My research spans the domains of image/video processing, computer vision, and visual perception. I am currently working on generative AI for visual data, AI/ML for video compression and vision-language models for scene modeling and understanding.
I was an Applied Scientist at Amazon Prime Video, Seattle, Washington, USA between 2022-2023, where I worked on automating the tasks of video content promotion, curation and moderation using data driven machine learning. I received a Ph.D. in Electrical and Computer Engineering from the University of Texas at Austin, Austin, Texas, USA in 2022. At UT Austin, I was part of the Laboratory of Image and Video Engineering, led by Prof. Alan Bovik. During my PhD, I conducted research on developing next generation video coding technologies using deep learning.
-
Convex Hull Prediction for Adaptive Video Streaming by Recurrent Learning by Paul S., Norkin A., Bovik A.C. IEEE Transactions on Image Processing 33 5114-5128 (2024)
-
Self-Supervised Learning of Perceptually Optimized Block Motion Estimates for Video Compression by Paul S., Norkin A. , Bovik A. C. IEEE Transactions on Image Processing 32 617-630 (2022)
-
A Subjective and Objective Study of Space-Time Subsampled Video Quality by Lee D. Y., Paul S. , Bampis C. G., Ko H. , Kim J. , Jeong S. Y., Homan B. , Bovik A. C. IEEE Transactions on Image Processing 31 934-948 (2021)
-
Speeding up VP9 Intra Encoder with Hierarchical Deep Learning Based Partition Prediction by Paul S., Norkin A. , Bovik A. C. IEEE Transactions on Image Processing 29 8134-8148 (2020)
-
Image Statistic Models Characterize Well Log Image Quality by Paul S., Bovik A. C. IEEE Geoscience and Remote Sensing Letters 16 1130-1134 (2019)
-
Deterministic Policy Gradient Based Robotic Path Planning with Continuous Action Spaces by Paul S., Vig L. International Conference on Computer Vision (ICCV) - (2017)
-
Selection of Keyframes for Video Colorization using Steerable Filtering by Paul S., Bhattacharya S. , Gupta S. Sadhana 42 1685-1692 (2017)
-
Spatiotemporal Colorization of Video Using 3D Steerable Pyramids by Paul S., Bhattacharya S. , Gupta S. IEEE Transactions on Circuits and Systems for Video Technology 27 1605-1619 (2016)
-
RAISE: Realness Assessment for Image Synthesis and Evaluation by Mukherjee A., Dubey S., Paul S. Proceedings of the International Conference on Multimedia Information Processing and Retrieval, MIPR 449-455 (2025)
Principal Investigator
- Saliency Aware Quality Assessment and Compression of Visual Data SRIC, IIT KHARAGPUR
- Visual Data Compression Using Quality Guided Generative AI Anusandhan National Research Foundation (ANRF)
Ph. D. Students
Bitan Adak
Area of Research: Visual Data Compression Using Quality Guided Generative AI
Manem Chandra Sekhar Lokesh
Area of Research:
Shamba Chowdhury
Area of Research: