Anwesa Choudhuri

I am a Senior Research Scientist at United Imaging Intelligence, Boston, MA

I completed my Ph.D. in Electrical and Computer Engineering from the University of Illinois Urbana-Champaign (UIUC) in 2024, where I was advised by Girish Chowdhary and Alex Schwing.

My research focuses on video understanding, image and video segmentation, and image and video captioning.

Google Scholar  /  LinkedIn  /  Email

profile photo

News

Research Papers

Some of my recent publications are listed below.

PolypSegTrack: Unified Foundation Model for Colonoscopy Video Analysis
A Choudhuri, Z Gao, M Zheng, B Planche, T Chen, Z Wu
MICCAI, 2025
arXiv

A foundation model for joint detection, segmentation, classification, and tracking of polyps in endoscopy videos.

Order-aware Interactive Segmentation
B Wang, A Choudhuri, M Zheng, Z Gao, B Planche, A Deng, Q Liu, T Chen, Z Wu
ICLR, 2025
arXiv

Transformer-based model for fine-grained interactive segmentation.

OW-VISCapTor: Abstractors for Open-World Video Instance Segmentation and Captioning
A Choudhuri, G Chowdhary, A Schwing
NeurIPS, 2024
Project / arXiv

Video instance segmentation and captioning of open-world and close-world objects.

Context-Aware Relative Object Queries to Unify Video Instance and Panoptic Segmentation
A Choudhuri, G Chowdhary, AG Schwing
CVPR, 2023
Project / Paper

Simple approach for multiple video segmentation tasks using context-aware relative object queries (CAROQ).

Assignment-Space-Based Multi-Object Tracking and Segmentation
A Choudhuri, G Chowdhary, AG Schwing
ICCV, 2021
Project / Paper

Globally optimal solution for multi-object tracking and segmentation (MOTS) over the space of assignments.

Academic Services


Template adopted from here.