Sujata Kulkarni

Papers

Total Citations

H-Index

About

Sujata Kulkarni is a rising researcher at the intersection of artificial intelligence and human-computer interaction, with a focused expertise in multimodal affect recognition. Her work centers on developing deep learning frameworks that can perceive and interpret human emotions from real-world, audio-visual data. Kulkarni’s major contribution is the creation of the Multimodal Diverse Spatio-Temporal Network (MDSTN), a low-complexity architecture designed to overcome the limitations of unimodal approaches—such as relying solely on speech or visual cues—which often fail in dynamic, uncontrolled environments. Her research demonstrates that integrating multiple modalities significantly improves the robustness of affect recognition, with direct applications in healthcare, assistive robotics, stress and depression assessment, and even early detection of Alzheimer’s disease. Though early in her career, her two most-cited papers from 2024 and 2025 have each garnered 2 citations, signaling growing interest in her work. Kulkarni’s findings are particularly notable for their emphasis on real-world applicability, moving affect recognition from lab settings to practical, human-centered systems. Her ongoing contributions promise to enhance how machines understand and respond to human emotional states, making her a researcher to watch in the evolving field of affective computing.