News

• [2025/2]: A first-authored paper has been accepted by CVPR 2025 as Highlight.
• [2025/1]: A co-authored paper has been accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI, Top1 CV Journal).
• [2024/07]: A first-authored paper has been accepted by ACM SIGGRAPH Asia 2024 (Oral).
• [2024/06]: Invited talk at University of Cambridge Selwyn College.
• [2023/08]: A first-authored paper has been accepted by IEEE Transaction on Image Processing (Top Journal).
• [2023/07]: Invited talk at TechBeat platform.
• [2023/02]: A co-first-authored paper has been accepted by CVPR2023.
• [2023/02]: A co-first-authored paper has been accepted by Neurocomputing.
• [2020/12]: I am honored to be a three-star member of Shenghan High IQ Club .

Education

University of Cambridge
Department of Computer Science and Technology
Ph.D. Student

October 2023 - Present

Stanford University
Computer Science Department
Non-degree Undergraduate Student
On-site Research Intern (UVRI Intern)

January 2022 - June 2023

Fudan University
Intelligent Science and Technology (excellent class)
Undergraduate Student
GPA: 3.92/4.0; Ranking: 1/245

September 2019 - June 2023

Publications

(* indicates equal contribution)

---

Yancheng Cai, Fei Yin, Dounia Hammou, Rafał K. Mantiuk
Do computer vision foundation models learn the low-level characteristics of the human visual system?
CVPR 2025, Accepted - Highlight (Top 2% of submissions)
[Arxiv Paper] [Project] [Code] [Results]

Yancheng Cai, Ali Bozorgian, Maliha Ashraf, Robert Wanat, Rafał K. Mantiuk
elaTCSF: A Temporal Contrast Sensitivity Function for Flicker Detection and Modeling Variable Refresh Rate Flicker
SIGGRAPH Asia 2024, Accepted (With Strong Accept)
[Project] [Paper]

---

Yancheng Cai*, Stephen Tian*, Hong-Xing Yu, Sergey Zakharov, Katherine Liu, Adrien Gaidon, Yunzhu Li, Jiajun Wu
Multi-object manipulation via object-centric neural scattering functions
CVPR 2023, Published (With two Strong Accepts)
[Project] [Paper]

---

Yancheng Cai, Bo Zhang, Baopu Li, Tao Chen, Hongliang Yan, Jingdong Zhang, Jiahao Xu
Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-free One-Stage Detectors
TIP (IEEE Transactions on Image Processing), Published
[IEEE paper] [知乎]

---

Jingdong Zhang, Peng Ye, Bo Zhang, Hancheng Ye, Baopu Li, Yancheng Cai, Tao Chen
BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-Task Dense Predictions
TPAMI (IEEE Transactions on Pattern Analysis and Machine Intelligence), Published
[IEEE paper]

---

Lei Lu*, Yancheng Cai*, Hua Huang, Ping Wang
An efficient fine-grained vehicle recognition method based on part-level feature optimization
Neurocomputing, Published
[paper]

---

Research Experience

• January 2022 - June 2023, Research Assistant, Stanford Vision and Learning Lab
  Advisors: Prof. Jiajun Wu, Prof. Yunzhu Li.
• October 2020 - June 2023, Research Assistant, Fudan Embedded Deep Learning and Visual Analysis Lab
  Advisors: Prof. Tao Chen.

Selected Award

• 2022 China National Scholarship (The highest honorable national scholarship to Chinese students). (0.2%)
• 2020 China National Scholarship (The highest honorable national scholarship to Chinese students). (0.2%)
• 6th place in the China Finals of the Advanced Driver Assistance Systems Competition (ADAS) held by Dell.
• Top Ten Students in School of Information Science and Technology, Fudan University. (1%)
• Fudan University Individual Award for Scientific Research. (0.5%)

Academic Service

• Journal Reviewer: T-PAMI
• Conference Reviewer: CVPR 2023, CVPR 2022, ECCV 2022