Towards Unified Surgical Skill Assessment
Not on the map. Why?
Abstract (arXiv)
Surgical skills have a great influence on surgical safety and patients' well-being. Traditional assessment of surgical skills involves strenuous manual efforts, which lacks efficiency and repeatability. Therefore, we attempt to automatically predict how well the surgery is performed using the surgical video. In this paper, a unified multi-path framework for automatic surgical skill assessment is proposed, which takes care of multiple composing aspects of surgical skills, including surgical tool usage, intraoperative event pattern, and other skill proxies. The dependency relationships among these different aspects are specially modeled by a path dependency module in the framework. We conduct extensive experiments on the JIGSAWS dataset of simulated surgical tasks, and a new clinical dataset of real laparoscopic surgeries. The proposed framework achieves promising results on both datasets, with the state-of-the-art on the simulated dataset advanced from 0.71 Spearman's correlation to 0.80. It is also shown that combining multiple skill aspects yields better performance than relying on a single aspect.
Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). Builds on 26 of its 66 references that are in the map. First posted on arXiv 2 Jun 2021.
Builds on
26 of 66 references.
References · 26
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
- 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 899
- 2016Temporal Convolutional Networks for Action Segmentation and Detectioncited by 504
- 2019MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentationcited by 370
- 2020Memory-augmented Dense Predictive Coding for Video Representation Learningcited by 137
- 2019What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessmentcited by 100
- 2016Learning To Score Olympic Eventscited by 87
- 2020Uncertainty-aware Score Distribution Learning for Action Quality Assessmentcited by 80
- 2018Action Quality Assessment Across Multiple Actionscited by 78
14 more
- 2018Learning to score the figure skating sports videoscited by 72
- 2018The Pros and Cons: Rank-aware Temporal Attention for Skill Determination in Long Videoscited by 68
- 2019Video-based surgical skill assessment using 3D convolutional neural networkscited by 57
- 2018Tool Detection and Operative Skill Assessment in Surgical Videos Using Region-Based Convolutional Neural Networkscited by 56
- 2016Am I a Baller? Basketball Performance Assessment from First-Person Videoscited by 40
- 2019Manipulation-skill Assessment from Videos with Spatial Attention Networkcited by 29
- 2017Video and Accelerometer-Based Motion Analysis for Automated Surgical Skills Assessmentcited by 28
- 2017Automated Surgical Skill Assessment in RMIS Trainingcited by 21
- 2018Evaluating surgical skills from kinematic data using convolutional neural networkscited by 19
- 2018Deep Learning with Convolutional Neural Network for Objective Skill Evaluation in Robot-assisted Surgerycited by 17
- 2020Unsupervised Surgical Instrument Segmentation via Anchor Generation and Semantic Diffusioncited by 14
- 2015Augmenting Bag-of-Words: Data-Driven Discovery of Temporal and Structural Information for Activity Recognitioncited by 6
- 2020Deep learning-based computer vision to recognize and classify suturing gestures in robot-assisted surgerycited by 5
- 2020Surgical Skill Assessment on In-Vivo Clinical Data via the Clearness of Operating Fieldcited by 2
Built on by
Citing papers per year: 2022: 5; 2023: 7; 2024: 12; 2025: 14; 2026: 11.
49 papers.
