About Me

• PhD student at Stony Brook University, NY, USA advised by Michael Ryoo.
• Former Research Intern at Apple with Jonathon Shlens.
• Former Research Assistant at MBZUAI with Salman Khan and Muzammal Naseer.
• B.Sc. from University of Moratuwa (graduated 2020), with thesis on Multi-Object Tracking and Panoptic Segmentation advised by Ranga Rodrigo and Sadeep Jayasumana.
• Interested in Computer Vision and Machine Learning with focus on the subdomains of Self-Supervised Learning, Cross-Modal Interpretable Representations, and Video Analysis.
• Enjoy poetry, dancing, and theatre during my leisure time.

Have a look at my resume for more details.

Updates

• Language-based Video Self-Supervised Learning accepted to NeurIPS 2023!
• Our paper Perceptual Grouping in Contrastive VLMs accepted to ICCV 2023!
• Work on Diffusion Illusions wins best demo award at CVPR 2023!
• T2I Diffusion Models are Zero-Shot Segmentors presented at CVPR workshop 2023.

Publications

• May 2023: Language-based Video Self-Supervised Learning, NeurIPS 2023.
• November 2022: T2I Diffusion Models are Zero-Shot Segmentors, CVPR workshop 2023.
• October 2022: Perceptual Grouping in Contrastive VLMs, ICCV 2023.
• November 2021: Self-supervised Video Transformers, CVPR 2022 (oral).
• July 2021: Adversarial Transferability of Vision Transformers, ICLR 2022 (spotlight).
• May 2021: Intriguing Properties of Vision Transformers, NeurIPS 2021 (spotlight).
• March 2021: Orthogonal Projection Loss, ICCV 2021.
• January, 2021: Conditional Generative Modeling, ICLR 2021.
• September, 2020: Panoptic Segmentation, BMVC 2020 (oral).
• September 2019: Activity Recognition in Videos, TCSVT journal.