Qianqian Xiong

Papers

Total Citations

113

H-Index

About

Qianqian Xiong is a leading researcher in computer vision and deep learning, with a primary focus on human action recognition and video understanding. Her most influential work, the "Transferable two-stream convolutional neural network for human action recognition" (2020), has garnered 113 citations, establishing her as a key contributor to the field. In this seminal paper, Xiong introduced a novel architecture that integrates spatial and temporal streams with transfer learning, significantly improving the accuracy and generalization of action recognition models across diverse datasets. Her contributions address critical challenges in video analysis, such as handling complex motion patterns and reducing domain shift, making her methods widely adopted in both academic research and practical applications like surveillance and human-computer interaction. Beyond this flagship work, Xiong’s research extends to efficient neural network design and multi-modal learning, consistently pushing the boundaries of how machines interpret human behavior. Her innovative approach and high-impact publications have made her a respected voice in the computer vision community, inspiring students and researchers to explore the intersection of transfer learning and spatiotemporal modeling.