Abrar Majeedi

I'm a PhD student at the University of Wisconsin-Madison, working on computer vision, focusing on video machine learning and sequential data.

I am fortunate to be advised by Prof. Yin Li. I have previously done research internships at Amazon, Microsoft and Dell EMC.

Email  /  CV  /  Scholar  /  Github

profile photo

Research

I'm interested in computer vision and deep learning. I have mostly worked on video machine learning and lately I have been working on multimodal sequential data.

RICA2: Rubric-Informed, Calibrated Assessment of Actions
Abrar Majeedi, Viswanatha Reddy Gajjala, Satya Sai Srinath Namburi GNVV, Yin Li,
European Conference on Computer Vision (ECCV) 2024
Project page / arXiv

Action quality assessment in videos by incorporating human designed scoring rubrics while providing calibrated uncertainty estimates.

Glottic Opening Detection using Deep Learning for Neonatal Intubation with Video Laryngoscopy
Abrar Majeedi, Patrick Peebles, Yin Li, Ryan McAdams,
Nature - Journal of Perinatology 2024

Auotmatically detect the glottic opening during neonatal intubation using video laryngoscopy to improve intubation outcomes.

Deep learning to quantify care manipulation activities in neonatal intensive care units
Abrar Majeedi, Ryan McAdams, Ravneet Kaur, Shubham Gupta, Harpreet Singh, Yin Li
npj Digital Medicine, June 2024
PDF / Code

Automatically quantify care manipulation activities in neonatal intensive care units (NICUs), while integrating physiological signal data to monitor neonatal stress in NICUs.

Full Reference Video Quality Assessment for Machine Learning-Based Video Codecs
Abrar Majeedi, Babak Naderi, Yasaman Hosseinkashi, Juhee Cho, Ruben Alvarez Martinez, Ross Cutler
Preprint, 2022
Paper / Code

Assess perceptual quality of videos encoded by Machine Learning-based Video Codecs.

Detecting Egocentric Actions with ActionFormer
Chenlin Zhang, Lin Sui, Abrar Majeedi, Viswantha Reddy Gajjala, Yin Li
EPIC @ CVPR Workshop 2022
Report / Code

Placed 2nd in the Egocentric action detection challenge



Website template from Jon Barron