Anirudh Jamkhandi
Papers
1
Total Citations
21
H-Index
1
About
Anirudh Jamkhandi is a researcher at the forefront of computer vision and human motion modeling, with a focus on generating realistic, long-term interactions between people. His most cited work, "Cross-Conditioned Recurrent Networks for Long-Term Synthesis of Inter-Person Human Motion Interactions" (2020), tackles one of the most challenging problems in sequence modeling: producing coherent, multi-person motion over extended time horizons. By introducing a cross-conditioned recurrent architecture, Jamkhandi enables the synthesis of natural, interactive dynamics—such as two people walking, dancing, or gesturing together—without the drift or collapse that plagues traditional auto-regressive models. This contribution has direct applications in animation, human-robot interaction, and motion-based surveillance, earning 21 citations and establishing a new benchmark for interactive motion generation. His work bridges the gap between single-person motion prediction and the complex, interdependent movements of social interactions, offering a scalable solution for immersive virtual environments and embodied AI. Jamkhandi’s research continues to push the boundaries of how machines understand and generate human behavior, making him a rising voice in the synthesis of realistic, multi-agent motion.
Research Focus
Key Achievements
Top Papers
- 1