FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283798951> ?p ?o ?g. }

• W4283798951 endingPage "102525" @default.
• W4283798951 startingPage "102525" @default.
• W4283798951 abstract "The fine-grained localization of clinicians in the operating room (OR) is a key component to design the new generation of OR support systems. Computer vision models for person pixel-based segmentation and body-keypoints detection are needed to better understand the clinical activities and the spatial layout of the OR. This is challenging, not only because OR images are very different from traditional vision datasets, but also because data and annotations are hard to collect and generate in the OR due to privacy concerns. To address these concerns, we first study how joint person pose estimation and instance segmentation can be performed on low resolutions images with downsampling factors from 1x to 12x. Second, to address the domain shift and the lack of annotations, we propose a novel unsupervised domain adaptation method, called AdaptOR, to adapt a model from an in-the-wild labeled source domain to a statistically different unlabeled target domain. We propose to exploit explicit geometric constraints on the different augmentations of the unlabeled target domain image to generate accurate pseudo labels and use these pseudo labels to train the model on high- and low-resolution OR images in a self-training framework. Furthermore, we propose disentangled feature normalization to handle the statistically different source and target domain data. Extensive experimental results with detailed ablation studies on the two OR datasets MVOR+ and TUM-OR-test show the effectiveness of our approach against strongly constructed baselines, especially on the low-resolution privacy-preserving OR images. Finally, we show the generality of our method as a semi-supervised learning (SSL) method on the large-scale COCO dataset, where we achieve comparable results with as few as 1% of labeled supervision against a model trained with 100% labeled supervision. Code is available at https://github.com/CAMMA-public/HPE-AdaptOR." @default.
• W4283798951 created "2022-07-05" @default.
• W4283798951 creator A5001473909 @default.
• W4283798951 creator A5054515868 @default.
• W4283798951 creator A5071976104 @default.
• W4283798951 date "2022-08-01" @default.
• W4283798951 modified "2023-10-18" @default.
• W4283798951 title "Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating room" @default.
• W4283798951 cites W1982696459 @default.
• W4283798951 cites W2030536784 @default.
• W4283798951 cites W2045798786 @default.
• W4283798951 cites W2104094955 @default.
• W4283798951 cites W2344234940 @default.
• W4283798951 cites W2465748486 @default.
• W4283798951 cites W2495373560 @default.
• W4283798951 cites W2596192549 @default.
• W4283798951 cites W2786808285 @default.
• W4283798951 cites W2901505625 @default.
• W4283798951 cites W2921303908 @default.
• W4283798951 cites W2956571395 @default.
• W4283798951 cites W2963455537 @default.
• W4283798951 cites W2964221239 @default.
• W4283798951 cites W2965604235 @default.
• W4283798951 cites W2965963311 @default.
• W4283798951 cites W2984810221 @default.
• W4283798951 cites W3000303838 @default.
• W4283798951 cites W3026575546 @default.
• W4283798951 cites W3031923721 @default.
• W4283798951 cites W3041133507 @default.
• W4283798951 cites W3103685091 @default.
• W4283798951 cites W3119635706 @default.
• W4283798951 cites W3133610314 @default.
• W4283798951 cites W3135266094 @default.
• W4283798951 cites W3139136049 @default.
• W4283798951 cites W3150684546 @default.
• W4283798951 cites W3196875695 @default.
• W4283798951 doi "https://doi.org/10.1016/j.media.2022.102525" @default.
• W4283798951 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35809529" @default.
• W4283798951 hasPublicationYear "2022" @default.
• W4283798951 type Work @default.
• W4283798951 citedByCount "4" @default.
• W4283798951 countsByYear W42837989512022 @default.
• W4283798951 countsByYear W42837989512023 @default.
• W4283798951 crossrefType "journal-article" @default.
• W4283798951 hasAuthorship W4283798951A5001473909 @default.
• W4283798951 hasAuthorship W4283798951A5054515868 @default.
• W4283798951 hasAuthorship W4283798951A5071976104 @default.
• W4283798951 hasBestOaLocation W42837989511 @default.
• W4283798951 hasConcept C110384440 @default.
• W4283798951 hasConcept C115961682 @default.
• W4283798951 hasConcept C134306372 @default.
• W4283798951 hasConcept C136886441 @default.
• W4283798951 hasConcept C144024400 @default.
• W4283798951 hasConcept C153180895 @default.
• W4283798951 hasConcept C154945302 @default.
• W4283798951 hasConcept C15744967 @default.
• W4283798951 hasConcept C165696696 @default.
• W4283798951 hasConcept C19165224 @default.
• W4283798951 hasConcept C2780767217 @default.
• W4283798951 hasConcept C31972630 @default.
• W4283798951 hasConcept C33923547 @default.
• W4283798951 hasConcept C36503486 @default.
• W4283798951 hasConcept C38652104 @default.
• W4283798951 hasConcept C41008148 @default.
• W4283798951 hasConcept C52102323 @default.
• W4283798951 hasConcept C542102704 @default.
• W4283798951 hasConcept C89600930 @default.
• W4283798951 hasConceptScore W4283798951C110384440 @default.
• W4283798951 hasConceptScore W4283798951C115961682 @default.
• W4283798951 hasConceptScore W4283798951C134306372 @default.
• W4283798951 hasConceptScore W4283798951C136886441 @default.
• W4283798951 hasConceptScore W4283798951C144024400 @default.
• W4283798951 hasConceptScore W4283798951C153180895 @default.
• W4283798951 hasConceptScore W4283798951C154945302 @default.
• W4283798951 hasConceptScore W4283798951C15744967 @default.
• W4283798951 hasConceptScore W4283798951C165696696 @default.
• W4283798951 hasConceptScore W4283798951C19165224 @default.
• W4283798951 hasConceptScore W4283798951C2780767217 @default.
• W4283798951 hasConceptScore W4283798951C31972630 @default.
• W4283798951 hasConceptScore W4283798951C33923547 @default.
• W4283798951 hasConceptScore W4283798951C36503486 @default.
• W4283798951 hasConceptScore W4283798951C38652104 @default.
• W4283798951 hasConceptScore W4283798951C41008148 @default.
• W4283798951 hasConceptScore W4283798951C52102323 @default.
• W4283798951 hasConceptScore W4283798951C542102704 @default.
• W4283798951 hasConceptScore W4283798951C89600930 @default.
• W4283798951 hasLocation W42837989511 @default.
• W4283798951 hasLocation W42837989512 @default.
• W4283798951 hasLocation W42837989513 @default.
• W4283798951 hasLocation W42837989514 @default.
• W4283798951 hasOpenAccess W4283798951 @default.
• W4283798951 hasPrimaryLocation W42837989511 @default.
• W4283798951 hasRelatedWork W1534568064 @default.
• W4283798951 hasRelatedWork W1540444031 @default.
• W4283798951 hasRelatedWork W1968716783 @default.
• W4283798951 hasRelatedWork W2533072256 @default.
• W4283798951 hasRelatedWork W2736638679 @default.
• W4283798951 hasRelatedWork W3108980762 @default.

• next