loading
Documents

Research.Publish.Connect.

Affiliation

University of Bristol, United Kingdom
Context (please use complete words only)
Field
Sort by

37 Papers

A Fine-grained Perspective onto Object Interactions from First-person Views

Author: Dima Damen

Affiliation: University of Bristol, United Kingdom

Digital Object Identifier: 10.5220/0008345900110013

Proceedings of VISIGRAPP 2019, ISBN: 978-989-758-354-4

Collapse Button Quick Abstract
Traditionally, action understanding has been limited to assigning one out of a pre-selected set of labels to a trimmed video sequence. This talk goes beyond traditional action recognition to fine-grained understand of daily object interactions. The talk will discuss works that attempt to understand ‘when’ an object interaction takes place, including ‘when’ it can be considered completed, ‘which’ semantic labels can describe the interactions, ‘how’ the interaction can be described (or captioned) and ‘who’ is better when contrasting people perform the same interaction. Potentials and limitations of current deep architectures to solve for fine-grained object interaction understanding will be discussed. The talk will focus on the first-person viewpoint –captured using wearable cameras- as it offers a unique perspective onto objects during interactions.

Exhaustive Testing of Trader-agents in Realistically Dynamic Continuous Double Auction Markets: AA Does Not Dominate

Topics: Multi-Agent Systems; Industrial Applications of AI; Agent Models and Architectures; Simulation; Economic Agent Models; Intelligent Auctions and Markets

Author: Dave Cliff

Affiliation: Department of Computer Science University of Bristol, Bristol BS8 1UB and U.K

Digital Object Identifier: 10.5220/0007382802240236

Proceedings of ICAART 2019, ISBN: 978-989-758-350-6

Collapse Button Quick Abstract
We analyse results from over 3.4million detailed market-trading simulation sessions which collectively confirm an unexpected result: in markets with dynamically varying supply and demand, the best-performing automated adaptive auction-market trading-agent currently known in the AI/Agents literature, i.e. Vytelingum’s Adaptive-Aggressive (AA) strategy, can be routinely out-performed by simpler trading strategies. AA is the most recent in a series of AI trading-agent strategies proposed by various researchers over the past twenty years: research papers contributing major steps in this evolution of strategies have been published at IJCAI, in the Artificial Intelligence journal, and at AAMAS. The innovative step taken here is to brute-force exhaustively evaluate AA in market environments that are in various ways more realistic, closer to real-world financial markets, than the simple constrained abstract experimental evaluations routinely used in the prior academic AI/Agents research literature. We conclude that AA can indeed appear dominant when tested only against other AI-based trading agents in the highly simplified market scenarios that have become the methodological norm in the trading-agents academic research literature, but much of that success seems to be because AA was designed with exactly those simplified experimental markets in mind. As soon as we put AA in scenarios closer to real-world markets, modify it to fit those markets accordingly, and exhaustively test it against simpler trading agents, AA’s dominance simply disappears.
Collapse Button Related Ontology Subjects/Areas/Topics (20)
Agent Models and Architectures

Economic Agent Models

Multi-Agent Systems

Agents

Enterprise Information Systems

Operational Research

Artificial Intelligence

Industrial Applications of AI

Simulation

Artificial Intelligence and Decision Support Systems

Information Systems Analysis and Specification

Soft Computing

Bioinformatics

Knowledge Engineering and Ontology Development

Software Engineering

Biomedical Engineering

Knowledge-Based Systems

Symbolic Systems
Distributed and Mobile Software Systems

Methodologies and Technologies

Detection and Recognition of Painted Road Surface Markings

Topics: Video Analysis; Classification; Image Understanding

Authors: Jack Greenhalgh and Majid Mirmehdi

Affiliation: University of Bristol, United Kingdom

Digital Object Identifier: 10.5220/0005273501300138

Proceedings of ICPRAM 2015, ISBN: 978-989-758-076-5

Collapse Button Quick Abstract
A method for the automatic detection and recognition of text and symbols painted on the road surface is presented. Candidate regions are detected as maximally stable extremal regions (MSER) in a frame which has been transformed into an inverse perspective mapping (IPM) image, showing the road surface with the effects of perspective distortion removed. Detected candidates are then sorted into words and symbols, before they are interpreted using separate recognition stages. Symbol-based road markings are recognised using histogram of oriented gradient (HOG) features and support vector machines (SVM). Text-based road signs are recognised using a third-party optical character recognition (OCR) package, after application of a perspective correction stage. Matching of regions between frames, and temporal fusion of results is used to improve performance. The proposed method is validated using a data-set of videos, and achieves F-measures of 0.85 for text characters and 0.91 for symbols.
Collapse Button Related Ontology Subjects/Areas/Topics (9)
Applications

