Filters








3,310 Hits in 5.0 sec

Learning Invariant Representation of Tasks for Robust Surgical State Estimation [article]

Yidan Qin, Max Allan, Yisong Yue, Joel W. Burdick, Mahdi Azizian
2021 arXiv   pre-print
The combination of high diversity and limited data calls for new learning methods that are robust and invariant to operating conditions and surgical techniques.  ...  We propose StiseNet, a Surgical Task Invariance State Estimation Network with an invariance induction framework that minimizes the effects of variations in surgical technique and operating environments  ...  Metrics The quality of the learned invariant representations of surgical states e e e 1 and other information e e e 2 is visually examined.  ... 
arXiv:2102.09119v1 fatcat:tgwvb7cpezbytf5ohesffqtr6a

Towards Generalizable Surgical Activity Recognition Using Spatial Temporal Graph Convolutional Networks [article]

Duygu Sarikaya, Pierre Jannin
2020 arXiv   pre-print
The proposed modality is based on spatial temporal graph representations of surgical tools in videos, for surgical activity recognition.  ...  To our knowledge, our paper is the first to use spatial temporal graph representations of surgical tools, and pose-based skeleton representations in general, for surgical activity recognition.  ...  Using the learned model, we estimated the pose coordinates for the rest of the frames.  ... 
arXiv:2001.03728v4 fatcat:f2azlpri3jhcbhth576nluzzxy

Motion2Vec: Semi-Supervised Representation Learning from Surgical Videos [article]

Ajay Kumar Tanwani, Pierre Sermanet, Andy Yan, Raghav Anand, Mariano Phielipp, Ken Goldberg
2020 arXiv   pre-print
In this paper, we learn a motion-centric representation of surgical video demonstrations by grouping them into action segments/sub-goals/options in a semi-supervised manner.  ...  Learning meaningful visual representations in an embedding space can facilitate generalization in downstream tasks such as action segmentation and imitation.  ...  Finally, the inherent cyclic nature of suturing task calls for learning compositional structure of the action segments.  ... 
arXiv:2006.00545v1 fatcat:l7r5yhmm5jbmtckxrhi43xacuu

Gesture Recognition in Robotic Surgery: a Review

Beatrice Vanamsterdam, Matthew Clarkson, Danail Stoyanov
2021 IEEE Transactions on Biomedical Engineering  
The development of large and diverse open-source datasets of annotated demonstrations is essential for development and validation of robust solutions for surgical gesture recognition.  ...  This paper reviews the state-of-the-art in methods for automatic recognition of fine-grained gestures in robotic surgery focusing on recent data-driven approaches and outlines the open questions and future  ...  [57] or multi-task learning to jointly recognize surgical gestures and estimate the progress of the surgical task, in order to introduce ordering relationships and temporal context explicitly into the  ... 
doi:10.1109/tbme.2021.3054828 pmid:33497324 fatcat:si5dcvrvnzc55dse6cst2k5tfi

A Tetrahedron-Based Heat Flux Signature for Cortical Thickness Morphometry Analysis [chapter]

Yonghui Fan, Gang Wang, Natasha Lepore, Yalin Wang
2018 Lecture Notes in Computer Science  
labels for retinal vessel segmentation task 481 Model-based refinement of nonlinear registrations in 3D histology reconstruction 482 Probabilistic Source Separation on resting-state fMRI and Its Use for  ...  Non-local Deep Feature Fusion for Malignancy Characterization of Hepatocellular Carcinoma 334 Deep Reinforcement Learning for Surgical Gesture Segmentation and Classification 339 Omni-supervised learning  ... 
doi:10.1007/978-3-030-00931-1_48 pmid:30338317 pmcid:PMC6191198 fatcat:dqhvpm5xzrdqhglrfftig3qejq

Learning Actionable Representations from Visual Observations [article]

Debidatta Dwibedi, Jonathan Tompson, Corey Lynch, Pierre Sermanet
2019 arXiv   pre-print
In particular we investigate the effectiveness of learning task-agnostic representations for continuous control tasks.  ...  We show that the representations learned by agents observing themselves take random actions, or other agents perform tasks successfully, can enable the learning of continuous control policies using algorithms  ...  ACKNOWLEDGEMENT We thank Sergey Levine and Vincent Vanhoucke for reviews and constructive feedback.  ... 
arXiv:1808.00928v3 fatcat:bniir5snrnbc3blnkjr4slyssu

Histogram of Oriented Gradients Meet Deep Learning: A Novel Multi-task Deep Network for Medical Image Semantic Segmentation [article]

Binod Bhattarai, Ronast Subedi, Rebati Raman Gaire, Eduard Vazquez, Danail Stoyanov
2022 arXiv   pre-print
Together with the ground truth semantic segmentation masks for the primary task and pseudo-labels for the auxiliary task, we learn the parameters of the deep network to minimise the loss of both the primary  ...  We present our novel deep multi-task learning method for medical image segmentation. Existing multi-task methods demand ground truth annotations for both the primary and auxiliary tasks.  ...  Auxiliary tasks focusing on such aspects would help the network to learn the robust representation for semantic segmentation.  ... 
arXiv:2204.01712v1 fatcat:alzfybhktzf7jb2wnkdpqqqrui

