About Me

Hi 👋, I am Chengan Che, a PhD researcher in Computer Vision at King’s College London. My research focuses on large-scale dataset curation, video foundation model pretraining, self-supervised video representation learning, and vision-language learning.

I am particularly interested in learning visual representations that capture temporal and procedural structure in complex videos, with applications to surgical artificial intelligence.

News

• [Feb 2026] Four papers accepted to CVPR 2026, including two first-author papers.
• [Nov 2025] Released PL-Stitch, a self-supervised approach for learning procedure-aware video representations.
• [Mar 2025] Released LEMON, a large-scale open-access surgical video dataset containing 4K videos and approximately 85 million frames.

Selected Publications

LEMON: A Large Endoscopic MONocular Dataset and Foundation Model for Perception in Surgical Settings

Chengan Che, Chao Wang, Tom Vercauteren, Sophia Tsoka, Luis C. Garcia-Peraza-Herrera
CVPR 2026
Paper · Code

A Stitch in Time: Learning Procedural Workflow via Self-Supervised Plackett-Luce Ranking

Chengan Che, Chao Wang, Xinyue Chen, Sophia Tsoka, Luis C. Garcia-Peraza-Herrera
CVPR 2026
Paper · Code

Can LLM-Generated Text Empower Surgical Vision-Language Pre-training?

Chengan Che, Chao Wang, Jiayuan Huang, Xinyue Chen, Luis C. Garcia-Peraza-Herrera
CVPR Workshop 2026 AI4RWC, Oral Presentation
Paper · Code

Back to the Feature: Explaining Video Classifiers with Video Counterfactual Explanations

Chao Wang, Chengan Che, Xinyue Chen, Sophia Tsoka, Luis C. Garcia-Peraza-Herrera
CVPR 2026
Paper · Code

Experience

PhD Researcher in Computer Vision

King’s College London, London, UK
October 2023–Present

My research covers large-scale surgical video dataset curation, surgical foundation models, self-supervised video understanding, and vision-language pretraining.

Computer Vision Engineer

Hangzhou Lizhi Network Technology Company, Hangzhou, China
January 2022–July 2023

Developed and deployed object detection and semantic segmentation systems, including real-time inference on NVIDIA Jetson Xavier devices.

Mentoring

Teaching Assistant and Co-Supervisor

King’s College London, London, UK
2024–2025

Co-supervised thesis projects for five MSc and five BSc Computer Science students, supporting experimental design, dataset curation, deep learning implementation, and academic writing.

Served as a Teaching Assistant for the Machine Learning module, leading tutorials, assessing coursework, and providing technical support to undergraduate and postgraduate students.