no code implementations • 10 Feb 2024 • Ayman Abaid, Muhammad Ali Farooq, Niamh Hynes, Peter Corcoran, Ihsan Ullah
It has been shown that Cardiac CTA images can be successfully generated using using Text to Image (T2I) stable diffusion model.
no code implementations • 10 Jan 2024 • Muhammad Ali Farooq, Wang Yao, Michael Schukat, Mark A Little, Peter Corcoran
This study explores the utilization of Dermatoscopic synthetic data generated through stable diffusion models as a strategy for enhancing the robustness of machine learning model training.
no code implementations • 18 Nov 2023 • Gabriel Cosache, Francisco Salgado, Cosmin Rotariu, George Sterpu, Rishabh Jain, Peter Corcoran
An overview is given of the DAVID Smart-Toy platform, one of the first Edge AI platform designs to incorporate advanced low-power data processing by neural inference models co-located with the relevant image or audio sensors.
no code implementations • 8 Nov 2023 • Muhammad Ali Farooq, Dan Bigioi, Rishabh Jain, Wang Yao, Mariam Yiwere, Peter Corcoran
Contemporary Human Computer Interaction (HCI) research relies primarily on neural network models for machine vision and speech understanding of a system user.
1 code implementation • 7 Nov 2023 • Rishabh Jain, Peter Corcoran
The approach involved finetuning a multi-speaker TTS model to work with child speech.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
1 code implementation • 7 Nov 2023 • Andrei Barcovschi, Rishabh Jain, Peter Corcoran
We demonstrate that finetuning Conformer-transducer models on child speech yields significant improvements in ASR performance on child speech, compared to the non-finetuned models.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 15 Aug 2023 • Paul Kielty, Cian Ryan, Mehdi Sefidgar Dilmaghani, Waseem Shariff, Joe Lemley, Peter Corcoran
In a binary classification task, the fastened/unfastened frames were identified with an F1 score of 0. 989 and 0. 944 on the simulated and real test sets respectively.
no code implementations • 8 Aug 2023 • Wang Yao, Muhammad Ali Farooq, Joseph Lemley, Peter Corcoran
This work explores the effect of age and aging on the performance of facial authentication methods.
no code implementations • 8 Aug 2023 • Wang Yao, Muhammad Ali Farooq, Joseph Lemley, Peter Corcoran
The lack of ethnic diversity in data has been a limiting factor of face recognition techniques in the literature.
no code implementations • 25 Jul 2023 • Muhammad Ali Farooq, Wang Yao, Gabriel Costache, Peter Corcoran
In this research work, we proposed a novel ChildGAN, a pair of GAN networks for generating synthetic boys and girls facial data derived from StyleGAN2.
no code implementations • 25 Jul 2023 • Muhammad Ali Farooq, Waseem Shariff, Mehdi Sefidgar Dilmaghani, Wang Yao, Moazam Soomro, Peter Corcoran
Optical sensors have played a pivotal role in acquiring real world data for critical applications.
1 code implementation • 24 Jul 2023 • Rishabh Jain, Andrei Barcovschi, Mariam Yiwere, Peter Corcoran, Horia Cucu
We demonstrate that finetuning Whisper on child speech yields significant improvements in ASR performance on child speech, compared to non finetuned Whisper models.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 4 May 2023 • Paul Kielty, Mehdi Sefidgar Dilmaghani, Cian Ryan, Joe Lemley, Peter Corcoran
An additional 12300 frames were generated from event simulations of a public dataset to test against other methods.
no code implementations • 2 Mar 2023 • Mohamed Moustafa, Amr Elrasad, Joseph Lemley, Peter Corcoran
The data prepared is to include camera frames as well as sensor readings from an electrocardiograph sensor.
1 code implementation • 18 Jan 2023 • Muhammad Ali Farooq, Waseem Shariff, Faisal Khan, Peter Corcoran
In this research work, we have proposed a thermal tiny-YOLO multi-class object detection (TTYMOD) system as a smart forward sensing system that should remain effective in all weather and harsh environmental conditions using an end-to-end YOLO deep learning framework.
no code implementations • 10 Jan 2023 • Dan Bigioi, Shubhajit Basak, Michał Stypułkowski, Maciej Zięba, Hugh Jordan, Rachel McDonnell, Peter Corcoran
Taking inspiration from recent developments in visual generative tasks using diffusion models, we propose a method for end-to-end speech-driven video editing using a denoising diffusion model.
no code implementations • 14 Dec 2022 • Waseem Shariff, Muhammad Ali Farooq, Joe Lemley, Peter Corcoran
The focus is on building efficient state-of-the-art object detection networks with better inference results for fast-moving forward perception using an event camera.
no code implementations • 7 Dec 2022 • Santosh Kumar Yadav, Achleshwar Luthra, Esha Pahwa, Kamlesh Tiwari, Heena Rathore, Hari Mohan Pandey, Peter Corcoran
To address such complexities, in this paper, we propose a novel Sparse Weighted Temporal Attention (SWTA) module to utilize sparsely sampled video frames for obtaining global weighted temporal attention.
no code implementations • 10 Nov 2022 • Santosh Kumar Yadav, Esha Pahwa, Achleshwar Luthra, Kamlesh Tiwari, Hari Mohan Pandey, Peter Corcoran
To address such complexities, in this paper, we propose a novel Sparse Weighted Temporal Fusion (SWTF) module to utilize sparsely sampled video frames for obtaining global weighted temporal fusion outcome.
no code implementations • 25 Oct 2022 • Mehdi Sefidgar Dilmaghani, Waseem Shariff, Cian Ryan, Joe Lemley, Peter Corcoran
To increase the users degree of freedom in controlling the output of these cameras, such as changing the sensitivity of the sensor to light changes, controlling the number of generated events and other similar operations, the camera manufacturers usually introduce some tools to make sensor level changes in camera settings.
