A repository for surgical action triplet dataset. Data are videos of laparoscopic cholecystectomy that have been annotated with <instrument, verb, target> labels for every surgical fine-grained activity.

[IPCAI'24 Best Paper] Advancing Surgical VQA with Scene Graph Knowledge

Official repository for "Dissecting Self-Supervised Learning Methods for Surgical Computer Vision"

SurgLaVi: Official repository

[MICCAI'22] AutoLaparo: A New Dataset of Integrated Multi-tasks for Image-guided Surgical Automation in Laparoscopic Hysterectomy

Collated a list of useful open-access work related to surgical phase recognition and surgical skills and workflow analysis.

Visualization of dataset splits for surgical phase and instrument recognition

[MIDL 2026] - Official repo for the paper: "SurgeNetDINO: Towards Effective Surgical Representation Learning with DINO Models""

A curated list of surgical AI resources (continually updated)

Application for reviewing and annotating frames with critical view of safety (CVS) criteria and other relevant information

Surgical Gesture Recognition Using Multi-Encoder Based Architecture.

FASTRL is a a set of benchmark tasks used in surgical training which are adapted to the reinforcement learning setting for the purpose of training agents capable of providing assistance to the surgical trainees. The benchmark is provided with the purpose of exploring the domain of human-centric teaching agents within the learning-to-teach formalism

Two open-source web tools for annotating surgical video: frame-annotator (clip classification) and surgical-annotator (multi-task masks, keypoints & phases). Built for trustworthy, reproducible surgical-AI datasets (MICCAI 2026 SafeSurg).

SpatioTemporalRDV: A modular, spatio-temporal architecture (ResNet-18 + TCN) for surgical action triplet recognition on the CholecT50 dataset. Optimized for consumer hardware.

🚀 Accelerate reinforcement learning for language models with FastRL, leveraging innovative techniques to enhance training efficiency and reduce bottlenecks.