Gaurvi Goyal

Papers

Total Citations

H-Index

About

Gaurvi Goyal is a researcher in computer vision and human action recognition, with a particular focus on multimodal datasets and view-invariant analysis. Her most cited work, "The MoCA dataset, kinematic and multi-view visual streams of fine-grained cooking actions" (2020, 22 citations), introduces a pioneering bi-modal dataset that captures both Motion Capture (MoCap) data and multi-view video sequences—including an ego-like perspective—of fine-grained upper body cooking actions. This contribution is significant because it enables researchers to investigate how actions appear invariant across different viewpoints, a critical challenge for real-world applications like robotics, augmented reality, and activity understanding. By providing synchronized kinematic and visual streams, Goyal’s work bridges the gap between motion analysis and computer vision, offering a benchmark for studying action properties that remain consistent regardless of camera angle. Her research impacts fields ranging from human-computer interaction to sports science, where understanding movement from multiple perspectives is essential. Goyal’s dataset has become a valuable resource for advancing view-invariant action recognition, demonstrating her ability to create foundational tools that drive further innovation in the field.