| 
          
            | 
                Jeya Maria Jose
               I am a Senior Researcher at  Microsoft Research. My research spans Computer Vision, Machine Learning, and NLP with an emphasis on impactful real-world applications like Healthcare. My current research revolves around building multi-modal AI systems that harness large-scale real-world data to accelerate biomedical discoveries, optimize clinical workflows, and transform healthcare.  
		     Previously, I was a postdoctoral researcher at Stanford University, working with Andrew Ng and Curtis Langlotz. I obtained my Ph.D. and M.S from Johns Hopkins University advised by  Vishal M Patel .     
		      I am glad to be recognized as an  Amazon fellow . I also had the opportunity to work with research teams at Google,  NVIDIA , and  Adobe  during my Ph.D. 
		 
              
               
                Email  / 
                CV  / 
               
                Google Scholar  / 
		      Github  / 
                 LinkedIn 
               |   |  
            
			News
             
                
		    
		      January, 2025   - 1 paper accepted at  ICLR 2025.
		     October, 2024   - Won the Young Scientist Impact Award from MICCAI Society.
		     August, 2024   - 1 paper accepted at  WACV 2025.
		     July, 2024   - 1 paper accepted at  ECCV 2024.
		     April, 2024   - 4 papers accepted at  MIDL 2024.
		     February, 2024   - Serving as Area Chair for  MICCAI 2024.
		     October, 2023   - 1 paper accepted at  WACV 2024.
		     November, 2023   -  Won the  DAAD AI-Net Fellowship.
		     August, 2023   - Invited Talk  at MedAI Group. Link for  Slides,  Video.
		     May, 2023   - Invited Talk  at Amazon. Link for  Slides.
		     April, 2023   -  Defended my Ph.D.!! Link for  Slides.
		     March, 2023   - 1 paper accepted at  MIDL 2023.
		     February, 2023   - 1 paper accepted at  CVPR 2023.
		     January, 2023   - 1 paper accepted at  ICLR 2023.
		     October, 2022   -  Won the  Amazon Research Fellowship.
		     September, 2022   -  Received  Young Scientist Impact Award - Finalist  at MICCAI 2022.
		     August, 2022   -  1 paper accepted at  WACV 2023.
		     August, 2022   -  Received  NIH MICCAI Award 2022, which rewards early career scientists.
		     June, 2022   -  3 papers accepted at  MICCAI 2022.
		     June, 2022   -  Invited Talk at  IEEE SPS Summer School on AI in Healthcare.
		     May, 2022   -  Awarded Outstanding Automation Paper Finalist (top 3) at  ICRA 2022.
		     March, 2022   -  Presented a Tutorial at  ISBI 2022 on medical image segmentation.
		     March, 2022   -  1 paper accepted at  CVPR 2022.
		     January, 2022   -  1 paper accepted at  ICRA 2022.
		     November, 2021   -  1 paper accepted in  IEEE Transactions on Medical Imaging.
		     June, 2021   -  2 papers accepted at  MICCAI 2021.
		     May, 2021   -  Joined  Adobe  as a Research Intern.
		     May, 2021   -  1 paper accepted at  ICIP 2021 .
		     November, 2020   -  1 paper accepted in  IEEE Journal of Selected Topics in Signal Processing .
		     November, 2020   -  1 paper accepted at  WACV 2021 .
		     July, 2020   -  Recipient of  MICCAI Student Travel Award 2020, which rewards first author students of the highest-quality MICCAI papers.
		     May, 2020   -  1 paper accepted in the  IEEE Journal of Selected Topics in Signal Processing .
		     May, 2020   - 1 paper accepted  at  MICCAI 2020   (Early Acceptance).
		    September, 2019 - Awarded  Best Student Paper award  at  CVIP 2019 . August, 2019   -     Joined  Johns Hopkins University  for my Ph.D with ECE fellowship.
             		 
 
 
            
			Research	
				 
	
            |  | The Illusion of Readiness: Stress Testing Large Frontier Models on Multimodal Medical Benchmarks    
		     Microsoft Research, Microsoft Health and Life Sciences
		     Paper
 |  
	
            |  | Time-to-Event Pretraining for 3D Medical Imaging  ICLR 2025  
		     Zepeng Huo*, Jason Alan Fries*, Alejandro Lozano*, Jeya Maria Jose , Ethan Steinberg, Louis Blankemeier,
Akshay S. Chaudhari, Curtis Langlotz, Nigam H. Shah
		     Paper
 |  
	
            |  | Merlin: A Vision Language Foundation Model for 3D Computed Tomography  Preprint 2024  
		     Stanford AIMI (L.Blankemeier et al.)  
		     Paper
 |  
	
