Dissertation · 2014 · Open access
On-the-fly visual category search in web-scale image collections
Oxford University Research Archive (ORA) (University of Oxford) · Published 1 January 2014 · DOI 10.5287/ora-2zoj1qmky
In brief
“On-the-fly visual category search in web-scale image collections” is a 2014 dissertation by Ken Chatfield, published in Oxford University Research Archive (ORA) (University of Oxford). OpenAlex counts 0 citations as of 16 November 2026. It is open access: the full text is free to read at Oxford University Research Archive (ORA) (University of Oxford).
- Citations
- 0
- Authors
- 1
Abstract
This thesis tackles the problem of large-scale visual search for categories within large collections of images. Given a textual description of a visual category, such as 'car' or 'person', the objective is to retrieve images containing that category from the corpus quickly and accurately, and without the need for auxiliary meta-data or, crucially and in contrast to previous approaches, expensive pre-training. The general approach to identifying different visual categories within a dataset is to train classifiers over features extracted from a set of training images. The performance of such classifiers relies heavily on sufficiently discriminative image representations, and many methods have been proposed which involve the aggregating of local appearance features into rich bag-of-words encodings. We begin by conducting a comprehensive evaluation of the latest such encodings, identifying best-of-breed practices for training powerful visual models using these representations. We also contrast these methods with the latest breed of Convolutional Network (ConvNet) based features, thus developing a state-of-the-art architecture for large-scale image classification. Following this, we explore how a standard classification pipeline can be adapted for use in a real-time setting. One of the major issues, particularly with bag-of-words based methods, is the high dimensionality of the encodings, which causes ranking over large datasets to be prohibitively expensive. We therefore assess different methods for compressing such features, and further propose a novel cascade approach to ranking which both reduces ranking time and improves retrieval performance. Finally, we explore the problem of training visual models on-the-fly, making use of visual data dynamically collected from the web to train classifiers on demand. On this basis, we develop a novel GPU architecture for on-the-fly visual category search which is capable of retrieving previously unknown categories over unannonated datasets of millions of images in just a few seconds.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Chatfield, K. (2014). On-the-fly visual category search in web-scale image collections. Oxford University Research Archive (ORA) (University of Oxford). https://doi.org/10.5287/ora-2zoj1qmky
MLA 9
Chatfield, Ken. “On-the-fly visual category search in web-scale image collections.” Oxford University Research Archive (ORA) (University of Oxford), 2014. https://doi.org/10.5287/ora-2zoj1qmky.
Chicago
Chatfield, Ken. 2014. “On-the-fly visual category search in web-scale image collections.” Oxford University Research Archive (ORA) (University of Oxford). https://doi.org/10.5287/ora-2zoj1qmky.
Harvard
Chatfield, K. (2014) ‘On-the-fly visual category search in web-scale image collections’, Oxford University Research Archive (ORA) (University of Oxford). doi:10.5287/ora-2zoj1qmky.
IEEE
K. Chatfield, “On-the-fly visual category search in web-scale image collections,” Oxford University Research Archive (ORA) (University of Oxford), 2014, doi: 10.5287/ora-2zoj1qmky.
BibTeX
@phdthesis{chatfield2014visual,
title = {{On-the-fly visual category search in web-scale image collections}},
author = {Chatfield, Ken},
year = {2014},
doi = {10.5287/ora-2zoj1qmky},
url = {https://doi.org/10.5287/ora-2zoj1qmky}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- bag-of-words
- local appearance features
- image classification
- real-time classification
- dimensionality reduction
- GPU architecture
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Chatfield, K. (2014). On-the-fly visual category search in web-scale image collections. Oxford University Research Archive (ORA) (University of Oxford). https://doi.org/10.5287/ora-2zoj1qmky
How many times has this paper been cited?
0 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access: read the free full text at Oxford University Research Archive (ORA) (University of Oxford).
Who wrote this paper?
Ken Chatfield.
What is the DOI of this paper?
10.5287/ora-2zoj1qmky. The permanent link is https://doi.org/10.5287/ora-2zoj1qmky.
Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.