Anindya Mondal

PhD Student in Computer Vision and AI

Surrey Institute for People-Centred AI (CVSSP), University of Surrey

I am a third-year PhD student advised by Dr. Anjan Dutta, Dr. Xiatian Zhu, and Dr. Joaquin M. Prada.

My research focuses on vision-language representation learning with applications in action recognition, object counting, and text-to-image synthesis. I aim to develop practical algorithms that enable robust scene understanding and generation in real-world settings by effectively integrating multi-modal signals.

Email: a.mondal [at] surrey.ac.uk

Research Interests

My research lies at the intersection of computer vision and natural language processing, with a focus on:

Vision-Language Models: Multi-modal representation learning for robust scene understanding
Generative AI: Text-to-image synthesis with precise instance control and counting
Action Recognition: Actor-agnostic video understanding using multi-modal queries
Object Counting: Multi-label counting with semantic-geometric priors for real-world applications

Publications

CountLoop: Iterative Agent Guided High Instance Image Generation

Anindya Mondal, Ayan Banerjee, Sauradip Nag, Josep Llàdos, Xiatian Zhu, Anjan Dutta

Under Review

PDF Surrey Project Page

OmniCount: Multi-label Object Counting with Semantic-Geometric Priors

Anindya Mondal, Sauradip Nag, Xiatian Zhu, Anjan Dutta

AAAI 2025

DOI Project Page

Actor-agnostic Action Recognition thumbnail

Actor-agnostic Multi-label Action Recognition with Multi-modal Query

Anindya Mondal, Sauradip Nag, Joaquin M. Prada, Xiatian Zhu, Anjan Dutta

ICCVW 2023

DOI Code

Time-varying Signals Recovery via Graph Neural Networks

JAC Correa, JH Giraldo, Anindya Mondal et al.

ICASSP 2023

PDF DOI

Recovery of Missing Sensor Data thumbnail

Recovery of Missing Sensor Data by Reconstructing Time-varying Graph Signals

Anindya Mondal et al.

EUSIPCO 2022

PDF DOI Code

Moving Object Detection for Event-based Vision using Graph Spectral Clustering

Anindya Mondal, R. Shashant et al.

ICCVW 2021

PDF DOI Code

News

Jan 2025: Paper on multi-label object counting accepted at AAAI 2025! 🎉
Dec 2024: Awarded AAAI 2025 Conference Travel Grant (worth $1200)
Oct 2023: Presented our work on actor-agnostic action recognition at ICCV Workshop 2023 in Paris
Sep 2022: Started PhD at University of Surrey with full studentship funding

Education

PhD in Computer Vision and AI (2022 – Present)
University of Surrey, UK
Surrey Institute for People-Centred AI (CVSSP)
Advisors: Dr. Anjan Dutta, Dr. Xiatian Zhu, and Dr. Joaquin M. Prada

Awards & Recognition

AAAI 2025 Conference Travel Grant (worth $1200), Philadelphia, USA
ICCV 2023 Conference Grant, Paris, France
University of Surrey Postgraduate Studentship (2022 – 2025), Full PhD funding
Uplink Research Internship Award, ACM SIGKDD India Chapter

Teaching

2023 – 2025: Teaching Assistant for Applied Machine Learning (EEEM068), Advanced Topics in Computer Vision and Deep Learning (EEEM071), and UKRI Centre for Doctoral Training (CDT) at the University of Surrey

Academic Service

Peer Reviewer: ICASSP, ICCV, CVPR, ECCV, NeurIPS, ICPR, IEEE Transactions on Signal Processing (TSP), IEEE Transactions on Signal and Information Processing over Networks (TSIPN)