            |  | MaxFusion: Plug&Play Multi-Modal Generation in Text-to-Image Diffusion Models  ECCV 2024  
		     Nithin GK, Jeya Maria Jose
                , Vishal M. Patel   
		     Paper  |  Project  |  Code
 |  
	
            |  | Diffscaler: Enhancing the Generative Prowess of Diffusion Transformers  Preprint 2024  
		     Nithin GK, Jeya Maria Jose
                , Vishal M. Patel   
		     Paper
 |  
	
            |  | CheXagent: Towards a Foundation Model for Chest X-Ray Interpretation  Preprint 2024  
		     Z. Chen, M. Varma, JB Delbrouck, M. Paschali, L. Blankemeier, DV Veen Jeya Maria Jose
                ,  A. Youssef, JP Cohen, EP Reis, EB Tsai, A. Johnston, C. Olsen, TM Abraham, S. Gatidis, Akshay S. Chaudhari, Curtis Langlotz   
		     Paper  |  Project  |  Demo  |  Code
 |  
	
            |  | ReBotNet: Fast Real-time Video Enhancement  WACV 2025  
		     Jeya Maria Jose
                , Rahul Garg, Andeep Toor, Xin Tong, Weijuan Xi, Andreas Lugmayr, Vishal M. Patel and Anne Menini   
		     Paper  |  Project   |  Code
 |  
	
            |  | Disruptive Autoencoders: Leveraging Low-level features for 3D Medical Image Pre-training  MIDL 2024  
		     Jeya Maria Jose
                , Yucheng Tang, Dong Yang, Ziyue Xu, Can Zhao, Wenqi Li, Vishal M. Patel, Bennett Landman, Daguang Xu, Yufan He and Vishwesh Nath   
		     Paper  |  Weights |  Pre-training Code
 |  
            |  | Auto-Generating Weak Labels for Real & Synthetic Data to Improve Label-Scarce Medical Image Segmentation  MIDL 2024  
		     Tanvi Deshpande, Eva Prakash, Elsie Gyang Ross, Curtis Langlotz, Andrew Ng, Jeya Maria Jose
               
		    
 Paper  |  Code
 |  
            |  | Unlocking Robust Segmentation Across All Age Groups via Continual Learning  MIDL 2024  
		     Chih-Ying Liu,  Jeya Maria Jose, Camila Gonzalez, Curtis Langlotz, Andrew Ng, Sergios Gatidis 
               
		    
 Paper
 |  
            |  | Target and Task specific Source-Free Domain Adaptive Image Segmentation  MIDL 2024  
		     Vibashan VS*, Jeya Maria Jose*
                , and Vishal M. Patel
  *equal contribution Paper  |  Code |  
	
            |  | Self-Supervised Denoising Transformer with Gaussian Process  WACV 2024  
		     Rajeev Yasarla, Jeya Maria Jose
                , Vishwanath Sindagi, Vishal M. Patel   
		     Paper
 |  
            |  | CLIP Goes 3D: Leveraging Prompt Tuning for Language-Grounded 3D Recognition  OpenSUN3D, ICCV 2023  
		     Deepti Hegde*, Jeya Maria Jose*
                , and Vishal M. Patel
  *equal contribution Paper  |  Code  |  Project |  
            |  | On-the-Fly Test-time Adaptation for Medical Image Segmentation  MIDL 2023  
		     Jeya Maria Jose
                , Pengfei Guo, Vibashan VS, and Vishal M. Patel   
		     Paper  |  Code
 |  
            |  | Ambiguous Medical Image Segmentation using Diffusion Models  CVPR 2023  
		     Aimon Rahman, Jeya Maria Jose, Ilker H,
               and Vishal M. Patel    
		     Paper  |  Code  |  Project
 |  
            |  | Interactive Portrait Harmonization  ICLR 2023  
		     Jeya Maria Jose, He Zhang, Jianming Zhang, Yilin Wang, Zhe Lin
, Jose Echevarria, Yinglan Ma, Zijun Wei, Kalyan Sunkavalli, and Vishal M. Patel    
		     Paper  |  Code  |  Project
 |  
            |  | Fine-Context Shadow Detection using Shadow Removal  WACV 2023  
		     Jeya Maria Jose
               and Vishal M. Patel    
		     Paper
 |  
            |  | TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions  CVPR 2022  
		     Jeya Maria Jose, Rajeev Yasarla
               and Vishal M. Patel    
		     Paper  |  Code  |  Project
 |  
            |  | UNeXt: MLP-based Rapid Medical Image Segmentation Network  MICCAI 2022  
		     Jeya Maria Jose
               and Vishal M. Patel    
		     Paper  |  Code  |  Project
 |  
            |  | Simultaneous Bone and Shadow Segmentation Network using Task Correspondence Consistency  MICCAI 2022  
		     Aimon Rahman, Jeya Maria Jose, Ilker H,
               and Vishal M. Patel    
		     Paper
 |  
            |  | Orientation-guided Graph Convolutional Network for Bone Surface Segmentation  MICCAI 2022  
		     Aimon Rahman, Chaminda Bandara, Jeya Maria Jose, Ilker H,
               and Vishal M. Patel    
		     Paper
 |  
            |  | SPIN Road Mapper: Extracting Roads from Aerial Images via Spatial and Interaction Space Graph Reasoning for Autonomous Driving  ICRA 2022 (Outstanding Automation Paper Finalist) 
		     Chaminda Bandara,	      
Jeya Maria Jose,
               and Vishal M. Patel    
		     Paper  |  Code
 |  
            |  | Medical Transformer: Gated Axial-Attention for Medical Image Segmentation  MICCAI 2021  
		     
