Ever since I embarked on my journey in the field of Computer Science, I have been fascinated by the limitless possibilities offered by Computer Vision. My research interests lie primarily in the intersection of deep learning, image understanding, and visual reasoning. I aim to develop novel algorithms and models that can better comprehend the semantic meaning of visual data, enabling machines to reason and make informed decisions based on visual cues. I am particularly interested in exploring techniques that integrate multi-modal information, such as combining visual and textual data to enhance understanding and interpretation. During my undergraduate studies, I taught myself the fundamentals of Computer Vision and its applications. The ability to extract rich information from 2D images and videos was intriguing, but now I also realize that extending this understanding to the 3D world holds immense potential for solving complex real-world problems. I aim to contribute to the development of robust and efficient techniques for object detection and tracking, scene reconstruction, and understanding human-object interactions in 3D space.