Biography
Mohammad Alsharid graduated from Khalifa University in Abu Dhabi, United Arab Emirates with highest honours, earning a BSc. degree in Computer Engineering. Before coming to Oxford to join the DPhil in Engineering Science program, Alsharid had interned at the Sheikh Zayed Institute for Pediatric Surgical Innovation at Children’s National Health System in Washington DC, USA in 2015, Samsung Electronics in Suwon, South Korea in 2016, and the Mohammad Bin Rashed Space Center in Dubai, United Arab Emirates in 2017.
Awards and Prizes
Rhodes Scholar, Class of 2017.
Most Recent Publications
Gaze-assisted automatic captioning of fetal ultrasound videos using three-way multi-modal deep neural networks.
Gaze-assisted automatic captioning of fetal ultrasound videos using three-way multi-modal deep neural networks.
A course-focused dual curriculum for image captioning
A course-focused dual curriculum for image captioning
A curriculum learning based approach to captioning ultrasound images
A curriculum learning based approach to captioning ultrasound images
Self-supervised contrastive video-speech representation learning for ultrasound
Self-supervised contrastive video-speech representation learning for ultrasound
Captioning ultrasound images automatically
Captioning ultrasound images automatically
Research Interests
Alsharid's current research work covers machine learning, natural language processing, computer vision, and the multi-modal interplay of these fields as well as their role in biomedical image analysis.
Current Projects
Alsharid is currently involved with the PULSE project. His focus is primarily on generating textual captions for ultrasound visuals in an automated fashion.
Research Groups
Related Academics
Most Recent Publications
Gaze-assisted automatic captioning of fetal ultrasound videos using three-way multi-modal deep neural networks.
Gaze-assisted automatic captioning of fetal ultrasound videos using three-way multi-modal deep neural networks.
A course-focused dual curriculum for image captioning
A course-focused dual curriculum for image captioning
A curriculum learning based approach to captioning ultrasound images
A curriculum learning based approach to captioning ultrasound images
Self-supervised contrastive video-speech representation learning for ultrasound
Self-supervised contrastive video-speech representation learning for ultrasound
Captioning ultrasound images automatically
Captioning ultrasound images automatically
Most Recent Publications
Gaze-assisted automatic captioning of fetal ultrasound videos using three-way multi-modal deep neural networks.
Gaze-assisted automatic captioning of fetal ultrasound videos using three-way multi-modal deep neural networks.
A course-focused dual curriculum for image captioning
A course-focused dual curriculum for image captioning
A curriculum learning based approach to captioning ultrasound images
A curriculum learning based approach to captioning ultrasound images
Self-supervised contrastive video-speech representation learning for ultrasound
Self-supervised contrastive video-speech representation learning for ultrasound
Captioning ultrasound images automatically
Captioning ultrasound images automatically
