Filters








7,011 Hits in 6.7 sec

Human Pose Estimation with Iterative Error Feedback [article]

Joao Carreira, Pulkit Agrawal, Katerina Fragkiadaki, Jitendra Malik
2016 arXiv   pre-print
Feedforward architectures can learn rich representations of the input space but do not explicitly model dependencies in the output spaces, that are quite structured for tasks such as articulated human  ...  IEF shows excellent performance on the task of articulated pose estimation in the challenging MPII and LSP benchmarks, matching the state-of-the-art without requiring ground truth scale annotation.  ...  From left to right we show the sequence of corrections the method makes -on the right is the ground truth pose, including annotated occluded keypoints, which are not evaluated.  ... 
arXiv:1507.06550v3 fatcat:tuie6i3dtzdrllyfs6vzj65uuy

Human Pose Estimation with Iterative Error Feedback

Joao Carreira, Pulkit Agrawal, Katerina Fragkiadaki, Jitendra Malik
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Feedforward architectures can learn rich representations of the input space but do not explicitly model dependencies in the output spaces, that are quite structured for tasks such as articulated human  ...  IEF shows excellent performance on the task of articulated pose estimation in the challenging MPII and LSP benchmarks, matching the state-of-the-art without requiring ground truth scale annotation.  ...  Pulkit Agrawal was partially supported by a Fulbright Science and Technology Fellowship. We gratefully acknowledge NVIDIA corporation for the donation of Tesla GPUs for this research.  ... 
doi:10.1109/cvpr.2016.512 dblp:conf/cvpr/CarreiraAFM16 fatcat:bd45sk4e4jgrllyg2xlyqu6bsm

Subchondral bone length in knee osteoarthritis: A deep learning derived imaging measure and its association with radiographic and clinical outcomes [article]

Gary H. Chang, Lisa K. Park, Nina A. Le, Ray S. Jhun, Tejus Surendran, Joseph Lai, Hojoon Seo, Nuwapa Promchotichai, Grace Yoon, Jonathan Scalera, Terence D. Capellini, David T. Felson (+1 others)
2021 medRxiv   pre-print
ABSTRACTObjectiveDevelop a bone shape measure that reflects the extent of cartilage loss and bone flattening in knee osteoarthritis (OA) and test it against estimates of disease severity.MethodsA fast  ...  Publicly available annotations of the cartilage and menisci were used as references to annotate the tibia and the femur in 61 knees.  ...  and left knees), and knees with only medial JSN (1604 right and 1504 left knees) with knees with no JSN (5128 right and left knees). .  ... 
doi:10.1101/2021.04.28.21256271 fatcat:hlf4q5dfona4nnretvzwk4f5ju

Automated segmentation and analysis of normal and osteoarthritic knee menisci from magnetic resonance images – data from the Osteoarthritis Initiative

A. Paproki, C. Engstrom, S.S. Chandra, A. Neubert, J. Fripp, S. Crozier
2014 Osteoarthritis and Cartilage  
s u m m a r y Objective: To validate an automatic scheme for the segmentation and quantitative analysis of the medial meniscus (MM) and lateral meniscus (LM) in magnetic resonance (MR) images of the knee  ...  The MM and LM were automatically segmented in the MR images based on a deformable model approach.  ...  Acknowledgements The authors would like to thank Mike Bowes (Imorphics) and Dr Charles Hutchinson (University of Manchester) for kindly providing the manual segmentations for public access.  ... 
doi:10.1016/j.joca.2014.06.029 pmid:25014660 fatcat:5x2zwqzkwjhj3gaa2czvbdq6yq

Validity and reliability of an iPad with a three-dimensional camera for posture imaging

A. Agustsson, MK. Gislason, P. Ingvarsson, E. Rodby-Bousquet, Th. Sveinsson
2019 Gait & Posture  
Method: A 3-D model of a lying posture, created using an iPad with a 3-D camera, was compared to a Qualisys motion analysis system of the same lying posture, the latter used as the gold standard.  ...  It is important to quantify a static posture to evaluate the need for and effectiveness of interventions such as physical management, physiotherapy, spinal orthosis or surgical treatment on the alignment  ...  Pauline Pope for her advices and the independent raters for their contribution.  ... 
doi:10.1016/j.gaitpost.2018.12.018 fatcat:rd4lg5irkndnhmsujt4q4izzj4

