Wenbin Wang is currently an Assistant Professor in College of Computer and Information Technology, China Three Gorges University. Previously, he obtained his Ph.D. degree in the Key Lab. of Intelligent Information Processing (IIP) at Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), advised by Prof. Xilin Chen and Prof. Ruiping Wang. Before this, he received his B.Eng. degree in Computer Science and Technology from Nankai University (NKU, 2013-2017). His research interests include but not limited to scene understanding, object detection, scene graph generation, and AIGC.

🔥 News

  • 2024.12:  🎉🎉 One paper is accepted by The Visual Computer (CCF-C). This is the first work on AIGC of our group.
  • 2024.11:  🎉🎉 Wenbin Wang is awarded the Nomination Award in the Doctoral Dissertation Incentive Program by the China Society of Image and Graphics (CSIG).
  • 2024.06:  🎉🎉 One paper on fine-grained SGG co-authored with Prof. Y. Li, Wuhan University, is accepted by ECCV 2024. Congrats!
  • 2023.05:  🎉🎉 One paper on hierarchical SGG (SGoI) is accepted by International Journal of Computer Vision (IJCV) 2023.
  • 2022.07:  🎉🎉 One paper is accepted by SCIENTIA SINICA Informationis.
  • 2021.07:  🎉🎉 One paper on SGG and image captioning is accepted by ICCV 2021.
  • 2020.07:  🎉🎉 One paper on hierarchical scene graph generation is accepted by ECCV 2020.
  • 2019.03:  🎉🎉 One paper on visual relationship detection is accepted by CVPR 2019.

📝 Publications

IJCV 2023
sym

Importance First: Generating Scene Graph of Human Interest

Wenbin Wang, Ruiping Wang, Shiguang Shan, Xilin Chen

  • There exists a hierarchical preference about human perception when they analyze a natural scene.
  • SGoI (Scene Graph of Human Interest) generation framework is proposed to present the scene graph according to the content importance.
  • CODE release: TGIR
ICCV 2021
sym

Topic Scene Graph Generation by Attention Distillation from Caption

Wenbin Wang, Ruiping Wang, Xilin Chen

  • Scene graph generation and image captioning can be viewed as two forms of scene understanding.
  • A shared framework that jointly generates scene graph and image caption is proposed in this work.
  • CODE release: MMSceneGraph : an SGG toolkit based on MMdetection, including most SOTA SGG methods.

🎖 Honors and Awards

  • Nomination Award of the Doctoral Dissertation Incentive Program, China Society of Image and Graphics (中国图象图形学学会博士学位论文激励计划提名奖), 2024.
  • Chutian Scholar Talent Program of Hubei Province (湖北省“楚天学子”人才计划).

📖 Educations

  • 2017.09 - 2022.09, Ph.D., Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China.
  • 2013.09 - 2017.06, Undergraduate, Nankai University, Tianjin, China.

🎓 Team Members

📚 Academic Services

  • Invited journal reviewer for IEEE TPAMI / IEEE TMM / PR / ESWA
  • Invited conference reviewer for CVPR / ICCV / ECCV / NeurIPS
  • Member of the Intelligent Service Professional Committee, Chinese Association for Artificial Intelligence (CAAI)(人工智能学会智能服务专业委员会委员)
  • Member of CCF, CSIG

📁 Fundings

  • Research on scene graph generation with multi-scale spatial and multi-granularity semantic features. Natural Science Foundation of HuBei Province (Grant No. 2024AFB283), 2024.03~2026.03
  • Research on semantic analysis of remote sensing scenes based on scene graph. Science Foundation of China Three Gorges University (Grant No. 2023RCKJ0022), 2023.10~2026.10

📚 Teaching

  • Graduate courses
    • Academic norms and writings, Fall, 2024
  • Undergraduate courses