Sort:
By area:
- 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 477
- 2023SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentationcited by 103
- 2024EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real Worldcited by 93
- 2023Diffusion Action Segmentationcited by 74
- 2025MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environmentscited by 28
- 2022Exploring Intra- and Inter-Video Relation for Surgical Semantic Scene Segmentationcited by 27
- 2022Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessmentcited by 25
- 2024Multimodal Action Quality Assessmentcited by 20
- 2024A Comprehensive Survey of Action Quality Assessment: Method and Benchmarkcited by 20
- 2023PECoP: Parameter Efficient Continual Pretraining for Action Quality Assessmentcited by 19
- 2024ExpertAF: Expert Actionable Feedback from Videocited by 17
- 2025BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimationcited by 17
37 more
- 2024Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessmentcited by 14
- 2022Less is More: Surgical Phase Recognition from Timestamp Supervisioncited by 13
- 2022Surgical Skill Assessment via Video Semantic Aggregationcited by 13
- 2024RICA2: Rubric-Informed, Calibrated Assessment of Actionscited by 13
- 2023Continual Action Assessment via Task-Consistent Score-Discriminative Feature Distribution Modelingcited by 12
- 2023SurgicalPart-SAM: Part-to-Whole Collaborative Prompting for Surgical Instrument Segmentationcited by 8
- 2024SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challengecited by 7
- 2025A Decade of Action Quality Assessment: Largest Systematic Survey of Trends, Challenges, and Future Directionscited by 7
- 2022Using Hand Pose Estimation To Automate Open Surgery Training Feedbackcited by 6
- 2025Beyond Role-Based Surgical Domain Modeling: Generalizable Re-Identification in the Operating Roomcited by 6
- 2026Towards a Medical AI Scientistcited by 5
- 2023Prompt-enhanced Hierarchical Transformer Elevating Cardiopulmonary Resuscitation Instruction via Temporal Action Segmentationcited by 4
- 2024Surgical Triplet Recognition via Diffusion Modelcited by 4
- 2025HuMoCon: Concept Discovery for Human Motion Understandingcited by 4
- 2024CycleSAM: Few-Shot Surgical Scene Segmentation with Cycle- and Scene-Consistent Feature Matchingcited by 3
- 2025EgoSurgery-HTS: A Dataset for Egocentric Hand-Tool Segmentation in Open Surgery Videoscited by 3
- 2025Leadership Assessment in Pediatric Intensive Care Unit Team Trainingcited by 3
- 2025Hierarchical Context Transformer for Multi-level Semantic Scene Understandingcited by 2
- 2025Towards Dynamic 3D Reconstruction of Hand-Instrument Interaction in Ophthalmic Surgerycited by 2
- 2025Exploring Pre-training Across Domains for Few-Shot Surgical Skill Assessmentcited by 2
- 2024ZEAL: Surgical Skill Assessment with Zero-shot Tool Inference Using Unified Foundation Modelcited by 1
- 2024ReCAP: Recursive Cross Attention Network for Pseudo-Label Generation in Robotic Surgical Skill Assessmentcited by 1
- 2025Multi-Modal Gesture Recognition from Video and Surgical Tool Pose Information via Motion Invariantscited by 1
- 2025End-to-End Deep Learning for Real-Time Neuroimaging-Based Assessment of Bimanual Motor Skillscited by 1
- 2026A benchmark for video-based laparoscopic skill analysis and assessmentcited by 1
- 2026CoRe-DA: Contrastive Regression for Unsupervised Domain Adaptation in Surgical Skill Assessmentcited by 1
- 2026SurgTEMP: Temporal-Aware Surgical Video Question Answering with Text-guided Visual Memory for Laparoscopic Cholecystectomycited by 1
- 2024Robust Surgical Phase Recognition From Annotation Efficient Supervisioncited by 0
- 2025Meta-SurDiff: Classification Diffusion Model Optimized by Meta Learning is Reliable for Online Surgical Phase Recognitioncited by 0
- 2025Explainable AI for Automated User-specific Feedback in Surgical Skill Acquisitioncited by 0
- 2026SurgFusion-Net: Diversified Adaptive Multimodal Fusion Network for Surgical Skill Assessmentcited by 0
- 2026How good was my shot? Quantifying Player Skill Level in Table Tenniscited by 0
- 2026MoAKE: Toward Unified All-in-One Action Quality Assessment via Mixture of Action Knowledge Expertscited by 0
- 2026Bootstrapping Vision-Language Model for Hysteroscopic Surgical Scene Segmentationcited by 0
- 2026SurgSkill-Bench: A Benchmark for Multimodal Surgical Skill Assessmentcited by 0
- 2026DART: Depth-as-Target Pretraining for Surgical Vision Foundation Modelscited by 0
- 2026Semantic RGB--Depth Based Surgical Skill Assessment in Microscopic Stereo Videoscited by 0
- 2026Semantic RGB--Depth Based Surgical Skill Assessment in Microscopic Stereo Videos1 Oct 2026
- 2026DART: Depth-as-Target Pretraining for Surgical Vision Foundation Models3 Sep 2026
- 2026SurgSkill-Bench: A Benchmark for Multimodal Surgical Skill Assessment31 Aug 2026
- 2026Bootstrapping Vision-Language Model for Hysteroscopic Surgical Scene Segmentation10 Aug 2026
- 2026MoAKE: Toward Unified All-in-One Action Quality Assessment via Mixture of Action Knowledge Experts22 Jul 2026
- 2026SurgTEMP: Temporal-Aware Surgical Video Question Answering with Text-guided Visual Memory for Laparoscopic Cholecystectomy31 Mar 2026
- 2026CoRe-DA: Contrastive Regression for Unsupervised Domain Adaptation in Surgical Skill Assessment31 Mar 2026
- 2026Towards a Medical AI Scientist30 Mar 2026
- 2026How good was my shot? Quantifying Player Skill Level in Table Tennis26 Mar 2026
- 2026SurgFusion-Net: Diversified Adaptive Multimodal Fusion Network for Surgical Skill Assessment18 Feb 2026
- 2026A benchmark for video-based laparoscopic skill analysis and assessment10 Feb 2026
- 2025Exploring Pre-training Across Domains for Few-Shot Surgical Skill Assessment11 Sep 2025
37 more
- 2025Explainable AI for Automated User-specific Feedback in Surgical Skill Acquisition4 Aug 2025
- 2025Meta-SurDiff: Classification Diffusion Model Optimized by Meta Learning is Reliable for Online Surgical Phase Recognition17 Jun 2025
- 2025Leadership Assessment in Pediatric Intensive Care Unit Team Training30 May 2025
- 2025HuMoCon: Concept Discovery for Human Motion Understanding27 May 2025
- 2025Towards Dynamic 3D Reconstruction of Hand-Instrument Interaction in Ophthalmic Surgery23 May 2025
- 2025BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation26 Mar 2025
- 2025EgoSurgery-HTS: A Dataset for Egocentric Hand-Tool Segmentation in Open Surgery Videos24 Mar 2025
- 2025End-to-End Deep Learning for Real-Time Neuroimaging-Based Assessment of Bimanual Motor Skills21 Mar 2025
- 2025Multi-Modal Gesture Recognition from Video and Surgical Tool Pose Information via Motion Invariants19 Mar 2025
- 2025Beyond Role-Based Surgical Domain Modeling: Generalizable Re-Identification in the Operating Room17 Mar 2025
- 2025MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments4 Mar 2025
- 2025Hierarchical Context Transformer for Multi-level Semantic Scene Understanding21 Feb 2025
- 2025A Decade of Action Quality Assessment: Largest Systematic Survey of Trends, Challenges, and Future Directions5 Feb 2025
- 2024A Comprehensive Survey of Action Quality Assessment: Method and Benchmark15 Dec 2024
- 2024RICA2: Rubric-Informed, Calibrated Assessment of Actions4 Aug 2024
- 2024ExpertAF: Expert Actionable Feedback from Video1 Aug 2024
- 2024SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge16 Jul 2024
- 2024CycleSAM: Few-Shot Surgical Scene Segmentation with Cycle- and Scene-Consistent Feature Matching9 Jul 2024