CEL-Unet: Distance Weighted Maps and Multi-Scale Pyramidal Edge Extraction for Accurate Osteoarthritic Bone Segmentation in CT Scans

Matteo Rossi, Luca Marsilio, Luca Mainardi, Alfonso Manzotti, Pietro Cerveri
2022 Frontiers in Signal Processing  
A set of 700 knee CT scans was used to train the model and test segmentation performance. Qualitatively CEL-Unet correctly segmented cases where the state-of-the-art architectures failed.  ...  bony shapes is one of the main critical factors for the success of the operation.  ...  AUTHOR CONTRIBUTIONS All authors listed have made a substantial, direct, and intellectual contribution to the work and approved it for publication.  ... 
doi:10.3389/frsip.2022.857313 fatcat:vicawnsocnfrvm4cuqh2bmdzdu

Bodies Uncovered: Learning to Manipulate Real Blankets Around People via Physics Simulations [article]

Kavya Puthuveetil, Charles C. Kemp, Zackory Erickson
2022 arXiv   pre-print
We compare two approaches for optimizing policies which provide a robot with grasp and release points that uncover a target part of the body: 1) reinforcement learning and 2) self-supervised learning with  ...  In this work, we introduce a formulation for robotic bedding manipulation around people in which a robot uncovers a blanket from a target body part while ensuring the rest of the human body remains covered  ...  As shown in Fig. 3 , the observation represents the pose of the human's right leg s RL , left leg s LL , right arm s RA , and left arm s LA using the 2D position of elbow and knee joints, as well as the  ... 
arXiv:2109.04930v2 fatcat:xvgwj6a5c5gqxkem36tmne7si4

Predicting Knee Joint Instability Using a Tibio-Femoral Statistical Shape Model

Pietro Cerveri, Antonella Belfatto, Alfonso Manzotti
2020 Frontiers in Bioengineering and Biotechnology  
This discloses the opportunity to use the SSM to predict potential misalignment in the knee for a new patient by processing the bone shapes, removing the need for measuring clinical landmarks as the rotation  ...  Statistical shape models (SSMs) are a well established computational technique to represent the morphological variability spread in a set of matching surfaces by means of compact descriptive quantities  ...  Left surfaces were mirrored in the medio-lateral direction to obtain equivalent right surfaces for the construction of the right distal femur and proximal tibia SSM.  ... 
doi:10.3389/fbioe.2020.00253 pmid:32363179 pmcid:PMC7182437 fatcat:toyi3fpenbaofedv5nk7qezofu

Disentangling the energetic costs of step time asymmetry and step length asymmetry in human walking

Jan Stenum, Julia T Choi
2021 Journal of Experimental Biology  
Furthermore, the costs are not additive when walking with asymmetric step times and step lengths: metabolic power of concurrent asymmetry in step lengths and step times is driven by the cost of step time  ...  The metabolic power of asymmetry is explained by positive mechanical power produced during single support phases to compensate for a net loss of center of mass power incurred during double support phases  ...  Umberger and Richard Ellis for sharing data that we used to predict the cost of non-preferred step time and step length.  ... 
doi:10.1242/jeb.242258 pmid:33929536 fatcat:uxk7r2eizbg6hhmxbdhgbhpmze

Cartilage Topography Assessment with Local Area Cartilage Segmentation (LACS) for Knee MRI

Alexander Mathiessen, Erin L. Ashbeck, Emily Huang, Edward John Bedrick, C. Kent Kwoh, Jeffrey Duryea
2021 Arthritis care & research  
Estimated SRMs for LACS and Chondrometrics measures were similar in the random sample, and SRM heat-maps identified sub-regions of LACS-measured cartilage loss.  ...  ), an enriched sample of 126 knees.  ...  Acknowledgements The authors thank Quinley Miao for invaluable assistance.  ... 
doi:10.1002/acr.24745 pmid:34219396 pmcid:PMC8727638 fatcat:d5shltkgsbantozsw6iujbf5jy

