S
Suzanne Little
Researcher at Dublin City University
Publications - 105
Citations - 1340
Suzanne Little is an academic researcher from Dublin City University. The author has contributed to research in topics: Image retrieval & Semantic Web. The author has an hindex of 18, co-authored 98 publications receiving 1108 citations. Previous affiliations of Suzanne Little include Istituto di Scienza e Tecnologie dell'Informazione & Open University.
Papers
More filters
Proceedings ArticleDOI
Fully Convolutional Crowd Counting on Highly Congested Scenes
TL;DR: The state-of-the-art for crowd counting in high density scenes is advanced by further exploring the idea of a fully convolutional crowd counting model introduced by (Zhang et al., 2016), and a training set augmentation scheme that minimises redundancy among training samples to improve model generalisation and overall counting performance is developed.
Posted Content
ResnetCrowd: A Residual Deep Learning Architecture for Crowd Counting, Violent Behaviour Detection and Crowd Density Level Classification
TL;DR: Experiments show that a multi-task approach boosts individual task performance for all tasks and most notably for violent behaviour detection which receives a 9% boost in ROC curve AUC (Area under the curve).
Proceedings ArticleDOI
People, Penguins and Petri Dishes: Adapting Object Counting Models to New Visual Domains and Object Types Without Forgetting
TL;DR: In this article, a technique to adapt a CNN-based object counter to additional visual domains and object types while still preserving the original counting function is proposed, which is used to produce a singular patch-based counting regressor capable of counting various object types including people, vehicles, cell nuclei and wildlife.
Proceedings ArticleDOI
ResnetCrowd: A residual deep learning architecture for crowd counting, violent behaviour detection and crowd density level classification
TL;DR: This article proposed ResnetCrowd, a deep residual architecture for simultaneous crowd counting, violent behaviour detection and crowd density level classification, which achieved a 9% boost in ROC curve AUC (Area under the curve).
Book ChapterDOI
Dynamic Generation of Intelligent Multimedia Presentations through Semantic Inferencing
TL;DR: A system, based on this architecture, which was developed as a service to run over OAI archives - but is applicable to any repositories containing mixed-media resources described using Dublin Core, and which may be able to generate new knowledge by exposing previously unrecognized connections.