Abrar Majeedi

I'm a PhD candidate at the University of Wisconsin-Madison, working on multimodal deep learning. I am fortunate to be advised by Prof. Yin Li.

I have also gained valuable research experience through internships at Amazon, Microsoft and Dell EMC.

Email  /  CV  /  Scholar  /  Github

profile photo

Research

My research focus is multimodal deep learning for sequential data. I am also interested in Vision Language Models, Large Language Models, and their applications in sequential data such as videos, sensor data (time series) and text.

Awards

  • Jan 2025: Our Poster "Deep learning to quantify care manipulation activities in neonatal intensive care units" won an Award for Best Innovation in Neonatology at the Cleveland Clinic Children's SHINE (Syposium on Health Innovation and Neonatal Excellence) Conference, Orlando, FL.
  • Nov 2024: Our paper "RICA2: Rubric-Informed, Calibrated Assessment of Actions" won the Best Poster Award at NSF Poster Competition at Purdue University, West Lafayette, IN.

Publications

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 / Paper Link

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, Nov 2024
Paper link

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
Paper Link / 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

Won 2nd place in the Egocentric action detection challenge



Website template from Jon Barron