Image and Video Analysis

Software Engineering

Classification

Image Understanding

Theory and Methods

Computer Vision, Visualization and Computer Graphics

Pattern Recognition

Video Analysis

Using Inertial Data to Enhance Image Segmentation - Knowing Camera Orientation Can Improve Segmentation of Outdoor Scenes

Topics: Segmentation and Grouping; Machine Learning Technologies for Vision; Color and Texture Analyses; Categorization and Scene Understanding; Vision for Robotics

Authors: Osian Haines , David Bull and J. F. Burn

Affiliation: University of Bristol, United Kingdom

Digital Object Identifier: 10.5220/0005274000210032

Proceedings of VISAPP 2015/VISIGRAPP, ISBN: 978-989-758-090-1

Collapse Button Quick Abstract
In the context of semantic image segmentation, we show that knowledge of world-centric camera orientation (from an inertial sensor) can be used to improve classification accuracy. This works because certain structural classes (such as the ground) tend to appear in certain positions relative to the viewer. We show that orientation information is useful in conjunction with typical image-based features, and that fusing the two results in substantially better classification accuracy than either alone – we observed an increase from 61% to 71% classification accuracy, over the six classes in our test set, when orientation information was added. The method is applied to segmentation using both points and lines, and we also show that combining points with lines further improves accuracy. This work is done towards our intended goal of visually guided locomotion for either an autonomous robot or human.
Collapse Button Related Ontology Subjects/Areas/Topics (8)
Applications

Image and Video Analysis

Segmentation and Grouping

Color and Texture Analyses

Pattern Recognition

Software Engineering
Computer Vision, Visualization and Computer Graphics

Robotics

Why Robots Failed - Demonstrating the Superiority of Multiple-order Trading Agents in Experimental Human-agent Financial Markets

Topics: Economic Agent Models; Auctions and Markets

Author: Marco De Luca

Affiliation: University of Bristol, United Kingdom

Digital Object Identifier: 10.5220/0005203100440053

Proceedings of ICAART 2015, ISBN: 978-989-758-073-4

Collapse Button Quick Abstract
In the past decade there has been a rapid growth of the use of adaptive automated trading systems, commonly referred to in the finance industry as ``robot traders'': AI applications replacing highly-paid human traders in the global financial markets. The academic roots of this industry-changing deployment of AI technologies can be traced back to research published by a team of researchers at IBM at IJCAI 2001, which was subsequently replicated and extended by De Luca and Cliff at IJCAI 2011 and ICAART 2011. Here, we focus on the order management policy enforced by Open Exchange (OpEx), the open source algorithmic trading system designed by De Luca, for both human and robot traders: while humans are allowed to manage multiple orders simultaneously, robots only deal with one order at the time. We hypothesise that such unbalance may have strongly influenced the victory of human traders over robot traders, reported in past studies by De Luca et al., and by Cartlidge and Cliff. We employed OpEx to implement a multiple-order policy for robots as well as humans, and ran several human vs. robot trading experiments. Using aggregated market metrics and time analysis, we reached two important conclusions. First, we demonstrated that, in mixed human-robot markets, robots dealing multiple simultaneous orders consistently outperform robots dealing one order at a time. And second, we showed that while human traders outperform single-order robot traders under specific circumstances, multiple-order robot traders are never outperformed by human traders. We thus conclude that the performance of robot traders in a human-robot mixed market is strongly influenced by the order management policy they employ.
Collapse Button Related Ontology Subjects/Areas/Topics (4)
Agents

Auctions and Markets

Economic Agent Models
Artificial Intelligence

Neuron Dynamics of Two-compartment Traub Model for Hardware-based Emulation

Topics: Computational Neuroscience; Neuroinformatics and Bioinformatics; Neural Network Hardware Implementation and Applications