- 2024ZEAL: Surgical Skill Assessment with Zero-shot Tool Inference Using Unified Foundation Model3 Jul 2024
- 2024Robust Surgical Phase Recognition From Annotation Efficient Supervision26 Jun 2024
- 2024Surgical Triplet Recognition via Diffusion Model19 Jun 2024
- 2024ReCAP: Recursive Cross Attention Network for Pseudo-Label Generation in Robotic Surgical Skill Assessment22 Apr 2024
- 2024EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World24 Mar 2024
- 2024Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessment20 Mar 2024
- 2024Multimodal Action Quality Assessment31 Jan 2024
- 2023SurgicalPart-SAM: Part-to-Whole Collaborative Prompting for Surgical Instrument Segmentation22 Dec 2023
- 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives30 Nov 2023
- 2023PECoP: Parameter Efficient Continual Pretraining for Action Quality Assessment11 Nov 2023
- 2023Continual Action Assessment via Task-Consistent Score-Discriminative Feature Distribution Modeling29 Sep 2023
- 2023Prompt-enhanced Hierarchical Transformer Elevating Cardiopulmonary Resuscitation Instruction via Temporal Action Segmentation31 Aug 2023
- 2023SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation17 Aug 2023
- 2023Diffusion Action Segmentation31 Mar 2023
- 2022Using Hand Pose Estimation To Automate Open Surgery Training Feedback13 Nov 2022
- 2022Surgical Skill Assessment via Video Semantic Aggregation4 Aug 2022
- 2022Exploring Intra- and Inter-Video Relation for Surgical Semantic Scene Segmentation29 Mar 2022
- 2022Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment28 Feb 2022
- 2022Less is More: Surgical Phase Recognition from Timestamp Supervision16 Feb 2022
- 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 477
- 2023SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentationcited by 103
- 2024EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real Worldcited by 93
- 2023Diffusion Action Segmentationcited by 74
- 2025MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environmentscited by 28
- 2022Exploring Intra- and Inter-Video Relation for Surgical Semantic Scene Segmentationcited by 27
- 2022Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessmentcited by 25
- 2024Multimodal Action Quality Assessmentcited by 20
- 2024A Comprehensive Survey of Action Quality Assessment: Method and Benchmarkcited by 20
- 2023PECoP: Parameter Efficient Continual Pretraining for Action Quality Assessmentcited by 19
- 2024ExpertAF: Expert Actionable Feedback from Videocited by 17
- 2025BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimationcited by 17
12 most cited of 46 All 46 (JSON)
- 2026Semantic RGB--Depth Based Surgical Skill Assessment in Microscopic Stereo Videos1 Oct 2026
- 2026DART: Depth-as-Target Pretraining for Surgical Vision Foundation Models3 Sep 2026
- 2026SurgSkill-Bench: A Benchmark for Multimodal Surgical Skill Assessment31 Aug 2026
- 2026MoAKE: Toward Unified All-in-One Action Quality Assessment via Mixture of Action Knowledge Experts22 Jul 2026
- 2026SurgTEMP: Temporal-Aware Surgical Video Question Answering with Text-guided Visual Memory for Laparoscopic Cholecystectomy31 Mar 2026
- 2026CoRe-DA: Contrastive Regression for Unsupervised Domain Adaptation in Surgical Skill Assessment31 Mar 2026
- 2026Towards a Medical AI Scientist30 Mar 2026
- 2026How good was my shot? Quantifying Player Skill Level in Table Tennis26 Mar 2026
- 2026SurgFusion-Net: Diversified Adaptive Multimodal Fusion Network for Surgical Skill Assessment18 Feb 2026
- 2026A benchmark for video-based laparoscopic skill analysis and assessment10 Feb 2026
- 2025Exploring Pre-training Across Domains for Few-Shot Surgical Skill Assessment11 Sep 2025
- 2025Explainable AI for Automated User-specific Feedback in Surgical Skill Acquisition4 Aug 2025
12 newest of 46 All 46 (JSON)