A
Anthony Dick
Researcher at University of Adelaide
Publications - 132
Citations - 7884
Anthony Dick is an academic researcher from University of Adelaide. The author has contributed to research in topics: Question answering & Video tracking. The author has an hindex of 39, co-authored 131 publications receiving 7037 citations. Previous affiliations of Anthony Dick include University of Cambridge.
Papers
More filters
Proceedings ArticleDOI
A fast, modular scene understanding system using context-aware object detection
TL;DR: The use of the semantic space is proposed to improve specific out-of-the-box object detectors and an update model to take the evidence from different detection into account in the semantic segmentation process.
Book ChapterDOI
Finding camera overlap in large surveillance networks
TL;DR: This paper describes the design and deployment of an algorithm called exclusion that is specifically aimed at finding correspondence between regions in cameras for large camera networks, and investigates its performance and accuracy over this network.
Journal ArticleDOI
Online Metric-Weighted Linear Representations for Robust Visual Tracking
TL;DR: It is shown that online distance metric learning significantly improves the robustness of the tracker, especially on those sequences exhibiting drastic appearance changes, and design a time-weighted reservoir sampling method in order to bound growth in the number of training samples.
Posted Content
Image Captioning and Visual Question Answering Based on Attributes and External Knowledge
TL;DR: In this paper, a visual question answering model was proposed that combines an internal representation of the content of an image with information extracted from a general knowledge base to answer a broad range of image-based questions.
Proceedings ArticleDOI
Middleware for video surveillance networks
Henry Detmold,Anthony Dick,Katrina Falkner,David S. Munro,Anton van den Hengel,Ronald Morrison +5 more
TL;DR: This paper introduces middleware supporting both computation and communication in automated video surveillance networks based on the Blackboard architectural style, providing scalability, availability and the ability to integrate separately developed surveillance services.