29 citations · 34 across the 15 of their papers we have counts for
17 papers
DART: Depth-as-Target Pretraining for Surgical Vision Foundation Models
John J. Han, Adam Schmidt, Muhammad Abdullah Jamal +2
Vision foundation models (VFMs) are valuable in data-scarce domains such as surgery, where a single pretrained backbone can provide rich representations for many downstream tasks.…
SUREON: A Benchmark and Vision-Language-Model for Surgical Reasoning
Alejandra Perez, Anita Rau, Lee White +4
Surgeons don't just see -- they interpret. When an expert observes a surgical scene, they understand not only what instrument is being used, but why it was chosen, what risk it pos…
On the Role of Depth in Surgical Vision Foundation Models: An Empirical Study of RGB-D Pre-training
John J. Han, Adam Schmidt, Muhammad Abdullah Jamal +4
Vision foundation models (VFMs) have emerged as powerful tools for surgical scene understanding. However, current approaches predominantly rely on unimodal RGB pre-training, overlo…
Mitigating Surgical Data Imbalance with Dual-Prediction Video Diffusion Model
Danush Kumar Venkatesh, Adam Schmidt, Muhammad Abdullah Jamal +1
Surgical video datasets are essential for scene understanding, enabling procedural modeling and intra-operative support. However, these datasets are often heavily imbalanced, with…
SurgLaVi: Large-Scale Hierarchical Dataset for Surgical Vision-Language Representation Learning
Alejandra Perez, Chinedu Nwoye, Ramtin Raji Kermani +2
Vision-language pre-training (VLP) offers unique advantages for surgery by aligning language with surgical videos, enabling workflow understanding and transfer across tasks without…
Multi-view Video-Pose Pretraining for Operating Room Surgical Activity Recognition
Idris Hamoud, Vinkle Srivastav, Muhammad Abdullah Jamal +3
Understanding the workflow of surgical procedures in complex operating rooms requires a deep understanding of the interactions between clinicians and their environment. Surgical ac…
A Two-Stage Progressive Pre-training using Multi-Modal Contrastive Masked Autoencoders
Muhammad Abdullah Jamal, Omid Mohareri
In this paper, we propose a new progressive pre-training method for image understanding tasks which leverages RGB-D datasets. The method utilizes Multi-Modal Contrastive Masked Aut…
VidLPRO: A eo-anguage re-training Framework for botic and Laparoscopic Surgery
Mohammadmahdi Honarmand, Muhammad Abdullah Jamal, Omid Mohareri
We introduce VidLPRO, a novel video-language (VL) pre-training framework designed specifically for robotic and laparoscopic surgery. While existing surgical VL models primarily rel…
Rethinking RGB-D Fusion for Semantic Segmentation in Surgical Datasets
Muhammad Abdullah Jamal, Omid Mohareri
Surgical scene understanding is a key technical component for enabling intelligent and context aware systems that can transform various aspects of surgical interventions. In this w…
AdaEmbed: Semi-supervised Domain Adaptation in the Embedding Space
Ali Mottaghi, Mohammad Abdullah Jamal, Serena Yeung +1
Semi-supervised domain adaptation (SSDA) presents a critical hurdle in computer vision, especially given the frequent scarcity of labeled data in real-world settings. This scarcity…
ST(OR)2: Spatio-Temporal Object Level Reasoning for Activity Recognition in the Operating Room
Idris Hamoud, Muhammad Abdullah Jamal, Vinkle Srivastav +3
Surgical robotics holds much promise for improving patient safety and clinician experience in the Operating Room (OR). However, it also comes with new challenges, requiring strong…
M3D: Learning 3D priors using Multi-Modal Masked Autoencoders for 2D image and video understanding
Muhammad Abdullah Jamal, Omid Mohareri
We present a new pre-training strategy called M3D (ulti-odal asked ) built based on Multi-modal masked autoencode…
SurgMAE: Masked Autoencoders for Long Surgical Video Analysis
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 me…
Multi-Modal Unsupervised Pre-Training for Surgical Operating Room Workflow Analysis
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. On the other hand, we see…
An Empirical Study on Activity Recognition in Long Surgical Videos
Zhuohong He, Ali Mottaghi, Aidean Sharghi +2
Activity recognition in surgical videos is a key research area for developing next-generation devices and workflow monitoring systems. Since surgeries are long processes with highl…
Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective
Muhammad Abdullah Jamal, Matthew Brown, Ming-Hsuan Yang +2
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 e…
Task-Agnostic Meta-Learning for Few-shot Learning
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 t…