no code implementations • 19 Dec 2023 • Idris Hamoud, Muhammad Abdullah Jamal, Vinkle Srivastav, Didier Mutter, Nicolas Padoy, Omid Mohareri
Surgical robotics holds much promise for improving patient safety and clinician experience in the Operating Room (OR).
no code implementations • 26 Sep 2023 • Muhammad Abdullah Jamal, Omid Mohareri
We present a new pre-training strategy called M$^{3}$3D ($\underline{M}$ulti-$\underline{M}$odal $\underline{M}$asked $\underline{3D}$) built based on Multi-modal masked autoencoders that can leverage 3D priors and learned cross-modal representations in RGB-D data.
no code implementations • 19 May 2023 • Muhammad Abdullah Jamal, Omid Mohareri
There has been a growing interest in using deep learning models for processing long surgical videos, in order to automatically detect clinical/operational activities and extract metrics that can enable workflow efficiency tools and applications.
no code implementations • 16 Jul 2022 • Muhammad Abdullah Jamal, Omid Mohareri
Data-driven approaches to assist operating room (OR) workflow analysis depend on large curated datasets that are time consuming and expensive to collect.
no code implementations • 5 May 2022 • Zhuohong He, Ali Mottaghi, Aidean Sharghi, Muhammad Abdullah Jamal, Omid Mohareri
In this paper, we investigate many state-of-the-art backbones and temporal models to find architectures that yield the strongest performance for surgical activity recognition.
no code implementations • ICCV 2021 • Muhammad Abdullah Jamal, Liqiang Wang, Boqing Gong
Gradient-based meta-learning relates task-specific models to a meta-model by gradients.
1 code implementation • CVPR 2020 • Muhammad Abdullah Jamal, Matthew Brown, Ming-Hsuan Yang, Liqiang Wang, Boqing Gong
Object frequency in the real world often follows a power law, leading to a mismatch between datasets with long-tailed class distributions seen by a machine learning model and our expectation of the model to perform well on all classes.
Ranked #27 on Long-tail Learning on Places-LT
no code implementations • CVPR 2019 • Muhammad Abdullah Jamal, Guo-Jun Qi
However, the generalizability on new tasks of a meta-learner could be fragile when it is over-trained on existing tasks during meta-training phase.
no code implementations • CVPR 2018 • Muhammad Abdullah Jamal, Haoxiang Li, Boqing Gong
Arguably, no single face detector fits all real-life scenarios.
no code implementations • 20 May 2018 • Muhammad Abdullah Jamal, Guo-Jun Qi, Mubarak Shah
Meta-learning approaches have been proposed to tackle the few-shot learning problem. Typically, a meta-learner is trained on a variety of tasks in the hopes of being generalizable to new tasks.