Kuldeep Singh Yadav

About

Greetings! I am Dr. Kuldeep S. Yadav, currently working as a Scientist at CSIR–Fourth Paradigm Institute (CSIR-4PI), Bengaluru, and serving as an Assistant Professor at the Academy of Scientific and Innovative Research (AcSIR), India. My work primarily lies at the intersection of data science, computer vision, affective computing, and cybersecurity, where I aim to design intelligent systems for suspiciousness detection, anomaly analysis, and human–computer interaction.

I have successfully completed my Postdoctoral Fellowship in Electrical Engineering at the Indian Institute of Technology Delhi, where I focused on the application of deep learning techniques for real-time suspiciousness estimation and anomaly detection in uncontrolled environments. This experience further strengthened my expertise in developing robust vision-based frameworks that integrate object detection, facial emotion recognition, and behavioral analysis for practical deployments in smart surveillance and security systems.

My academic journey culminated with a Ph.D. in Electronics and Communication Engineering from NIT Silchar, carried out under an SERB-DST project in collaboration with IIT Guwahati. My doctoral research focused on the development of a Deep Learning-based Hand-Gesticulated Character Recognition System for Human–Computer Interaction, involving extensive work in gesture analysis, object detection, segmentation, tracking, and recognition. During this work, I also developed multiple specialized datasets that enabled training of deep learning models from scratch for gesture and gesticulated character recognition. Earlier, I completed my M. Tech in Computer Vision and Image Processing from LNMIIT Jaipur, where I worked on facial expression recognition and sign language recognition using advanced machine learning and feature engineering techniques.

Alongside my academic career, I have gained valuable professional experience. I served as a Young Professional with the Department of Telecommunication, Government of India, where I worked across both research and administrative domains. I was also associated as a Research Fellow under the IMPRINT-II DST, SERB project, contributing to the development of a Disability-Friendly Virtual Text-Entry Keyboard Interface System to aid accessibility under real-world conditions. These experiences allowed me to blend research with societal applications, bridging the gap between theory and practice.

I am passionate about pushing the boundaries of artificial intelligence for security, healthcare, and human–computer interaction.

Employment

• CSIR Fourth Paradigm Institute Scientist
  2025 - Present
• Academy of Scientific and Innovative Research Assistant Professor
  2025 - Present
• Indian Institute of Technology Delhi Postdoc Fellow
  2023 - Present
• Ministry of Communication Young Scientist
  2022 - Present
• National Institute Of Technology Silchar Project Research Fellow
  2019 - 2022

Education

Education history is unavailable.

Projects & Funding

Projects & funding information is unavailable.

Publications (40)

• Brain age group classification based on resting state functional connectivity metrics
  Biomedical Signal Processing and Control 2026 DOI: 10.1016/j.bspc.2026.109617
  +Save
• Towards generalized real-world image super-resolution: an adaptive zero-shot and efficient generative approach for handling unknown degradations
  Neural Computing and Applications 2026 DOI: 10.1007/s00521-026-12263-0
  +Save
• HFLSR: High-Frequency Learning for Stable and Realistic Single Image Super-Resolution
  Iranian Journal of Science and Technology, Transactions of Electrical Engineering 2026
  +Save
• DL-AAT: An Automatic Annotation Tool for Efficient Data Labeling in Vision-Based Systems
  2026 DOI: 10.1007/978-3-032-15809-3_32
  +Save
• FER20E: An Extended Facial Expression Recognition Dataset With 20 Discrete Emotions
  IEEE Transactions on Image Processing 2026 DOI: 10.1109/TIP.2026.3721357
  +Save
• Darknet-Based Threat Intelligence: A Survey of Scanning Detection and Adversary Attribution Methods
  2025 DOI: 10.36227/techrxiv.176531791.10542677/v1
  +Save
• Frequency-aware deep networks and patch-wise generative adversarial training for single image super-resolution in wavelet domain
  Applied Soft Computing 2025 DOI: 10.1016/j.asoc.2025.114035
  +Save
• A Robust and Lightweight Generative Adversarial Network with Zero-Shot Learning for Image Super-Resolution
  2025 National Conference on Communications (NCC) 2025 DOI: 10.1109/ncc63735.2025.10983879
  +Save
• Cross-Cultural Facial Expression Recognition: A Deep Learning Study On Indian Cultural Diversity
  2025 National Conference on Communications (NCC) 2025 DOI: 10.1109/ncc63735.2025.10982913
  +Save
• DASGAN: Degradation Generation and Adaptive GAN Training for Real-World Image Super-Resolution
  2025 IEEE 22nd India Council International Conference (INDICON) 2025 DOI: 10.1109/INDICON68490.2025.11392932
  +Save