Dataset Release for "Action Recognition in Video Recordings from Gynecologic Laparoscopy"

This dataset includes video annotations generated for the research paper titled: "Action REcognition in Video Recordings from Gynecology laparoscopy". This dataset includes 18 laparoscopic surgery videos randomly sampled from a collection of more than 600 recordings of gynecologic laparoscopic surgery at the Medical University of Vienna. All 18 laparoscopic surgery videos are segmented and annotated by clinical experts.


The dataset encompasses annotations for the recognition and classification of six target actions in Laparoscopic surgery. These actions incluse Abdominal Access, Grasping Anatomy, Knot Pushing, Needle Pulling, Needle Pushing, and Suction. For each relevant action, we have provided a training and a testing set. The dataset is designed for implementing multiple binary classification approaches, where input vidoes are divided into two classes: the target action ant the remaining actions. This procedure is repeated for each target action, resulting in the creation of six binary classification models in total.








The datasets are exclusively provided for scientific research purposes and as such cannot be used commercially or for any other purpose. If any other purpose is intended, you may directly contact the originator of the videos, Assoc. Prof. DI Dr. Klaus Schoeffmann.

Besides, a reference must be made to the following publication when this dataset is used in any academic and research reports:

S. Nasirihaghighi, N. Ghamsarian, D. Stefanics, K. Schoeffmann, H. Husslein. 2023. Action Recognition in Video Recordings from Gynecologic Laparoscopy. IEEE 36th International Symposium on Computer Based Medical Systems (CBMS), L'Aquila, Italy, 2023, 6 pages. DOI:10.1007/978-3-319-73603-7_20

    author    = {Sahar Nasirihaghighi and
	             Negin Ghamsarian and
                 Daniela Stefanics and
                 Klaus Schoeffmann and
                 Heinrich Husslein},
    title     = {Action Recognition in Video Recordings from Gynecologic Laparoscopy},
    booktitle = {36th International Symposium on Computer Based Medical Systems, {CBMS} 2023,
                 L'Aquila, Italy, June 22-24, 2023},
    pages     = {29--34},
    publisher = {{IEEE}},
    year      = {2023},
    url       = {},
    doi       = {10.1109/CBMS58004.2023.00187},
    timestamp = {},
    biburl    = {},
    bibsource = {}

The datasets are licensed under Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0, Creative Commons License) and is created as well as maintained by the Multimedia Systems Group of the Institute of Information Technology (ITEC) at Alpen-Adria Universität in Klagenfurt, Austria.

This license allows users of this dataset to copy, distribute, and transmit the work under the following conditions:

For further legal details, please read the complete license terms.


If you agree to above conditions, you are free to download:

Action_Recognition.rar (~4 GB)


[2] K. Schoeffmann, M. Taschwer, S. Sarny, B. Münzer, M.J. Primus, and D. Putzgruber. Cataract-101: video dataset of 101 cataract surgeries. In Proceedings of the 9th ACM Multimedia Systems Conference, pages 421–425. ACM, 2018.