FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2883980546> ?p ?o ?g. }

• W2883980546 endingPage "710" @default.
• W2883980546 startingPage "693" @default.
• W2883980546 abstract "Effectively measuring the similarity between two human motions is necessary for several computer vision tasks such as gait analysis, person identification and action retrieval. Nevertheless, we believe that traditional approaches such as L2 distance or Dynamic Time Warping based on hand-crafted local pose metrics fail to appropriately capture the semantic relationship across motions and, as such, are not suitable for being employed as metrics within these tasks. This work addresses this limitation by means of a triplet-based deep metric learning specifically tailored to deal with human motion data, in particular with the problem of varying input size and computationally expensive hard negative mining due to motion pair alignment. Specifically, we propose (1) a novel metric learning objective based on a triplet architecture and Maximum Mean Discrepancy; as well as, (2) a novel deep architecture based on attentive recurrent neural networks. One benefit of our objective function is that it enforces a better separation within the learned embedding space of the different motion categories by means of the associated distribution moments. At the same time, our attentive recurrent neural network allows processing varying input sizes to a fixed size of embedding while learning to focus on those motion parts that are semantically distinctive. Our experiments on two different datasets demonstrate significant improvements over conventional human motion metrics." @default.
• W2883980546 created "2018-08-03" @default.
• W2883980546 creator A5041092666 @default.
• W2883980546 creator A5046896448 @default.
• W2883980546 creator A5051298870 @default.
• W2883980546 creator A5056241875 @default.
• W2883980546 creator A5073512409 @default.
• W2883980546 date "2018-01-01" @default.
• W2883980546 modified "2023-09-27" @default.
• W2883980546 title "Human Motion Analysis with Deep Metric Learning" @default.
• W2883980546 cites W1534304300 @default.
• W2883980546 cites W1689711448 @default.
• W2883980546 cites W2033994211 @default.
• W2883980546 cites W2064675550 @default.
• W2883980546 cites W2078993594 @default.
• W2883980546 cites W2080501585 @default.
• W2883980546 cites W2101032778 @default.
• W2883980546 cites W2124958607 @default.
• W2883980546 cites W2142203883 @default.
• W2883980546 cites W2143612262 @default.
• W2883980546 cites W2158164339 @default.
• W2883980546 cites W2169495281 @default.
• W2883980546 cites W2307770531 @default.
• W2883980546 cites W2397306716 @default.
• W2883980546 cites W2403938642 @default.
• W2883980546 cites W2417142196 @default.
• W2883980546 cites W2604375920 @default.
• W2883980546 cites W2605102252 @default.
• W2883980546 cites W2611932403 @default.
• W2883980546 cites W2623638694 @default.
• W2883980546 cites W2737260104 @default.
• W2883980546 cites W2742737904 @default.
• W2883980546 cites W2962708773 @default.
• W2883980546 cites W2962949994 @default.
• W2883980546 cites W2963026686 @default.
• W2883980546 cites W2964105113 @default.
• W2883980546 cites W2964203186 @default.
• W2883980546 cites W3099206234 @default.
• W2883980546 cites W3147254695 @default.
• W2883980546 cites W58346954 @default.
• W2883980546 doi "https://doi.org/10.1007/978-3-030-01264-9_41" @default.
• W2883980546 hasPublicationYear "2018" @default.
• W2883980546 type Work @default.
• W2883980546 sameAs 2883980546 @default.
• W2883980546 citedByCount "26" @default.
• W2883980546 countsByYear W28839805462019 @default.
• W2883980546 countsByYear W28839805462020 @default.
• W2883980546 countsByYear W28839805462021 @default.
• W2883980546 countsByYear W28839805462022 @default.
• W2883980546 countsByYear W28839805462023 @default.
• W2883980546 crossrefType "book-chapter" @default.
• W2883980546 hasAuthorship W2883980546A5041092666 @default.
• W2883980546 hasAuthorship W2883980546A5046896448 @default.
• W2883980546 hasAuthorship W2883980546A5051298870 @default.
• W2883980546 hasAuthorship W2883980546A5056241875 @default.
• W2883980546 hasAuthorship W2883980546A5073512409 @default.
• W2883980546 hasBestOaLocation W28839805462 @default.
• W2883980546 hasConcept C103278499 @default.
• W2883980546 hasConcept C104114177 @default.
• W2883980546 hasConcept C108583219 @default.
• W2883980546 hasConcept C115961682 @default.
• W2883980546 hasConcept C119857082 @default.
• W2883980546 hasConcept C120665830 @default.
• W2883980546 hasConcept C121332964 @default.
• W2883980546 hasConcept C153180895 @default.
• W2883980546 hasConcept C154945302 @default.
• W2883980546 hasConcept C157202957 @default.
• W2883980546 hasConcept C162324750 @default.
• W2883980546 hasConcept C176217482 @default.
• W2883980546 hasConcept C192209626 @default.
• W2883980546 hasConcept C21547014 @default.
• W2883980546 hasConcept C31972630 @default.
• W2883980546 hasConcept C41008148 @default.
• W2883980546 hasConcept C41608201 @default.
• W2883980546 hasConcept C50644808 @default.
• W2883980546 hasConcept C88516994 @default.
• W2883980546 hasConceptScore W2883980546C103278499 @default.
• W2883980546 hasConceptScore W2883980546C104114177 @default.
• W2883980546 hasConceptScore W2883980546C108583219 @default.
• W2883980546 hasConceptScore W2883980546C115961682 @default.
• W2883980546 hasConceptScore W2883980546C119857082 @default.
• W2883980546 hasConceptScore W2883980546C120665830 @default.
• W2883980546 hasConceptScore W2883980546C121332964 @default.
• W2883980546 hasConceptScore W2883980546C153180895 @default.
• W2883980546 hasConceptScore W2883980546C154945302 @default.
• W2883980546 hasConceptScore W2883980546C157202957 @default.
• W2883980546 hasConceptScore W2883980546C162324750 @default.
• W2883980546 hasConceptScore W2883980546C176217482 @default.
• W2883980546 hasConceptScore W2883980546C192209626 @default.
• W2883980546 hasConceptScore W2883980546C21547014 @default.
• W2883980546 hasConceptScore W2883980546C31972630 @default.
• W2883980546 hasConceptScore W2883980546C41008148 @default.
• W2883980546 hasConceptScore W2883980546C41608201 @default.
• W2883980546 hasConceptScore W2883980546C50644808 @default.
• W2883980546 hasConceptScore W2883980546C88516994 @default.
• W2883980546 hasLocation W28839805461 @default.
• W2883980546 hasLocation W28839805462 @default.
• W2883980546 hasOpenAccess W2883980546 @default.

• next