Portfolio · 2026

Pratyay Dutta

Ph.D. Candidate · Computer Science · UC Riverside

I specialize in computer vision, deep learning, and physics-based modeling. My research focuses on designing algorithms that learn effectively from data and bridge physical principles with neural networks.

I aim to push the boundaries of robust and interpretable AI by collaborating with interdisciplinary teams and contributing solutions that impact real-world vision tasks, from person re-identification to event-based perception.

"Stay Hungry. Stay Foolish"
Pratyay Dutta
5+
Papers
6+
Years Experience
5
Courses Taught

Academic Background

2023 - Present

Doctor of Philosophy (Ph.D.)

Computer Science
University of California, Riverside
Grade: 3.94/4.0
Currently Pursuing
3.94
2019 - 2023

Bachelor of Engineering

Electronics and Telecommunication Engineering
Jadavpur University
Grade: 9.5/10
9.5
2005 - 2019

Primary, Middle and High School

ICSE and ISC
Calcutta Boys' School
Class 10 (ICSE): 99.2% · Class 12 (ISC): 98.75%
Class X
99.2%
Class XII
98.75%

Publications

TPAMI: Under Review

SAKE: Structure Aware Kernel Experts for Event-Based Object Detection

Pratyay Dutta, Bir Bhanu

SAKE replaces heavy AI calculations with a heat-flow mechanism that mimics how information spreads along the edges of objects. This physics-inspired approach allows the model to "see" clearly in low light or fast motion with much less computing power.

2025
TBIOM 2025

POANet: Parts-based Occlusion Aware Network for Person Re-ID

Pratyay Dutta, Padmaja Jonnalagedda, Bir Bhanu

A parts-based occlusion-aware network for robust person re-identification, addressing partial visibility through structured part-level feature learning and attention-guided reconstruction.

2025
TCSVT 2025

Latent Diffusion-Guided Feature Inpainting for Occluded Person Re-Identification With Hybrid Re-Ranking

Pratyay Dutta, Bir Bhanu

Our De-Occluder (DDO) uses AI to "fill in" hidden parts of a person's image, allowing for accurate identification even when someone is partially blocked. Combined with a smart re-ranking system, it achieves state-of-the-art results in identifying people through dense crowds.

2025
TCBB 2022

Hierarchical Vaccine Allocation based on Epidemiological and Behavioral Considerations

Satyaki Roy, Pratyay Dutta, Preetam Ghosh

An optimized hierarchical vaccine distribution strategy incorporating epidemiological and behavioral factors with clustering-based zone allocation for improved vaccine redistribution across demographics.

2022
BIBM 2021

Generalizable Multi-Vaccine Distribution Strategy based on Demographic and Behavioral Heterogeneity

Satyaki Roy, Pratyay Dutta, Preetam Ghosh

A generalizable multi-vaccine distribution strategy using linear optimization and clustering algorithms to address demographic and behavioral heterogeneity across geographic zones.

2021

Experience

2023 –
Present

Research Assistant

University of California, Riverside

Conducting research under Dr. Bir Bhanu on event-based vision with anisotropic heat diffusion, virtual cloth try-off using Stable Diffusion, and latent diffusion-guided feature inpainting for occluded person re-identification.

Jun –
Aug 2022

Research Intern

Dalhousie University, Canada

Built a predictive modeling pipeline on Lichess chess data and trained a PPO-based RL agent capable of defeating amateur players below a target FIDE rating, under Dr. Yannick Marchand.

Jun 2020 –
Nov 2021

Research Intern

Virginia Commonwealth University, USA

Optimized multi-vaccine distribution strategies using linear programming and clustering; work resulted in publications at IEEE BIBM 2021 and IEEE/ACM TCBB 2022, under Dr. Preetam Ghosh.

Awards & Honors

2023

Dean's Fellowship

University of California, Riverside

Awarded for outstanding research acumen upon admission. Acceptance rate: 15%.

2020

MITACS Fellowship

MITACS Canada

Funded summer research internship at Dalhousie University, Canada. Acceptance rate: 18%.

2019

Bishop Thoburn Award — Student of the Year

Calcutta Boys' School

Recognized for outstanding achievement in academics, sports, and extracurricular activities. Awarded to 1 in 120 students.

Capabilities

Technical Software
Python
Applied in research workflows, model development, evaluation pipelines, and production-scale experimentation.
MATLAB
Applied in research workflows, model development, evaluation pipelines, and production-scale experimentation.
Java
Applied in research workflows, model development, evaluation pipelines, and production-scale experimentation.
C/C++
Applied in research workflows, model development, evaluation pipelines, and production-scale experimentation.
SQL
Applied in research workflows, model development, evaluation pipelines, and production-scale experimentation.
PyTorch
Applied in research workflows, model development, evaluation pipelines, and production-scale experimentation.
TensorFlow
Applied in research workflows, model development, evaluation pipelines, and production-scale experimentation.
OpenCV
Applied in research workflows, model development, evaluation pipelines, and production-scale experimentation.
Pandas
Applied in research workflows, model development, evaluation pipelines, and production-scale experimentation.
NumPy
Applied in research workflows, model development, evaluation pipelines, and production-scale experimentation.
Matplotlib
Applied in research workflows, model development, evaluation pipelines, and production-scale experimentation.
Git
Applied in research workflows, model development, evaluation pipelines, and production-scale experimentation.
Docker
Applied in research workflows, model development, evaluation pipelines, and production-scale experimentation.
Google Cloud Platform
Applied in research workflows, model development, evaluation pipelines, and production-scale experimentation.
VS Code
Applied in research workflows, model development, evaluation pipelines, and production-scale experimentation.
PyCharm
Applied in research workflows, model development, evaluation pipelines, and production-scale experimentation.
Virtual Environments
Applied in research workflows, model development, evaluation pipelines, and production-scale experimentation.
CUDA DDP/FSDP
Applied in research workflows, model development, evaluation pipelines, and production-scale experimentation.
Languages
English99%
Bengali98%
Hindi67%
German11.1%

Get in Touch

Have a question, collaboration idea, or just want to say hello?
Fill in the form and I'll get back to you.