Authors: Juan Carlos Moctezuma , Jose Luis Nunez-Yanez and Joseph P. McGeehan

Affiliation: University of Bristol, United Kingdom

Digital Object Identifier: 10.5220/0005089500850093

Proceedings of NCTA 2014/IJCCI, ISBN: 978-989-758-054-3

Collapse Button Quick Abstract
The two-compartment Pinsky and Rinzel version of the Traub model offers a suitable solution for hardware-based emulation, since it has a good trade-off between biophysical accuracy and computational resources. Many applications based on conductance-based models require a proper characterization of the neuron behaviour in terms of its parameters, such as tuning firing parameters, changing parameters during learning processes, replication and analysis of neuron recordings, etc. This work presents a study of the dynamics of such model especially suitable for hardware-based development. The morphology of the neuron is taken into account while the analysis focuses primarily on the relation between the firing/bursting properties and the relevant parameters of the model, such as current applied and morphology of the cell. Two different applied currents were considered: short duration and long steady. Seven different types of burst patterns were detected and analysed. The transformation process of the membrane voltage when a long steady current varies was classified into five stages. Finally, examples of neuron recording replication using the present methodology are developed.
Collapse Button Related Ontology Subjects/Areas/Topics (19)
Artificial Intelligence

Methodologies and Methods

Pattern Recognition

Biomedical Engineering

Neural Network Hardware Implementation and Applications

Physiological Computing Systems

Biomedical Signal Processing

Neural Networks

Sensor Networks

Computational Intelligence

Neurocomputing

Signal Processing

Computational Neuroscience

Neuroinformatics and Bioinformatics

Soft Computing

Health Engineering and Technology Applications

Neurotechnology, Electronics and Informatics

Theory and Methods
Human-Computer Interaction

Text Line Aggregation

Topics: Classification; Image Understanding; Object Recognition; Character Recognition

Authors: Christopher Beck 1 , Alan Broun 2 , Majid Mirmehdi 1 , Tony Pipe 2 and Chris Melhuish 2

Affiliations: 1 University of Bristol, United Kingdom , 2 University of the West of England, United Kingdom

Digital Object Identifier: 10.5220/0004817903930401

Proceedings of ICPRAM 2014, ISBN: 978-989-758-018-5

Collapse Button Quick Abstract
We present a new approach to text line aggregation that can work as both a line formation stage for a myriad of text segmentation methods (over all orientations) and as an extra level of filtering to remove false text candidates. The proposed method is centred on the processing of candidate text components based on local and global measures. We use orientation histograms to build an understanding of paragraphs, and filter noise and construct lines based on the discovery of prominent orientations. Paragraphs are then reduced to seed components and lines are reconstructed around these components. We demonstrate results for text aggregation on the ICDAR 2003 Robust Reading Competition data, and also present results on our own more complex data set.
Collapse Button Related Ontology Subjects/Areas/Topics (9)
Applications

Computer Vision, Visualization and Computer Graphics

Pattern Recognition

Character Recognition

Image Understanding

Software Engineering

Classification

Object Recognition

Theory and Methods

Trading Experiments using Financial Agents in a Simulated Cloud Computing Commodity Market

Topics: Economic Agent Models; Cloud Computing; Auctions and Markets

Author: John Cartlidge

Affiliation: University of Bristol, United Kingdom

Digital Object Identifier: 10.5220/0004925303110317

Proceedings of ICAART 2014, ISBN: 978-989-758-016-1

Collapse Button Quick Abstract
In September 2012, Amazon, the leading Infrastructure as a Service (IaaS) provider, launched a secondary marketplace venue for users to buy and sell cloud resources between themselves—the Amazon EC2 Reserved Instance Marketplace (ARIM). ARIM is designed to encourage users to purchase more long-term reserved instances, thus generating more stable demand for the provider and additional revenue through commission on sales. In this paper, we model ARIM using a multi-agent simulation model populated with zero-intelligence plus (ZIP) financial trading agents. We demonstrate that ARIM offers a new opportunity for market makers (MMs) to profit from buying and selling resources, but suggest that this opportunity may be fleeting. We also demonstrate that altering the market mechanism from a retail market (where only sellers post offers; similar to ARIM) to a continuous double auction (where both buyers and sellers post offers) can result in higher sale prices and therefore higher commissions. Since IaaS is a multi-billion dollar industry and currently the fastest growing segment of the cloud computing market, we therefore suggest that Amazon may profit from altering the mechanism of ARIM to enable buyers to post bids.
Collapse Button Related Ontology Subjects/Areas/Topics (7)
Agents

