JHU-ISI Gesture and Skill Assessment Working Set ( JIGSAWS ) : A Surgical Activity Dataset for Human Motion Modeling

By Yixin Gao, S. Vedula, Carol E. Reiley, N. Ahmidi, Balakrishnan Varadarajan, Henry C. Lin, Lingling Tao, Luca Zappella, B. Béjar, D. Yuh and 4 more. 2014

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Li Fei-Fei
2. Abhinav Kumar Gupta
3. Sergey Levine
4. Luc Van Gool
5. Kristen Grauman
6. Jitendra Malik
7. De-An Huang
8. Silvio Savarese

Citations in the corpus

• Neural Task Graphs: Generalizing to Unseen Tasks From a Single Video Demonstration (2018, methodology): “For the last question, we evaluate NTG on realworld surgical data and examine its graph prediction and evaluation of unseen tasks on the JIGSAWS [12] dataset.”
• Temporal Convolutional Networks: A Unified Approach to Action Segmentation (2016, unknown): “JHU-ISI Gesture and Skill Assessment Working Set (JIGSAWS) [5] was introduced to improve quantitative evaluation of robotic surgery training tasks.”
• FineGym: A Hierarchical Video Dataset for Fine-Grained Action Understanding (2020, background): “There are also attempts towards building datasets for fine-grained action recognition [6, 34, 19, 15, 24, 29].”
• Segmental Spatiotemporal CNNs for Fine-Grained Action Segmentation (2016, methodology): “JHU-ISI Gesture and Skill Assessment Working Set (JIGSAWS): JIGSAWS [9] was developed for recognizing actions in robotic surgery training tasks like suturing, needle passing, and knot tying.”
• A Function Approximation Method for Model-based High-Dimensional Inverse Reinforcement Learning (2017, methodology): “We apply the proposed method to surgical robot operators in JIGSAW data set [1].”
• Surgical data science – from concepts toward clinical translation (2020, background): “JHU-ISI Gesture and Skill Assessment Working Set (JIGSAWS): A Surgical Activity Dataset for Human Motion Modeling.”
• Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization (2019, background): “Temporal action localization is an important visual task with potential applications in video surveillance [42], video summarization [28], skill assessment [16], and others.”
• Deep Reinforcement Learning for Surgical Gesture Segmentation and Classification (2018, methodology): “The proposed method is tested on the suturing task of the JIGSAWS dataset [1,15].”
• Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities (2022, background): “Unlike existing skill assessment datasets [7, 13, 31, 33], which have only skill scores, we annotate specific mistakes and participant skill levels.”