Animashree Anandkumar
Papers
10
Total Citations
325
H-Index
6
About
Animashree Anandkumar is a researcher working at the dynamic intersection of machine learning, computer vision, and surgical robotics, with a particularly compelling focus on transforming how we understand and evaluate human surgical performance. Her most influential contribution — a vision transformer system for decoding surgeon activity from surgical videos (2023, 135 citations) — demonstrates that intraoperative behaviors can be systematically captured and analyzed using state-of-the-art deep learning architectures. Building on this, her work on surgical gestures as quantifiable performance metrics (2022, 54 citations) has helped establish a rigorous paradigm for decomposing complex procedures into measurable, clinically meaningful units. Anandkumar has also addressed the ethical dimensions of AI-driven assessment, showing that human visual explanations can meaningfully reduce bias in automated credentialing systems (2023, 46 citations) — a critical concern as such tools move toward real-world deployment. Beyond the operating room, her research spans uncertainty quantification in deep learning-based pose estimation and reinforcement learning for legged robotics, reflecting a broad command of applied AI. Her cumulative citation record underscores her growing influence in surgical AI, a field with profound implications for patient safety and clinical training.
Research Focus
Key Achievements
Top Papers
- 1A vision transformer for decoding surgeon activity from surgical videos135 citations · 2023
- 2
- 3
- 4Fast Uncertainty Quantification for Deep Object Pose Estimation31 citations · 2021
- 5
- 6Deep Learning to Automate Technical Skills Assessment in Robotic Surgery21 citations · 2021
- 7
- 8
- 9Quantification of Robotic Surgeries with Vision-Based Deep Learning2 citations · 2022
- 10Fast Uncertainty Quantification for Deep Object Pose Estimation2 citations · 2020