Cloud Computing

Databases and Data Security

Artificial Intelligence

Data Engineering

Economic Agent Models
Auctions and Markets

Comparison of Cloud Middleware Protocols and Subscription Network Topologies using CReST, the Cloud Research Simulation Toolkit - The Three Truths of Cloud Computing are: Hardware Fails, Software has Bugs, and People Make Mistakes

Topics: Cloud Computing Architecture; Cloud Ilities (Scalability, Availability, Reliability)

Authors: John Cartlidge and Dave Cliff

Affiliation: University of Bristol, United Kingdom

Digital Object Identifier: 10.5220/0004377500580068

Proceedings of CLOSER 2013, ISBN: 978-989-8565-52-5

Collapse Button Quick Abstract
We introduce the Cloud Research Simulation Toolkit (CReST), a new cloud computing simulation tool designed to enable cloud providers to research and test their systems before release. We compare CReST with other known cloud simulation tools and demonstrate the utility of CReST by evaluating different distributed middleware protocols and associated subscription network topologies for robustness and reliability. Our results extend previous work and demonstrate that the published literature contains inaccuracies. CReST has been released as open-source under a Creative Commons license on SourceForge, with the intention that it can be used and extended by the cloud computing research community.
Collapse Button Related Ontology Subjects/Areas/Topics (5)
Cloud Computing

Cloud Computing Enabling Technology

Fundamentals
Cloud Computing Architecture

Cloud Ilities (Scalability, Availability, Reliability)

Topological Map Building and Path Estimation Using Global-appearance Image Descriptors

Topics: Image Processing; Mobile Robots and Autonomous Systems

Authors: Francisco Amoros 1 , Luis Paya 1 , Oscar Reinoso 2 , Walterio Mayol-Cuevas 3 and Andrew Calway 3

Affiliations: 1 Miguel Hernandez University, Spain , 2 Miguel Hernández University, Spain , 3 University of Bristol, United Kingdom

Digital Object Identifier: 10.5220/0004485203850392

Proceedings of ICINCO 2013, ISBN: 978-989-8565-71-6

Collapse Button Quick Abstract
Visual-based navigation has been a source of numerous researches in the field of mobile robotics. In this paper we present a topological map building and localization algorithm using wide-angle scenes. Global-appearance descriptors are used in order to optimally represent the visual information. First, we build a topological graph that represents the navigation environment. Each node of the graph is a different position within the area, and it is composed of a collection of images that covers the complete field of view. We use the information provided by a camera that is mounted on the mobile robot when it travels along some routes between the nodes in the graph. With this aim, we estimate the relative position of each node using the visual information stored. Once the map is built, we propose a localization system that is able to estimate the location of the mobile not only in the nodes but also on intermediate positions using the visual information. The approach has been evaluated and shows good performance in real indoor scenarios under realistic illumination conditions.
Collapse Button Related Ontology Subjects/Areas/Topics (4)
Image Processing

Mobile Robots and Autonomous Systems

Robotics and Automation
Informatics in Control, Automation and Robotics

Topic(s):

Filter listed results, by

Publication date

From:
To:
Author
Locate Author in list below
Data pager
Data pager
1234567
 Page 1 of 7, items 1 to 10 of 61.
Add Author(s) to filter:
Conference
Locate Conference in list below
Data pager
Data pager
12
 Page 1 of 2, items 1 to 10 of 12.
Add Conference(s) to filter:

- Science and Technology Publications, Lda.
RESOURCES

Proceedings

Papers

Authors

Ontology

CONTACTS

Science and Technology Publications, Lda
Avenida de S. Francisco Xavier, Lote 7 Cv. C,
2900-616 Setúbal, Portugal.

Phone: +351 265 520 185
Fax: +351 265 520 186
Email: info@scitepress.org

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic