Industry Experiences

• Researcher at Bytedance AML,  2023.01~Now

• Research Intern at Amazon AWS，collaborate with Yi Zhu & Mu Li  2022.07~2022.12

• Research Intern at MSRA (Beijing)，collaborate with Chenfei Wu & Nan Duan  2020.12~2021.12

• Research Intern at Tencent AI Lab (shenzhen)，collaborate with Lin Ma,    2020.05~2020.11

Publication

• HOICLIP: Efficient Knowledge Transfer for HOI Detection with Visual Linguistic Model              Shan Ning*,  Longtian Qiu*,  Yongfei Liu and Xuming He    CVPR2023
• Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning [paper]                                Bo Wan*, Yongfei Liu*, Tinne Tuytelaars and Xuming He    ICLR2023
• Intention-aware Feature Propagation Network for Interactive Segmentation  [paper]                                                       Chuyu Zhang, Chuanyang Hu, Yongfei Liu, and Xuming He    In submission
• VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers [paper]           Meng Du, Estelle Guez Aflalo, Shao-Yen Teng, Yongfei Liu,  Chenfei Wu,  Nan Duan and Vasudev Lal    CVPR2022 best demo award                      This work was done when Yongfei was a research intern at MSRA  
• KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation  [paper] Yongfei Liu, Chenfei Wu, Shao-yen Tseng, Vasudev Lal, Xuming He  and  Nan Duan    NAACL2022
  This work was done when Yongfei was a research intern at MSRA                                                                                                                                                                                                                                                                                                             

• GEM: A General Evaluation Benchmark for Multimodal Tasks [paper] [dataset][leaderboard]

• Relation-aware Instance Refinement for Weakly-Supervised Visual Grounding [paper][code][video][poster][slides]

• Part-aware Prototype Network for Few-shot Semantic Segmentation [paper][code] [video] [slides]

• Learning Cross-modal Context Graph for Visual Grounding [paper] [code] [poster]

• Pose-aware Multi-level Feature Network for Human Object Interaction Detection (oral) [paper] [code]