I am a PhD Researcher specializing in Computer Vision and Multimodal Video Understanding, with a research focus on object detection, feature representation, and scene understanding from video. My work explores the learning and application of visual and multimodal representations to develop robust and generalizable systems for understanding complex real-world visual environments.
Alongside my research, I bring 3+ years of industry experience in software development, with a strong focus on system development using Django and FastAPI. I have hands-on experience with MySQL, PostgreSQL, Docker, CI/CD, Git, AWS, and Azure, developing and deploying scalable software solutions.
I am passionate about advancing intelligent visual systems through rigorous research, practical experimentation, and interdisciplinary collaboration. I am open to research collaborations, academic opportunities, and industry projects in computer vision, multimodal learning, video understanding, and related areas.
Research activities in computer vision, deep learning, video understanding, and intelligent visual systems.
Worked on Python-based software development and IoT-based systems.
Developed and maintained Python-based applications and backend systems.
Worked on full-stack web application development and backend systems.
Full-stack development involving web applications, backend services, and database systems.
I am open to research collaborations, academic opportunities, and industry projects in computer vision, multimodal learning, video understanding, and related areas.