February 2025. One paper on 'Multi-Modal Contrastive Masked Autoencoders: A Two-Stage Progressive Pre-training Approach for RGBD Datasets' is accepted to CVPR 2025.
November 2024. One paper on 'Rethinking RGB-D Fusion for Semantic Segmentation in Surgical Datasets' is accepted to ML4H 2024.
October 2024. One paper on 'VidLPRO: A Video-Language Pre-training Framework for Robotic and Laparoscopic Surgery' is accepted to AIM-FM Workshop @ NeurIPS'24.
November 2023. One paper on 'Masked Autoencoders for Video Pre-training' is accepted to NeurIPS 2023 Workshop: Self-Supervised Learning - Theory and Practice.
November 2023. One paper on 'Multi-Modal Masked Autoencoders' accepted to WACV 2024.
June 2023. Gave a talk on 'Towards Data-efficient learning for long surgical video analysis' in CVPR 2023 workshop on Medical Computer Vision.
Research Experience
He is currently a Staff ML Scientist at Intuitive Surgical.
Education
He received his B.E. degree in Information and Communication Systems from the National University of Sciences and Technology, Pakistan in 2013. He obtained his PhD from the University of Central Florida under the supervision of Dr. Liqianq Wang and Dr. Boqing Gong (remote/Google Research).
Background
His research interests are broadly in computer vision and machine learning, with a focus on data-efficient learning through meta-learning and domain adaptation. He is specifically interested in developing novel algorithms to efficiently learn beyond human curated datasets (e.g., few-shot learning, long-tail, etc.) for visual recognition.