Matches in SemOpenAlex for { <https://semopenalex.org/work/W3133711192> ?p ?o ?g. }
- W3133711192 endingPage "36558" @default.
- W3133711192 startingPage "36547" @default.
- W3133711192 abstract "Human motion similarity is practiced in many fields, including action recognition, anomaly detection, and human performance evaluation. While many computer vision tasks have benefited from deep learning, measuring motion similarity has attracted less attention, particularly due to the lack of large datasets. To address this problem, we introduce two datasets: a synthetic motion dataset for model training and a dataset containing human annotations of real-world video clip pairs for motion similarity evaluation. Furthermore, in order to compute the motion similarity from these datasets, we propose a deep learning model that produces motion embeddings suitable for measuring the similarity between different motions of each human body part. The network is trained with the proposed motion variation loss to robustly distinguish even subtly different motions. The proposed approach outperforms the other baselines considered in terms of correlations between motion similarity predictions and human annotations while being suitable for real-time action analysis. Both datasets and codes are released to the public." @default.
- W3133711192 created "2021-03-15" @default.
- W3133711192 creator A5018834240 @default.
- W3133711192 creator A5020230898 @default.
- W3133711192 creator A5022824031 @default.
- W3133711192 creator A5024398480 @default.
- W3133711192 creator A5034770254 @default.
- W3133711192 creator A5055863860 @default.
- W3133711192 creator A5076040416 @default.
- W3133711192 date "2021-01-01" @default.
- W3133711192 modified "2023-10-12" @default.
- W3133711192 title "A Body Part Embedding Model With Datasets for Measuring 2D Human Motion Similarity" @default.
- W3133711192 cites W1957718552 @default.
- W3133711192 cites W1986254198 @default.
- W3133711192 cites W1998718623 @default.
- W3133711192 cites W2089020382 @default.
- W3133711192 cites W2091735588 @default.
- W3133711192 cites W2117385163 @default.
- W3133711192 cites W2166267120 @default.
- W3133711192 cites W2172043283 @default.
- W3133711192 cites W2561080715 @default.
- W3133711192 cites W2606377603 @default.
- W3133711192 cites W2740537152 @default.
- W3133711192 cites W2749203358 @default.
- W3133711192 cites W2796633859 @default.
- W3133711192 cites W2806516088 @default.
- W3133711192 cites W2819476901 @default.
- W3133711192 cites W2883980546 @default.
- W3133711192 cites W2887057599 @default.
- W3133711192 cites W2894963073 @default.
- W3133711192 cites W2902579619 @default.
- W3133711192 cites W2913266832 @default.
- W3133711192 cites W2914830142 @default.
- W3133711192 cites W2921906393 @default.
- W3133711192 cites W2942957343 @default.
- W3133711192 cites W2944006115 @default.
- W3133711192 cites W2962691289 @default.
- W3133711192 cites W2963263909 @default.
- W3133711192 cites W2963795951 @default.
- W3133711192 cites W2972327058 @default.
- W3133711192 cites W2978874829 @default.
- W3133711192 cites W2999049832 @default.
- W3133711192 cites W3002005943 @default.
- W3133711192 cites W3020836386 @default.
- W3133711192 cites W3028433894 @default.
- W3133711192 cites W3035225512 @default.
- W3133711192 cites W3099206234 @default.
- W3133711192 cites W3103919331 @default.
- W3133711192 cites W3107322323 @default.
- W3133711192 cites W3110854813 @default.
- W3133711192 cites W3125747099 @default.
- W3133711192 cites W413992410 @default.
- W3133711192 doi "https://doi.org/10.1109/access.2021.3063302" @default.
- W3133711192 hasPublicationYear "2021" @default.
- W3133711192 type Work @default.
- W3133711192 sameAs 3133711192 @default.
- W3133711192 citedByCount "8" @default.
- W3133711192 countsByYear W31337111922021 @default.
- W3133711192 countsByYear W31337111922022 @default.
- W3133711192 countsByYear W31337111922023 @default.
- W3133711192 crossrefType "journal-article" @default.
- W3133711192 hasAuthorship W3133711192A5018834240 @default.
- W3133711192 hasAuthorship W3133711192A5020230898 @default.
- W3133711192 hasAuthorship W3133711192A5022824031 @default.
- W3133711192 hasAuthorship W3133711192A5024398480 @default.
- W3133711192 hasAuthorship W3133711192A5034770254 @default.
- W3133711192 hasAuthorship W3133711192A5055863860 @default.
- W3133711192 hasAuthorship W3133711192A5076040416 @default.
- W3133711192 hasBestOaLocation W31337111921 @default.
- W3133711192 hasConcept C103278499 @default.
- W3133711192 hasConcept C104114177 @default.
- W3133711192 hasConcept C108583219 @default.
- W3133711192 hasConcept C115961682 @default.
- W3133711192 hasConcept C119857082 @default.
- W3133711192 hasConcept C153180895 @default.
- W3133711192 hasConcept C154945302 @default.
- W3133711192 hasConcept C2777212361 @default.
- W3133711192 hasConcept C2986578859 @default.
- W3133711192 hasConcept C2987834672 @default.
- W3133711192 hasConcept C31972630 @default.
- W3133711192 hasConcept C41008148 @default.
- W3133711192 hasConcept C41608201 @default.
- W3133711192 hasConceptScore W3133711192C103278499 @default.
- W3133711192 hasConceptScore W3133711192C104114177 @default.
- W3133711192 hasConceptScore W3133711192C108583219 @default.
- W3133711192 hasConceptScore W3133711192C115961682 @default.
- W3133711192 hasConceptScore W3133711192C119857082 @default.
- W3133711192 hasConceptScore W3133711192C153180895 @default.
- W3133711192 hasConceptScore W3133711192C154945302 @default.
- W3133711192 hasConceptScore W3133711192C2777212361 @default.
- W3133711192 hasConceptScore W3133711192C2986578859 @default.
- W3133711192 hasConceptScore W3133711192C2987834672 @default.
- W3133711192 hasConceptScore W3133711192C31972630 @default.
- W3133711192 hasConceptScore W3133711192C41008148 @default.
- W3133711192 hasConceptScore W3133711192C41608201 @default.
- W3133711192 hasFunder F4320322120 @default.
- W3133711192 hasLocation W31337111921 @default.
- W3133711192 hasOpenAccess W3133711192 @default.