Research
My research broadly spans the field of computer vision, with specific interests including generative AI, diffusion models, action recognition, person recognition, and representation learning. You can check out my selected papers below, with important papers highlighted.
|
|
DVANet: Disentantgling View and Action Features for Multi-View Action Recognition
Nyle Siddiqui,
Praveen Tirupattur,
Mubarak Shah.
AAAI Conference on Artificial Intelligence, Main Technical Track (AAAI), 2024
paper  /  code  /  project page
We propose a novel transformer decoder-based architecture in tandem with two supervised contrastive losses for multi-view action recognition. By disentangling the view-relevant features from action-relevant features, we enable our model to learn action features that are robust to change in viewpoints. We show that changes in viewpoint impart perturbations on learned action features, and thus, disentangling these perturbations improves overall action recognition performance.
|
|
Machine and Deep Learning Applications to Mouse Dynamics for Continuous User Authentication
Nyle Siddiqui,
Rushit Dave,
Mounika Vanamala,
Naeem Seliya.
MDPI Journal of Machine Learning and Knowledge Extraction (MAKE), 2022
(4th most cited MAKE paper in 2022)
paper    
|
|
DLCR: Leveraging Diffusion and Large Language Models for Effective Clothes-Changing Re-Identification
Nyle Siddiqui,
Alin Croitoru,
Gaurav Kumar Nayak,
Radu Tudor Ionescu,
Mubarak Shah.
Under Review
Currenly under review. We use diffusion to improve clothes-changing person re-identification.
|
Feel free to steal this website's source code. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page.
|
|