My long-term research goal is to develop machine learning algorithms for solving computer vision problems with human-like efficiency and adaptability. In my doctoral research, I have been mainly working on distance metric learning methods for person re-identification in video surveillance cameras. My current research focus is on zero-shot learning, few-shot learning, self-supervised learning as well as the intersection of vision and language.
Publications/Preprints
Maximum Margin Metric Learning Over Discriminative Nullspace for Person Re-Identification T M Feroz Ali, Subhasis Chaudhuri European Conference on Computer Vision (ECCV), Munich, Germany, September 2018.
@inproceedings{ali2018maximum,
title={Maximum Margin Metric Learning over Discriminative Nullspace for Person Re-identification},
author={Ali, T M Feroz and Chaudhuri, Subhasis},
booktitle={Proceedings of the European Conference on Computer Vision},
year={2018},
organization={Springer}
}
Theoretical analysis of Null Foley-Sammon Transform and its Implications T M Feroz Ali, Subhasis Chaudhuri
(under review) IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).
A Semi-Supervised Maximum Margin Metric Learning Approach for Small Scale Person Re-identification T M Feroz Ali, Subhasis Chaudhuri IEEE International Conference on Computer Vision workshop (ICCVw), Seoul, Korea, October 2019.
@inproceedings{t2019semi,
title={A semi-supervised maximum margin metric learning approach for small scale person re-identification},
author={T Ali, M Feroz and Chaudhuri, Subhasis},
booktitle={Proceedings of the IEEE International Conference on Computer Vision Workshops},
year={2019}
}
Multiple Kernel Fisher Discriminant Metric Learning for Person Re-identification T M Feroz Ali, Kalpesh K Patel, Rajbabu Velmurugan,
Subhasis Chaudhuri ACM Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP), Hyderabad, India, December 2018.
@article{ali2019multiple,
title={Multiple kernel fisher discriminant metric learning for person re-identification},
author={Ali, TM and Patel, Kalpesh K and Velmurugan, Rajbabu and Chaudhuri, Subhasis},
journal={arXiv preprint arXiv:1910.03923},
year={2019}
}
Cross-View Kernel Similarity Metric Learning Using Pairwise Constraints for Person Re-identification T M Feroz Ali, Subhasis Chaudhuri
ACM Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP), Jodhpur, India, December 20-21.
@article{ali2019cross,
title={Cross-View Kernel Similarity Metric Learning Using Pairwise Constraints for Person Re-identification},
author={Ali, TM and Chaudhuri, Subhasis},
journal={arXiv preprint arXiv:1909.11316},
year={2019}
}
Kernel Maximum Margin Metric Learning for Person Re-identification and Novelty Detection T M Feroz Ali, Subhasis Chaudhuri
(under preparation) IEEE Transactions on Image Processing (TIP).
Multiple Kernel Metric Learning and Dual Cross-view Reciprocal Re-ranking for Person Re-identification T M Feroz Ali, Kalpesh K Patel, Rajbabu Velmurugan, Subhasis Chaudhuri
(under review) Journal of Visual Communication and Image Representation (JVCIR).
Co-segmentation using a Classification Framework
Avik Hati, T M Feroz Ali, Rajbabu Velmurugan, Subhasis Chaudhuri
Book chapter in Image Cosegmentation, Springer (under preparation).
Maneuvering, Multi-Target Tracking using Particle Filters T M Feroz Ali MTech Thesis, IIT Bombay, July 2012 (PDF)
Awards/Talks
Talk on 'Metric Learning for Person Re-identification' in IIT-HKBU Workshop on Data and Imaging Sciences held on February 2019 at Hong Kong Baptist University, Hong Kong.
Our ECCV 2018 paper invited for *Oral Talk* for ICVGIP 2018 Vision India session, conducted at IIIT Hyderabad. Selected among best papers (authored
primarily by Indian researchers in the last two years) presented at top-tier international vision conferences and journals.
Awarded the prestigious 'Visvesvaraya' PhD fellowship 2015-2019 from Ministry of Electronics and Information Technology (Meity), Government of India.
Services
Reviewer for Visual Computer: International Jouranl of Computer Graphics), Springer.
Reviewer for National Conference on Communication NCC-2015 and NCC-2021).