cataract dataset; PSI-AVA dataset
收藏资源简介:
本文中使用的数据集包括南方科技大学可信自主系统研究所和伯明翰大学计算机科学学院共同创建的白内障手术视频数据集,以及公开可用的PSI-AVA数据集。这些数据集用于训练和评估提出的HCT网络在手术场景的多层次语义理解方面的性能。数据集涵盖了手术的不同阶段、步骤、动作和仪器的识别,旨在提高手术辅助系统的上下文感知能力。
The datasets used in this paper include the cataract surgery video dataset jointly created by the Institute of Trusted Autonomous Systems of Southern University of Science and Technology and the School of Computer Science of the University of Birmingham, as well as the publicly available PSI-AVA dataset. These datasets are utilized to train and evaluate the performance of the proposed HCT network in multi-level semantic understanding of surgical scenarios. The datasets cover the recognition of different surgical phases, steps, actions and instruments, aiming to improve the context awareness capability of surgical assistance systems.