Discovery of high-level tasks in the operating room

L. Bouarfa, P.P. Jonker, J. Dankelman
2011 Journal of Biomedical Informatics  
Recognizing and understanding surgical high-level tasks from sensor readings is important for surgical workflow analysis.  ...  Surgical high-level task recognition is also a challenging task in ubiquitous computing because of the inherent uncertainty of sensor data and the complexity of the operating room environment.  ...  Background The prime objective of a context learning system is to infer a specific high-level task (HLT) from a set of observable low-level tasks (LLT).  ... 
doi:10.1016/j.jbi.2010.01.004 pmid:20060495 fatcat:llgu2vwidzawfpjsh47rhz2vr4

Vision-based and marker-less surgical tool detection and tracking: a review of the literature

David Bouget, Max Allan, Danail Stoyanov, Pierre Jannin
2017 Medical Image Analysis  
Having real-time knowledge of the pose of surgical tools with respect to the surgical camera and underlying anatomy is a key ingredient for such systems.  ...  This paper includes three primary contributions: (1) identification and analysis of data-sets used for developing and testing detection algorithms, (2) in-depth comparison of surgical tool detection methods  ...  Each particle represents one estimate of the system state and at each timestep it is projected through a, possibly non-linear, state transition function giving a new estimate of the system state.  ... 
doi:10.1016/j.media.2016.09.003 pmid:27744253 fatcat:ertyp274bvdxrjumxsvmd5mqau

Table of Contents

2021 IEEE Robotics and Automation Letters  
Pinciroli 3200 Learning Invariant Representation of Tasks for Robust Surgical State Estimation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Nejat 1793 Lightweight 3-D Localization and Mapping for Solid-State LiDAR . 2745 Self-Supervised Learning of Domain-Invariant Local Features for Robust Visual Localization Under Challenging Conditions  ... 
doi:10.1109/lra.2021.3072707 fatcat:qyphyzqxfrgg7dxdol4qamrdqu

Probabilistic Tracking of Affine-Invariant Anisotropic Regions

Stamatia Giannarou, Marco Visentini-Scarzanella, Guang-Zhong Yang
2013 IEEE Transactions on Pattern Analysis and Machine Intelligence  
to the paucity of reliable salient features coupled with free-form tissue deformation and changing visual appearance of surgical scenes.  ...  Despite a wide range of feature detectors developed in the computer vision community over the years, direct application of these techniques to surgical navigation has shown significant difficulties due  ...  Fan for running on our data the Online Learning [28] and Contextural Flow [31] trackers, respectively.  ... 
doi:10.1109/tpami.2012.81 pmid:22450819 fatcat:4qhn43xufbdzdoh333eun4japu

Monocular Depth Estimators: Vulnerabilities and Attacks [article]

Alwyn Mathew, Aditya Prakash Patra, Jimson Mathew
2020 arXiv   pre-print
In this paper, we investigate the robustness of the most state-of-the-art monocular depth estimation networks against adversarial attacks.  ...  Depth estimation is one of the essential tasks in robotics, and monocular depth estimation has a wide variety of safety-critical applications like in self-driving cars and surgical devices.  ...  The vulnerability of deep learning models for tasks like image classification, detection, and segmentation is extensively studied in the literature.  ... 
arXiv:2005.14302v1 fatcat:kzrap72jhbhajnne67vmeleljy

Imitation Learning: Progress, Taxonomies and Opportunities [article]

Boyuan Zheng, Sunny Verma, Jianlong Zhou, Ivor Tsang, Fang Chen
2021 arXiv   pre-print
We first introduce the background knowledge from development history and preliminaries, followed by presenting different taxonomies within Imitation Learning and key milestones of the field.  ...  However, this replicating process could be problematic, such as the performance is highly dependent on the demonstration quality, and most trained agents are limited to perform well in task-specific environments  ...  Different viewpoints introduce a wide range of contexts about the task environment and the goal is to learn invariant representation about the task.  ... 
arXiv:2106.12177v1 fatcat:wcvld6wvbffq5iht5z5cb563yi

The geometry of domain-general performance monitoring representations in the human medial frontal cortex [article]

Zhongzheng Fu, Danielle Beam, Jeffrey M. Chung, Chrystal M. Reed, Adam N. Mamelak, Ralph Adolphs, Ueli Rutishauser
2021 bioRxiv   pre-print
These findings reveal how the MFC representation of evaluative signals are both abstract and specific, suggesting a mechanism for computing and maintaining control demand estimates across trials and tasks  ...  This arose from a combination of single neurons whose responses were task-invariant and non-linearly mixed.  ...  Task-invariant representation of performance monitoring signals.  ... 
doi:10.1101/2021.07.08.451594 fatcat:jszwrozcsrb7tk2jqby5y3uljq

A Survey of Vision-Based Human Action Evaluation Methods

Qing Lei, Ji-Xiang Du, Hong-Bo Zhang, Shuang Ye, Duan-Sheng Chen
2019 Sensors  
methods, and deep learning-based feature representation methods.  ...  This line of study has become popular because of its explosively emerging real-world applications, such as physical rehabilitation, assistive living for elderly people, skill training on self-learning  ...  Acknowledgments: The authors would like to thank the anonymous reviewers for their valuable and insightful comments on an earlier version of this manuscript.  ... 
doi:10.3390/s19194129 pmid:31554229 pmcid:PMC6806217 fatcat:zgwsdv6xorfvxjck6rsjusezwe
« Previous Showing results 1 — 15 out of 3,310 results