Optimisation of a bicycle chainring to aid in rehabilitation of athletes suffering from patellofemoral pain syndrome (PFPS)

C.W.G. Phillips, A.I.J. Forrester, A.I. Purdue, M.J. Stokes
2010 Procedia Engineering  
There are numerous treatments for the pain; for example, strengthening of the quadriceps shows good clinical results.  ...  In this study, the geometry of a bicycle chainring has been optimised to increase the recruitment of Vastus Medialis Oblique (VMO).  ...  For both, there are two distinct peaks where the right and left VM respectively are activated.  ... 
doi:10.1016/j.proeng.2010.04.125 fatcat:r5oggubltja4fd7s744q6msg6i

Characterisation of growth plate dynamics in murine models of osteoarthritis [article]

Hasmik Jasmine Samvelyan, Kamel Madi, Anna E Tornqvist, Behzad Javaheri, Katherine Ann Staines
2020 bioRxiv   pre-print
GP bridging and higher bridge densities in medial compared to lateral tibiae of DMM and loaded knee joints of the mice.  ...  In 16-week-old C57BL/6 male mice (n=4), OA was induced using non-invasive mechanical loading of right knee joints with peak force of 11N. Non-loaded left knee joints were internal controls.  ...  Acknowledgements 437 The authors would like to thank The Roslin Institute of The University of Edinburgh for the 438 assistance with the care of animal models in this study. 439 **  ... 
doi:10.1101/2020.10.14.339119 fatcat:oeibsj7ohfgkzhgph74pmjtfzi

Neurophysiological markers predicting recovery of standing in humans with chronic motor complete spinal cord injury

Samineh Mesbah, Federica Gonnelli, Claudia A. Angeli, Ayman El-baz, Susan J. Harkema, Enrico Rejc
2019 Scientific Reports  
This framework can support researchers and clinicians during the process of selection of epidural stimulation parameters for standing motor rehabilitation.  ...  Additionally, the high classification accuracy of assisted and independent standing allowed the development of a prediction algorithm that can provide feedback on the effectiveness of muscle-specific activation  ...  We also gratefully acknowledge our research staff for their contribution to the data collection, and our training staff for their support of the research volunteers; Drs Maxwell Boakye and Jonathan Hodes  ... 
doi:10.1038/s41598-019-50938-y pmid:31597924 pmcid:PMC6785550 fatcat:jy4lr4g3xrhb5emr4iiv63vfpu

Experimental design for MRI by greedy policy search [article]

Tim Bakker, Herke van Hoof, Max Welling
2020 arXiv   pre-print
We offer a partial explanation for this phenomenon rooted in greater variance in the non-greedy objective's gradient estimates, and experimentally verify that this variance hampers non-greedy models in  ...  Unexpectedly, our experiments show that a simple greedy approximation of the objective leads to solutions nearly on-par with the more general non-greedy approach.  ...  Acknowledgements and disclosure of funding We thank Marco Federici, Shi Hu, Maximilian Ilse, Daniel Worrall, and especially Wouter Kool and Bas Veeling for useful discussions.  ... 
arXiv:2010.16262v2 fatcat:nddyq35krff6dhlgeekhwjiwae

Clinical evaluation of fully automated thigh muscle and adipose tissue segmentation using a U-Net deep learning architecture in context of osteoarthritic knee pain

Jana Kemnitz, Christian F. Baumgartner, Felix Eckstein, Akshay Chaudhari, Anja Ruhdorfer, Wolfgang Wirth, Sebastian K. Eder, Ender Konukoglu
2019 Magnetic Resonance Materials in Physics, Biology and Medicine  
Segmentation of thigh muscle and adipose tissue is important for the understanding of musculoskeletal diseases such as osteoarthritis.  ...  and (b) to evaluate the validity of this method based on a previous clinical study.  ...  We would like to thank the OAI participants, OAI study investigators, and OAI CLINICAL Center staff for generating this publicly available image sets and Martina Sattler for providing us with the image  ... 
doi:10.1007/s10334-019-00816-5 pmid:31872357 fatcat:yeerw2ungbg5np7gfkrmlvz5m4
« Previous Showing results 1 — 15 out of 7,011 results