no code implementations • 21 Sep 2022 • David O'Callaghan, Cian Ryan, Waseem Shariff, Muhammad Ali Farooq, Joseph Lemley, Peter Corcoran
The process of obtaining high-resolution images from single or multiple low-resolution images of the same scene is of great interest for real-world image and signal processing applications.
no code implementations • 6 Apr 2022 • Rishabh Jain, Andrei Barcovschi, Mariam Yiwere, Dan Bigioi, Peter Corcoran, Horia Cucu
Our models outperformed the wav2vec2 BASE 960 on child speech which is considered a state-of-the-art ASR model on adult speech by just using 10 hours of child speech data in finetuning.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 22 Mar 2022 • Rishabh Jain, Mariam Yiwere, Dan Bigioi, Peter Corcoran, Horia Cucu
Speech synthesis has come a long way as current text-to-speech (TTS) models can now generate natural human-sounding speech.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 5 Jan 2022 • Muhammad Ali Farooq, Waseem Shariff, Peter Corcoran
This study is focused on evaluating the real-time performance of thermal object detection for smart and safe vehicular systems by deploying the trained networks on GPU & single-board EDGE-GPU computing platforms for onboard automotive sensor suite testing.
no code implementations • 20 Sep 2021 • Muhammad Ali Farooq, Peter Corcoran, Cosmin Rotariu, Waseem Shariff
Object detection in thermal infrared spectrum provides more reliable data source in low-lighting conditions and different weather conditions, as it is useful both in-cabin and outside for pedestrian, animal, and vehicular detection as well as for detecting street-signs & lighting poles.
no code implementations • 8 Apr 2021 • Viktor Varkarakis, Wang Yao, Peter Corcoran
This work shows that an SoA neural face recognition model can be tuned to compensate for directional lighting effects, removing the need for a pre-processing step before applying facial recognition.
no code implementations • 5 May 2020 • Muhammad Ali Farooq, Peter Corcoran
The same technique is also used on our thermal face data acquired using prototype thermal camera (developed under Heliaus EU project) in an indoor lab environment which is then used for generating synthetic 3D face data along with varying yaw face angles and lastly facial depth map is generated.
no code implementations • 24 Mar 2020 • Viktor Varkarakis, Shabab Bazrafkan, Peter Corcoran
The role of this tool in building large, scalable datasets of synthetic facial data is also discussed.
no code implementations • 24 Mar 2020 • Viktor Varkarakis, Peter Corcoran
In this work, it is presented a semi-automatic method for cleaning the noisy large face datasets with the use of face recognition.
no code implementations • 13 Mar 2020 • Muhammad Ali Farooq, Asma Khatoon, Viktor Varkarakis, Peter Corcoran
The experimental results demonstrate notable improvement in train and validation accuracy by using the refined version of images of both the networks, however, the Inception-v3 network was able to achieve better validation accuracy thus it was finally selected to evaluate it on test data.
no code implementations • 2 Mar 2020 • Adrian-S. Ungureanu, Saqib Salahuddin, Peter Corcoran
As a biometric palmprints have been largely under-utilized, but they offer some advantages over fingerprints and facial biometrics.
no code implementations • 1 Mar 2019 • Viktor Varkarakis, Shabab Bazrafkan, Peter Corcoran
A data augmentation methodology is presented and applied to generate a large dataset of off-axis iris regions and train a low-complexity deep neural network.
no code implementations • 28 Jun 2018 • Joseph Lemley, Anuradha Kar, Alexandru Drimbarean, Peter Corcoran
Accurate and efficient eye gaze estimation is important for emerging consumer electronic systems such as driver monitoring systems and novel user interfaces.
no code implementations • 19 Jun 2018 • Shabab Bazrafkan, Peter Corcoran
Conditional generators learn the data distribution for each class in a multi-class scenario and generate samples for a specific class given the right input from the latent space.
no code implementations • 28 May 2018 • Shabab Bazrafkan, Peter Corcoran
Conditional generators are one of the successful implementations of such models wherein the created samples are constrained to a specific class.
no code implementations • 1 May 2018 • Shabab Bazrafkan, Hossein Javidnia, Peter Corcoran
One of the most interesting challenges in Artificial Intelligence is to train conditional generators which are able to provide labeled adversarial samples drawn from a specific distribution.
no code implementations • 1 Feb 2018 • Shabab Bazrafkan, Hossein Javidnia, Peter Corcoran
There have been a tremendous amount of attempts to detect these points from facial images however, there has never been an attempt to synthesize a random face and generate its corresponding facial landmarks.
Image and Video Processing
no code implementations • 7 Dec 2017 • Shabab Bazrafkan, Shejin Thavalengal, Peter Corcoran
Finally, the proposed model is compared with SegNet-basic, and a near-optimal tuning of the network is compared to a selection of other state-of-art iris segmentation algorithms.
no code implementations • 21 Nov 2017 • Hossein Javidnia, Peter Corcoran
Evaluation of this method based on a well-known benchmark indicates that the proposed framework performs well in terms of accuracy when compared to the top-ranked depth estimation methods and a baseline algorithm.
no code implementations • 21 Nov 2017 • Hossein Javidnia, Peter Corcoran
To tackle this issue, in this paper, a framework is proposed based on Preconditioned Alternating Direction Method of Multipliers (PADMM) for depth from the focal stack and synthetic defocus application.
no code implementations • 24 Mar 2017 • Joseph Lemley, Shabab Bazrafkan, Peter Corcoran
Smart Augmentation works by creating a network that learns how to generate augmented data during the training process of a target network in a way that reduces that networks loss.