network to a more general nonmonotonic logic and using its model and proof theory to generate entailments that correspond to what one would expect from “viewing” the inheritance hierarchy. Two approaches to a solution to the inheritance problem structure this paper. The first is widely known as the “path-based” or “proof theoretic”, and the second, the “Model-based” or “model theoretic”. The two approaches result in both a different interpretation of default links as well as a variation in the entailment strategy for a solution to teh inheritance problem. In either case, the entailments produced need some intuitive interpretation, which can be either credulous or skeptical. The semantics of both skeptical and credulous inheritance reasoners are examined.
Publisher: Springer Berlin Heidelberg
Date: 2005
DOI: 10.1007/11524564_19
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-11-2022
DOI: 10.36227/TECHRXIV.21500235.V1
Abstract: This is an original research article entitled “Online Video Super-Resolution using Unidirectional Recurrent Model”. Considering the critical constraints around video frames and resource availability in an online setting, this paper presents a new unidirectional video super-resolution (VSR) model with a recurrent architecture specifically designed for online applications. Many recent works in the video super-resolution domain focus on improving the super-resolution quality at the cost of computationally intense and input-heavy bidirectional modelling. To alleviate these drawbacks, we propose the Replenished Recurrency with Dual-Duct (R2D2) model which adopts unidirectional architecture to fully utilise local features and global memory available at each timest . The two variants – R2D2 and R2D2-lite presented in the paper generate state-of-the-art super-resolution quality at significantly optimised efficiency. This is believed an important step forward in real-world applications-inspired research in the video super-resolution domain.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 17-05-2023
DOI: 10.36227/TECHRXIV.21500235.V2
Abstract: Recurrent Neural Networks (RNN) are widespread for Video Super-Resolution (VSR) because of their proven ability to learn spatiotemporal inter-dependencies across the temporal dimension. Despite RNN’s ability to propagate memory across longer sequences of frames, vanishing gradient and error accumulation remain major obstacles to unidirectional RNNs in VSR. Several bi-directional recurrent models are suggested in the literature to alleviate this issue however, these models are only applicable to offline use cases due to heavy demands for computational resources and the number of frames required per input. This paper proposes a novel unidirectional recurrent model for VSR, namely “Replenished Recurrency with Dual-Duct” (R2D2), that can be used in an online application setting. R2D2 incorporates a recurrent architecture with a sliding-window-based local alignment resulting in a recurrent hybrid architecture. It also uses a dual-duct residual network for concurrent and mutual refinement of local features along with global memory for full utilisation of the information available at each timest . With novel modelling and sophisticated optimisation, R2D2 demonstrates competitive performance and efficiency despite the lack of information available at each time-st compared to its offline (bi-directional) counterparts. Ablation analysis confirms the additive benefits of the proposed sub-components of R2D2 over baseline RNN models.The PyTorch-based code for the R2D2 model will be released at R2D2 GitRepo.
Publisher: Informa UK Limited
Date: 05-1998
Publisher: IEEE
Date: 07-2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 15-03-2022
Publisher: Informa UK Limited
Date: 03-2003
DOI: 10.1080/713827120
Publisher: Springer Science and Business Media LLC
Date: 28-06-2012
Location: United Kingdom of Great Britain and Northern Ireland
Start Date: 2003
End Date: 12-2005
Amount: $211,035.00
Funder: Australian Research Council
View Funded ActivityStart Date: 06-2004
End Date: 02-2008
Amount: $222,261.00
Funder: Australian Research Council
View Funded ActivityStart Date: 11-2003
End Date: 12-2004
Amount: $20,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 01-2004
End Date: 12-2006
Amount: $30,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 10-2008
End Date: 12-2012
Amount: $246,239.00
Funder: Australian Research Council
View Funded ActivityStart Date: 12-2003
End Date: 12-2004
Amount: $20,000.00
Funder: Australian Research Council
View Funded Activity