I am a PhD Researcher at the Centre for Vision, Speech and Signal Processing (CVSSP) and the Surrey Institute for People-Centred AI, University of Surrey, Guildford, UK.
My research focuses on building robust vision systems by integrating multi-modal signals — with emphasis on object counting, multi-label action recognition, event-based vision, and text-to-image generation using vision-language and foundation models.
- 📍 Guildford, UK
- 🎓 Teaching Assistant — Applied ML (EEEM068) & Advanced CV and Deep Learning (EEEM071), University of Surrey
- 💼 Open to collaborations, research & industry opportunities
- 📫 anindyam[dot]jan[at]gmail[dot]com
| Paper | Venue | Links |
|---|---|---|
| CountLoop: Training-Free High-Instance Image Generation via Iterative Agent Guidance | Preprint 2025 |    |
| OmniCount: Multi-label Object Counting with Semantic-Geometric Priors | AAAI 2025 |  |
| MSQNet: Actor-agnostic Multi-label Action Recognition with Multi-modal Query | ICCVW 2023 |  |
| TimeGNN: Time-varying Signals Recovery via Graph Neural Networks | ICASSP 2023 |  |
| Recovery of Missing Sensor Data by Reconstructing Time-varying Graph Signals | EUSIPCO 2022 | |
| Moving Object Detection for Event-based Vision using Graph Spectral Clustering | ICCVW 2021 |  |
- 🏆 AAAI 2025 Conference cum Travel Grant — Philadelphia, USA
- 🏆 ICCV 2023 Conference Grant — Paris, France
- 🎓 University of Surrey Postgraduate Studentship (UK)
- 🏅 Uplink Research Internship Award — ACM SIGKDD India Chapter
⭐ If you find my work useful, consider starring the repositories!