Yuming Shen

University of East Anglia

Papers

1

Total Citations

5

H-Index

1

About

Yuming Shen is a leading researcher in artificial intelligence, specializing in vision-language understanding and cross-modal retrieval. His work addresses a critical challenge in AI: bridging the semantic gap between visual and textual data, particularly when training data is scarce. In his seminal paper, "Semi-supervised vision-language mapping via variational learning" (2017, 5 citations), Shen pioneered a variational approach to learn joint representations from limited labeled examples, enabling more robust image-sentence matching. This foundational contribution has influenced subsequent work in semi-supervised and few-shot learning for multimodal systems. Shen’s research is widely cited for its practical implications in robotic perception and autonomous systems, where efficient cross-modal understanding is essential. His innovative use of variational inference to tackle data scarcity has made him a notable figure in the field, with his work continuing to inspire new methods for scalable, data-efficient AI.

Research Focus

Key Achievements

1
H-Index
1
Papers
5
Total Citations
5
Avg Citations/Paper
🏆 Most Cited Paper
Semi-supervised vision-language mapping via variational learning
5 citations · 2017
📈 Most Prolific Year: 2017 (1 Papers)
🤝 Key Collaborators: 2
🏛 Institutions: University of East Anglia

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 11 days ago