Shray Gupta
About
Ph.D. scholar in Computer Science and Engineering at DTU. His M.Tech by Research work at DTU focused on hyperspectral image denoising. His research spans hyperspectral-image restoration and classification, explainable AI, and defenses against data-poisoning attacks. He also has prior software and frontend development experience.
Research focus · Hyperspectral Image Restoration and AI Security
Key Projects
3DHyCA hyperspectral denoising
co-developed a 3D convolutional autoencoder combining residual learning and hybrid channel attention to remove mixed noise from hyperspectral images.
Remote Sensing Cube Classification
applied contrastive learning to spectral-spatial feature extraction and hyperspectral cube classification.
Adaptive Multimodal Fusion
developed a network for robust classification using multi-source features.
Risk-Aware Poisoning Defense
developed a machine-learning framework for detecting and mitigating data-poisoning attacks.
Patents
- Shray Gupta, Anurag Goel and Rajeev Kumar, "System and Method for Adaptive Notification Delivery Based on Cognitive Load and Contextual Parameters," Indian patent application 202511069771 A; filed 22 July 2025; published 15 August 2025; applicant: Delhi Technological University.
Publications · 2
- Journal article3D hybrid convolutional autoencoder for hyperspectral image denoisingShray Gupta, Anurag GoelSignal, Image and Video Processing, 20(3), Article 124 · 2026DOI: 10.1007/s11760-026-05174-z ↗
- Conference paperUnveiling Pure Spectra: A Comprehensive Review of Hyperspectral Image Denoising from the Perspective of Explainable AIShray Gupta, Anurag Goel2026 Fourth International Conference on Secure Cyber Computing and Communications (ICSCCC), pp. 189–194 · 2026DOI: 10.1109/ICSCCC69031.2026.11599981 ↗