Welcome to my homepage. I am Song Wenfeng (宋文凤), an Associate Professor at Beijing Information Science and Technology University, specializing in digital human generation and reconstruction with a particular emphasis on medical applications. I earned both my Master’s and Doctoral degrees from Beihang University, under the mentorship of Professor Wang Huafeng (王华锋) during my Master’s program and Academician Zhao Qinping (赵沁平) during my Doctoral studies.

My research interests include virtual reality and computer vision with medical applications (e.g., human-scene interaction, medical image analysis) especially in the field of virtual human reconstruction. The experience in the State Key Laboratory of Virtual Reality Technology and System of Beihang motivates my interest and deep understanding of deep learning on Computer-assisted Diagnosis (CAD). My research domain is virtual reality for medical education and environment perception based on deep learning, including object detection based on image and video including unbalance dataset, depth estimation, person reid, UAV tracking.

🔥 News

  • 2024.05:  🎉🎉 One paper is accepted to TVCG.
  • 2024.03:  🎉🎉 Two papers are accepted to CVPR 2024.
  • 2023.12:  🎉🎉 One paper is accepted to AAAI 2024.
  • 2023.12:  🎉🎉 One paper is accepted to TIP.
  • 2023.07:  🎉🎉 One paper is accepted to ICCV 2023.
  • 2023.05:  🎉🎉 One paper is accepted to TVCG.
  • 2023.05:  🎉🎉 One paper is accepted to IJCV.
  • 2023.01:  🎉🎉 One paper is accepted to TPAMI.

📝 Selected Publications

[Full list]

CVPR 2024
sym

HOIAnimator: Generating Text-prompt Human-object Animations using Novel Perceptive Diffusion Models

Wenfeng Song, Xinyu Zhang, Shuai Li, Yang Gao, Aimin Hao, Xia Hou, Chenglizhao Chen, Ning Li, Hong Qin

Github

CVPR 2024
sym

Arbitrary Motion Style Transfer with Multi-condition Motion Latent Diffusion Model

Wenfeng Song, Xingliang Jin, Shuai Li, Chenglizhao Chen, Aimin Hao, Xia Hou, Ning Li, Hong Qin

Github

AAAI 2024
sym
TIP
sym

Rethinking Object Saliency Ranking: A Novel Whole-Flow Processing Paradigm

Mengke Song, Linfeng Li, Dunquan Wu, Wenfeng Song, Chenglizhao Chen

Github

ICCV 2023
sym

Sequential texts driven cohesive motions synthesis with natural transitions

Shuai Li, Sisi Zhuang, Wenfeng Song*, Xinyu Zhang, Hejia Chen, Aimin Hao

Github

TVCG
sym

FineStyle: Semantic-Aware Fine-Grained Motion Style Transfer with Dual Interactive-Flow Fusion

Wenfeng Song, Xingliang Jin, Shuai Li*, Chenglizhao Chen, Aimin Hao, Xia Hou

Github

IJCV
sym

Automatic generation of 3d scene animation based on dynamic knowledge graphs and contextual encoding

Wenfeng Song, Xinyu Zhang, Yuting Guo, Shuai Li, Aimin Hao, Hong Qin

Github

PR
sym

Dynamic attention augmented graph network for video accident anticipation

Wenfeng Song, Shuai Li*, Tao Chang, Ke Xie, Aimin Hao, Hong Qin

Github

TMM
sym

Joints-Centered Spatial-Temporal Features Fused Skeleton Convolution Network for Action Recognition

Wenfeng Song, Tangli Chu, Shuai Li*, Nannan Li, Aimin Hao, Hong Qin

Github

TIP
sym

Context-interactive CNN for person re-identification

Wenfeng Song, Shuai Li, Tao Chang, Aimin Hao, Qinping Zhao, Hong Qin

Github

📖 Educations

  • 2015.09- 2020.08, Ph.D, Beihang University, Beijing
  • 2012.09 - 2015.03, Master, Beihang University, Beijing