no code implementations • 5 Apr 2023 • Osman Tursun, Simon Denman, Sridha Sridharan, Clinton Fookes
We proposed a template-based image captioning approach for context modelling to create text-based contextual information from the heatmap and input data.
Explainable Artificial Intelligence (XAI) Image Captioning +2
1 code implementation • 5 Jul 2022 • Osman Tursun, Simon Denman, Sridha Sridharan, Clinton Fookes
High-quality saliency maps are essential in several machine learning application areas including explainable AI and weakly supervised object detection and segmentation.
no code implementations • 15 Apr 2021 • Osman Tursun, Simon Denman, Sridha Sridharan, Clinton Fookes
However, R-MAC suffers in the presence of background clutter/trivial regions and scale variance, and discards important spatial information.
no code implementations • 8 Feb 2021 • Osman Tursun, Simon Denman, Sridha Sridharan, Ethan Goan, Clinton Fookes
Recently, Zero-shot Sketch-based Image Retrieval (ZS-SBIR) has attracted the attention of the computer vision community due to it's real-world applications, and the more realistic and challenging setting than found in SBIR.
no code implementations • 5 Feb 2020 • Osman Tursun, Simon Denman, Sridha Sridharan, Clinton Fookes
However, their invariance to target data is pre-defined by the network architecture and training data.
1 code implementation • 16 Dec 2019 • Osman Tursun, Simon Denman, Rui Zeng, Sabesan Sivapalan, Sridha Sridharan, Clinton Fookes
The results of ablation studies demonstrate that the proposed multi-branch architecture with attention blocks is effective and essential.
1 code implementation • 11 Mar 2019 • Osman Tursun, Rui Zeng, Simon Denman, Sabesan Sivapalan, Sridha Sridharan, Clinton Fookes
Developing such a generic text eraser for real scenes is a challenging task, since it inherits all the challenges of multi-lingual and curved text detection and inpainting.
1 code implementation • 7 Nov 2018 • Osman Tursun, Simon Denman, Sabesan Sivapalan, Sridha Sridharan, Clinton Fookes, Sandra Mau
The demand for large-scale trademark retrieval (TR) systems has significantly increased to combat the rise in international trademark infringement.
no code implementations • WS 2017 • Osman Tursun, Ruket Cakici
Uyghur is the second largest and most actively used social media language in China.
2 code implementations • 20 Jan 2017 • Osman Tursun, Cemal Aker, Sinan Kalkan
In this paper, we provide a large-scale dataset with benchmark queries with which different TR approaches can be evaluated systematically.