 Jeya Maria Jose,
              Poojan Oza,
		    Ilker Hacihaliloglu,
		    Vishal M. Patel
		      Paper  |   Code   |  
            |  | Over-and-Under Complete Convolutional RNN for MRI Reconstruction  MICCAI 2021  
		     
 Pengfei Guo, Jeya Maria Jose,
              Puyang Wang,
		    Jinyuan Zhou,Shanshan Jiang,
		    Vishal M. Patel
		      Paper  |   Code   |  
            |  | KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation  IEEE Transactions on Medical Imaging  
		     
 
 Jeya Maria Jose,
              Vishwanath Sindagi,
		    Ilker Hacihaliloglu,
		    Vishal M. Patel
		      Paper  |   Code  |   Project  |  
            |  | Overcomplete Deep Subspace Clustering Networks  WACV 2021  
		     
 
		      Jeya Maria Jose and
		    Vishal M. Patel
		      Paper  |   Code   |  
            |  | Overcomplete Representations against Adversarial Videos  ICIP 2021  
		     Shao-Yuan Lo,	      
Jeya Maria Jose,
               and Vishal M. Patel    
		     Paper
 |  
            |  | Exploring Overcomplete Representations for Single Image Deraining using CNNs  IEEE Journal of Selected Topics in Signal Processing 
		     
 Rajeev Yasarla*,
		      Jeya Maria Jose*,
		    Vishal M. Patel
		      *equal contribution   Paper  |   Code   |  
            |  | KiU-Net: Towards Accurate Segmentation of Biomedical Images using Over-complete Representations  MICCAI 2020 (Oral)  
		     
 Jeya Maria Jose,
              Vishwanath Sindagi,
		    Ilker Hacihaliloglu,
		    Vishal M. Patel
		      Paper  |   Code  |   Project  |  
            |  | Learning to Segment Brain Anatomy from 2D Ultrasound with Less Data  IEEE Journal of Selected Topics in Signal Processing   
		     
 Jeya Maria Jose,
              Rajeev Yasarla,
		    Puyang Wang,
		    Ilker Hacihaliloglu,
		    Vishal M. Patel
		      Paper  |  
            |  | Tackling Multiple Visual Artifacts: Blind Image Restoration using Conditional Adversarial Networks  CVIP 2019   (Best Student Paper Award)  
		     M Anand,
              A Ashwin Natraj,
	      Jeya Maria Jose,
              K Subramanian,
              S Deivalakshmi    
		     Paper  |  Code
 |  
            |  | Brain Tumor Segmentation and Survival Prediction using 3D Attention UNet BraTS,   MICCAI Workshop 2019  Mobarakol Islam,
		    Vibashan VS,
		    Jeya Maria Jose,
		    Navodini Wijethilake,
		    Uppal Utkarsh,
		    Hongliang Ren
  Paper  |  
            |  | Glioma Prognosis: Segmentation of the Tumor and Survival Prediction using Shape, Geometric and Clinical Information BraTS,   MICCAI Workshop 2018  Mobarakol Islam,
              Jeya Maria Jose,
              Hongliang Ren
 Paper  | Poster |  
          
            | 
            
			Services
			    Web Chair: AVSS 2021
		     
			    Program Committe: DART Workshop, MICCAI 2022
		     
			    Reviewer at:
		      Journals : 
          
          IEEE Transactions on Pattern Analysis and Machine Intelligence  IEEE Transactions on Medical Imaging  Elsevier Medical Image Analysis  IEEE Transactions on Circuits and Systems for Video Technology  IEEE Transactions on Geoscience and Remote Sensing  Springer International Journal on Computer Vision Elsevier Pattern Recognition  Elsevier Computers in Biology and Medicine
		       
			 Conferences :
        
       CVPR ICCV ECCV NeurIPS ICLR ICML MICCAI MIDL WACV ICIP
		     
			     Workshops : 
             BrainLes,  Medical Image Learning with Less Labels and Imperfect Data  |  |