PeopleofSuperintelligence

Researcher

Jinshi Cui

Also known as 崔锦实

Jinshi Cui is a computer vision researcher at Peking University whose work spans people tracking, children's behavior and emotion recognition in conversation. Early papers with Huijing Zhao and Ryosuke Shibasaki tracked multiple people with laser scanners and video, including a 2006 CVPR paper that fused detection-based and matching-based approaches. Later papers turned to children, from a 2010 study of child-adult interactive behaviors in video to a 2013 gaze-estimation paper on peer play and a 2019 paper on predicting infant attachment from vision and audio features. In 2021, they coauthored three papers with Hanzhe Hu and Liwei Wang on few-shot object detection and semantic segmentation, and in 2023 they coauthored BERT-ERC, a model for emotion recognition in conversation. Cui is an associate professor in Peking University's School of Intelligence Science and Technology, with research areas in multimodal data fusion, computer vision and interdisciplinary research in psychology.

Timeline

  1. 2005

    Tracking people with laser and vision

    In 2005, they coauthor "Tracking multiple people using laser and vision" with Hongbin Zha, Huijing Zhao and Ryosuke Shibasaki. The paper appears in the proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems in Edmonton.

  2. 2006

    People tracking at CVPR

    In 2006, they coauthor "Fusion of Detection and Matching Based Approaches for Laser Based Multiple People Tracking" with Huijing Zhao and Ryosuke Shibasaki for CVPR. The paper fuses detection-based and matching-based approaches for laser-based tracking of multiple people.

  3. 2007–2008

    Multi-modal people tracking

    In 2007, they coauthor "Laser-based detection and tracking of multiple people in crowds" in Computer Vision and Image Understanding. In 2008, the same group of Cui, Hongbin Zha, Huijing Zhao and Ryosuke Shibasaki publishes "Multi-modal tracking of people using laser scanners and video camera" in Image and Vision Computing.

  4. 2010–2013

    Children's behavior in video

    In 2010, they coauthor "Visual analysis of child-adult interactive behaviors in video sequences" for the 16th International Conference on Virtual Systems and Multimedia. In 2013, they coauthor "Gaze Estimation in Children's Peer-Play Scenarios" with Li Wang, Hongbin Zha and Hamid K. Aghajan for the 2nd IAPR Asian Conference on Pattern Recognition in Naha, Japan.

  5. 2019

    Predicting infant attachment

    In 2019, they coauthor "Infant Attachment Prediction Using Vision and Audio Features in Mother-Infant Interaction" with Honggai Li, Li Wang and Hongbin Zha. The paper appears in the revised selected papers of the 5th Asian Conference on Pattern Recognition, held in Auckland, New Zealand.

  6. 2021

    Few-shot detection and segmentation

    In 2021, they coauthor three papers with Hanzhe Hu and Liwei Wang: "Dense Relation Distillation With Context-Aware Aggregation for Few-Shot Object Detection" at CVPR, "Region-Aware Contrastive Learning for Semantic Segmentation" at ICCV, and "Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning" at NeurIPS. The CVPR paper proposes DCNet, which tackles few-shot detection of novel classes from only a few annotated examples.

  7. 2023

    Emotion recognition with BERT-ERC

    In 2023, they coauthor "BERT-ERC: Fine-Tuning BERT Is Enough for Emotion Recognition in Conversation" with authors from Peking University and Xiaomi AI Lab, in the Proceedings of the AAAI Conference on Artificial Intelligence. The BERT-ERC model moves contextual and dialogue-structure information into the fine-tuning step of a pretrained language model and improves results on four datasets.

  8. As of October 2026

    Associate professor at Peking University

    Cui is an associate professor in the School of Intelligence Science and Technology at Peking University. Their listed research areas are multimodal data fusion, computer vision and interdisciplinary research in psychology.

  1. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Peking University. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  2. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Peking University. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  3. Companies supply the most prior-work hires at 7 of the 9 frontier AI labsIncludes Peking University. Our estimates of the organizations where 550 people worked directly before joining 9 frontier AI labs across 620 career transitions, comparing the main feeder organizations per lab.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Peking University. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Jinshi Cui yet. Send us a free-licensed photo.

  1. Tracking multiple people using laser and vision. - OI Wiki PKU Scholar pkuscholar.onrender.com. Checked 21 October 2026.
  2. Fusion of Detection and Matching Based Approaches for Laser Based Multiple People Tracking | ML Anthology mlanthology.org. Checked 21 October 2026.
  3. Jinshi Cui - Google Scholar scholar.google.com. Checked 21 October 2026.
  4. Multi-modal tracking of people using laser scanners and video camera. - OI Wiki PKU Scholar pkuscholar.onrender.com. Checked 21 October 2026.
  5. Gaze Estimation in Children's Peer-Play Scenarios. - OI Wiki PKU Scholar pkuscholar.onrender.com. Checked 21 October 2026.
  6. Infant Attachment Prediction Using Vision and Audio Features in Mother-Infant Interaction. - OI Wiki PKU Scholar pkuscholar.onrender.com. Checked 21 October 2026.
  7. Dense Relation Distillation With Context-Aware Aggregation for Few-Shot Object Detection - CVPR 2021 Open Access Repository openaccess.thecvf.com. Checked 21 October 2026.
  8. Region-Aware Contrastive Learning for Semantic Segmentation - ICCV 2021 Open Access Repository openaccess.thecvf.com. Checked 21 October 2026.
  9. Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning proceedings.neurips.cc. Checked 21 October 2026.
  10. BERT-ERC: Fine-Tuning BERT Is Enough for Emotion Recognition in Conversation | Proceedings of the AAAI Conference on Artificial Intelligence ojs.aaai.org. Checked 21 October 2026.
  11. Jinshi Cui - 北京大学人工智能研究院 ai.pku.edu.cn. Checked 21 October 2026.