Ning Xu | Artificial Intelligence | Best Researcher Award

Assoc Prof Dr. Ning Xu | Artificial Intelligence | Best Researcher Award

Tianjin University | China

PUBLICATION PROFILE

Google Scholar

πŸ‘¨β€πŸ« Summary

Assoc. Prof. Dr. Ning Xu is currently serving at the School of Electrical and Information Engineering, Tianjin University, China. He specializes in the fields of computer vision and artificial intelligence, with key research spanning Image Captioning, Text-to-Image Generation, Visual Question Answering, Visual Dialog, Scene Graph Generation, and Causality. His work is widely recognized, having been published in top-tier journals and conferences such as IEEE TIP, TKDE, TNNLS, TCYB, TMM, TCSVT, IJCAI, and ACM MM.

πŸŽ“ Education

Dr. Xu earned his Ph.D. in Electrical and Information Engineering from Tianjin University in 2019 under the supervision of Prof. An-An Liu. He completed his Bachelor of Engineering at Hainan University (Advanced Class) in 2013, advised by Prof. Yong Bai.

πŸ’Ό Professional Experience

From 2016 to 2017, he was a visiting scholar at the SeSaMe Research Centre, National University of Singapore, collaborating with Dr. Yongkang Wong. He now holds the title of Associate Professor at Tianjin University and is an active member of the Institute of Television and Image Information.

πŸ“š Academic Citations

Dr. Xu’s research has led to publications in top academic venues and the granting of two U.S. patents in the area of visual relationship detection, highlighting his contributions to region-aware and adaptive clustering learning methods.

πŸ› οΈ Technical Skills

His expertise covers deep learning, computer vision, image understanding, and multi-modal reasoning, with strong implementation experience in frameworks such as PyTorch and TensorFlow.

πŸ‘¨β€πŸ« Teaching Experience

At Tianjin University, he actively teaches and mentors both undergraduate and postgraduate students, focusing on AI, image processing, and machine learning courses.

πŸ” Research Interests

His research interests include but are not limited to Image Captioning, Text-to-Image Generation, Visual QA, Visual Dialog, Scene Graph Generation, and Causality, with a focus on developing interpretable and intelligent vision-language systems.

πŸ“š Top Notes Publications

1. Adaptively clustering-driven learning for visual relationship detection

  • Authors: Liu, A.A.; Wang, Y.; Xu, N.; Nie, W.; Nie, J.; Zhang, Y.

  • Journal: IEEE Transactions on Multimedia

  • Year: 2020

2. 3D Model classification based on few-shot learning

  • Authors: Nie, J.; Xu, N.; Zhou, M.; Yan, G.; Wei, Z.

  • Journal: Neurocomputing

  • Year: 2020

3. Image Captioning with multi-level similarity-guided semantic matching

  • Authors: Li, J.; Xu, N.; Nie, W.; Zhang, S.

  • Journal: Visual Informatics

  • Year: 2021

4. Part-aware interactive learning for scene graph generation

  • Authors: Tian, H.; Xu, N.; Liu, A.A.; Zhang, Y.

  • Journal: Proceedings of the 28th ACM International Conference on Multimedia

  • Year: 2020

5. Mask and predict: Multi-step reasoning for scene graph generation

  • Authors: Tian, H.; Xu, N.; Liu, A.A.; Yan, C.; Mao, Z.; Zhang, Q.; Zhang, Y.

  • Journal: Proceedings of the 29th ACM International Conference on Multimedia

  • Year: 2021