Chaitanya Ahuja

Papers

Total Citations

H-Index

About

Chaitanya Ahuja’s research sits at the compelling intersection of natural language processing and computer animation, where he pioneers methods to generate realistic human motion from text. His key contributions focus on grounding language in physical movement, enabling machines to translate descriptive sentences into dynamic poses and gestures. In his highly influential work, “Language2Pose: Natural Language Grounded Pose Forecasting” (2019, 9 citations), Ahuja introduced a framework that transforms natural language commands—specifying actions, speeds, and directions—into coherent animations, with applications ranging from movie script visualization to robot motion planning. Building on this, his paper “Style Transfer for Co-speech Gesture Animation: A Multi-speaker Conditional-Mixture Approach” (2020, 4 citations) advanced the field by modeling how different speakers’ unique gestural styles can be captured and transferred, making virtual characters more expressive and lifelike. Though early in his career, Ahuja’s work has already garnered attention for its novel approach to bridging linguistic semantics and kinematic output. His research not only pushes the boundaries of human-computer interaction but also lays foundational groundwork for future systems in virtual reality, assistive robotics, and automated content creation.