FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380090185> ?p ?o ?g. }

• W4380090185 endingPage "2593" @default.
• W4380090185 startingPage "2593" @default.
• W4380090185 abstract "Most current pose estimation methods have a high resource cost that makes them unusable in some resource-limited devices. To address this problem, we propose an ultra-lightweight end-to-end pose distillation network, which applies some helpful techniques to suitably balance the number of parameters and predictive accuracy. First, we designed a lightweight one-stage pose estimation network, which learns from an increasingly refined sequential expert network in an online knowledge distillation manner. Then, we constructed an ultra-lightweight re-parameterized pose estimation subnetwork that uses a multi-module design with weight sharing to improve the multi-scale image feature acquisition capability of the single-module design. When training was complete, we used the first re-parameterized module as the deployment network to retain the simple architecture. Finally, extensive experimental results demonstrated the detection precision and low parameters of our method." @default.
• W4380090185 created "2023-06-10" @default.
• W4380090185 creator A5008213911 @default.
• W4380090185 creator A5025465795 @default.
• W4380090185 creator A5063946775 @default.
• W4380090185 creator A5067186052 @default.
• W4380090185 creator A5080864025 @default.
• W4380090185 creator A5084203901 @default.
• W4380090185 date "2023-06-08" @default.
• W4380090185 modified "2023-10-15" @default.
• W4380090185 title "Human Pose Estimation via an Ultra-Lightweight Pose Distillation Network" @default.
• W4380090185 cites W1540144755 @default.
• W4380090185 cites W2030536784 @default.
• W4380090185 cites W2080873731 @default.
• W4380090185 cites W2097117768 @default.
• W4380090185 cites W2097151019 @default.
• W4380090185 cites W2128271252 @default.
• W4380090185 cites W2131263044 @default.
• W4380090185 cites W2155893237 @default.
• W4380090185 cites W2157982431 @default.
• W4380090185 cites W2307770531 @default.
• W4380090185 cites W2559085405 @default.
• W4380090185 cites W2612947062 @default.
• W4380090185 cites W2613192286 @default.
• W4380090185 cites W2752782242 @default.
• W4380090185 cites W2916798096 @default.
• W4380090185 cites W2962730651 @default.
• W4380090185 cites W2963402313 @default.
• W4380090185 cites W2963781481 @default.
• W4380090185 cites W2964062189 @default.
• W4380090185 cites W2964304707 @default.
• W4380090185 cites W3034399482 @default.
• W4380090185 cites W3098049078 @default.
• W4380090185 cites W3102288316 @default.
• W4380090185 cites W3110310592 @default.
• W4380090185 cites W3152887517 @default.
• W4380090185 cites W3171398643 @default.
• W4380090185 cites W3174053790 @default.
• W4380090185 cites W3176892444 @default.
• W4380090185 cites W3178774897 @default.
• W4380090185 cites W3187458216 @default.
• W4380090185 cites W3203925315 @default.
• W4380090185 cites W4205349208 @default.
• W4380090185 cites W4311723953 @default.
• W4380090185 cites W4313127332 @default.
• W4380090185 cites W4318499506 @default.
• W4380090185 cites W4319755384 @default.
• W4380090185 doi "https://doi.org/10.3390/electronics12122593" @default.
• W4380090185 hasPublicationYear "2023" @default.
• W4380090185 type Work @default.
• W4380090185 citedByCount "1" @default.
• W4380090185 countsByYear W43800901852023 @default.
• W4380090185 crossrefType "journal-article" @default.
• W4380090185 hasAuthorship W4380090185A5008213911 @default.
• W4380090185 hasAuthorship W4380090185A5025465795 @default.
• W4380090185 hasAuthorship W4380090185A5063946775 @default.
• W4380090185 hasAuthorship W4380090185A5067186052 @default.
• W4380090185 hasAuthorship W4380090185A5080864025 @default.
• W4380090185 hasAuthorship W4380090185A5084203901 @default.
• W4380090185 hasBestOaLocation W43800901851 @default.
• W4380090185 hasConcept C105339364 @default.
• W4380090185 hasConcept C111919701 @default.
• W4380090185 hasConcept C11413529 @default.
• W4380090185 hasConcept C119857082 @default.
• W4380090185 hasConcept C138885662 @default.
• W4380090185 hasConcept C149635348 @default.
• W4380090185 hasConcept C154945302 @default.
• W4380090185 hasConcept C165464430 @default.
• W4380090185 hasConcept C2776401178 @default.
• W4380090185 hasConcept C2780186347 @default.
• W4380090185 hasConcept C36613465 @default.
• W4380090185 hasConcept C38652104 @default.
• W4380090185 hasConcept C41008148 @default.
• W4380090185 hasConcept C41895202 @default.
• W4380090185 hasConcept C52102323 @default.
• W4380090185 hasConceptScore W4380090185C105339364 @default.
• W4380090185 hasConceptScore W4380090185C111919701 @default.
• W4380090185 hasConceptScore W4380090185C11413529 @default.
• W4380090185 hasConceptScore W4380090185C119857082 @default.
• W4380090185 hasConceptScore W4380090185C138885662 @default.
• W4380090185 hasConceptScore W4380090185C149635348 @default.
• W4380090185 hasConceptScore W4380090185C154945302 @default.
• W4380090185 hasConceptScore W4380090185C165464430 @default.
• W4380090185 hasConceptScore W4380090185C2776401178 @default.
• W4380090185 hasConceptScore W4380090185C2780186347 @default.
• W4380090185 hasConceptScore W4380090185C36613465 @default.
• W4380090185 hasConceptScore W4380090185C38652104 @default.
• W4380090185 hasConceptScore W4380090185C41008148 @default.
• W4380090185 hasConceptScore W4380090185C41895202 @default.
• W4380090185 hasConceptScore W4380090185C52102323 @default.
• W4380090185 hasFunder F4320321001 @default.
• W4380090185 hasIssue "12" @default.
• W4380090185 hasLocation W43800901851 @default.
• W4380090185 hasOpenAccess W4380090185 @default.
• W4380090185 hasPrimaryLocation W43800901851 @default.
• W4380090185 hasRelatedWork W1994602742 @default.
• W4380090185 hasRelatedWork W2198716702 @default.
• W4380090185 hasRelatedWork W2544359817 @default.

• next