Soumya Varma
Papers
1
Total Citations
7
H-Index
1
About
Soumya Varma is a researcher advancing the field of automated video understanding, with a primary focus on deep learning and natural language generation. Her most cited work, "Deep learning-based Video Captioning Technique using Transformer" (2022, 7 citations), introduces a novel approach to automatic video captioning—generating meaningful sentence descriptions from video content. This contribution addresses critical challenges in bridging visual and linguistic data, enabling machines to interpret complex scenes. Varma's research has significant real-world applications, including automatic object identification, real-time calamity detection, and assistive navigation for the visually impaired. By leveraging Transformer architectures, she enhances the accuracy and contextual relevance of generated captions, pushing the boundaries of how AI systems perceive and describe dynamic environments. Her work stands at the intersection of computer vision and natural language processing, offering practical solutions for accessibility and safety. With a growing citation record, Varma is establishing herself as an emerging voice in multimodal AI, dedicated to making video content more interpretable and useful across diverse domains.
Research Focus
Key Achievements
Top Papers
- 1Deep learning-based Video Captioning Technique using Transformer7 citations · 2022