Muhammad Abdullah Jamal

activity

20182026

most citedRethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective

29 citations · 34 across the 15 of their papers we have counts for

collaborators

Showing 2023Show all

3 papers · 1 filter

cs.CV2023★ 1 cited

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…

cs.CV2023

M $^{3}$ 3D: 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 M $^{3}$ 3D ( $M$ ulti- $M$ odal $M$ asked $3 D$ ) built based on Multi-modal masked autoencode…

cs.CV2023★ 3 cited

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…

ST(OR)2: Spatio-Temporal Object Level Reasoning for Activity Recognition in the Operating Room

M33D: Learning 3D priors using Multi-Modal Masked Autoencoders for 2D image and video understanding

SurgMAE: Masked Autoencoders for Long Surgical Video Analysis

M $^{3}$ 3D: Learning 3D priors using Multi-Modal Masked Autoencoders for 2D image and video understanding