FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2999688610> ?p ?o ?g. }

• W2999688610 endingPage "447" @default.
• W2999688610 startingPage "447" @default.
• W2999688610 abstract "Across the globe, remote image data is rapidly being collected for the assessment of benthic communities from shallow to extremely deep waters on continental slopes to the abyssal seas. Exploiting this data is presently limited by the time it takes for experts to identify organisms found in these images. With this limitation in mind, a large effort has been made globally to introduce automation and machine learning algorithms to accelerate both classification and assessment of marine benthic biota. One major issue lies with organisms that move with swell and currents, such as kelps. This paper presents an automatic hierarchical classification method local binary classification as opposed to the conventional flat classification to classify kelps in images collected by autonomous underwater vehicles. The proposed kelp classification approach exploits learned feature representations extracted from deep residual networks. We show that these generic features outperform the traditional off-the-shelf CNN features and the conventional hand-crafted features. Experiments also demonstrate that the hierarchical classification method outperforms the traditional parallel multi-class classifications by a significant margin (90.0% vs. 57.6% and 77.2% vs. 59.0%) on Benthoz15 and Rottnest datasets respectively. Furthermore, we compare different hierarchical classification approaches and experimentally show that the sibling hierarchical training approach outperforms the inclusive hierarchical approach by a significant margin. We also report an application of our proposed method to study the change in kelp cover over time for annually repeated AUV surveys." @default.
• W2999688610 created "2020-01-23" @default.
• W2999688610 creator A5000328299 @default.
• W2999688610 creator A5002219416 @default.
• W2999688610 creator A5005352988 @default.
• W2999688610 creator A5009750573 @default.
• W2999688610 creator A5011352836 @default.
• W2999688610 creator A5014216530 @default.
• W2999688610 creator A5020686179 @default.
• W2999688610 creator A5048231327 @default.
• W2999688610 creator A5062573833 @default.
• W2999688610 date "2020-01-13" @default.
• W2999688610 modified "2023-10-09" @default.
• W2999688610 title "Automatic Hierarchical Classification of Kelps Using Deep Residual Features" @default.
• W2999688610 cites W1519478720 @default.
• W2999688610 cites W1554992090 @default.
• W2999688610 cites W1925775338 @default.
• W2999688610 cites W1968511627 @default.
• W2999688610 cites W1981367618 @default.
• W2999688610 cites W1983835534 @default.
• W2999688610 cites W1987853315 @default.
• W2999688610 cites W2011435702 @default.
• W2999688610 cites W2039447327 @default.
• W2999688610 cites W2051621840 @default.
• W2999688610 cites W2052281895 @default.
• W2999688610 cites W2061291156 @default.
• W2999688610 cites W2066942950 @default.
• W2999688610 cites W2073328162 @default.
• W2999688610 cites W2080219328 @default.
• W2999688610 cites W2083119440 @default.
• W2999688610 cites W2115769223 @default.
• W2999688610 cites W2130353931 @default.
• W2999688610 cites W2140361685 @default.
• W2999688610 cites W2150766729 @default.
• W2999688610 cites W2170153270 @default.
• W2999688610 cites W2258850155 @default.
• W2999688610 cites W2317160870 @default.
• W2999688610 cites W2467909811 @default.
• W2999688610 cites W2473009902 @default.
• W2999688610 cites W2528261749 @default.
• W2999688610 cites W2740722806 @default.
• W2999688610 cites W2783353659 @default.
• W2999688610 cites W2964050365 @default.
• W2999688610 cites W4239510810 @default.
• W2999688610 doi "https://doi.org/10.3390/s20020447" @default.
• W2999688610 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7013955" @default.
• W2999688610 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31941132" @default.
• W2999688610 hasPublicationYear "2020" @default.
• W2999688610 type Work @default.
• W2999688610 sameAs 2999688610 @default.
• W2999688610 citedByCount "25" @default.
• W2999688610 countsByYear W29996886102020 @default.
• W2999688610 countsByYear W29996886102021 @default.
• W2999688610 countsByYear W29996886102022 @default.
• W2999688610 countsByYear W29996886102023 @default.
• W2999688610 crossrefType "journal-article" @default.
• W2999688610 hasAuthorship W2999688610A5000328299 @default.
• W2999688610 hasAuthorship W2999688610A5002219416 @default.
• W2999688610 hasAuthorship W2999688610A5005352988 @default.
• W2999688610 hasAuthorship W2999688610A5009750573 @default.
• W2999688610 hasAuthorship W2999688610A5011352836 @default.
• W2999688610 hasAuthorship W2999688610A5014216530 @default.
• W2999688610 hasAuthorship W2999688610A5020686179 @default.
• W2999688610 hasAuthorship W2999688610A5048231327 @default.
• W2999688610 hasAuthorship W2999688610A5062573833 @default.
• W2999688610 hasBestOaLocation W29996886101 @default.
• W2999688610 hasConcept C111368507 @default.
• W2999688610 hasConcept C11413529 @default.
• W2999688610 hasConcept C115961682 @default.
• W2999688610 hasConcept C119857082 @default.
• W2999688610 hasConcept C12267149 @default.
• W2999688610 hasConcept C127313418 @default.
• W2999688610 hasConcept C138885662 @default.
• W2999688610 hasConcept C153180895 @default.
• W2999688610 hasConcept C153274386 @default.
• W2999688610 hasConcept C154945302 @default.
• W2999688610 hasConcept C155512373 @default.
• W2999688610 hasConcept C185798385 @default.
• W2999688610 hasConcept C18903297 @default.
• W2999688610 hasConcept C205649164 @default.
• W2999688610 hasConcept C2776401178 @default.
• W2999688610 hasConcept C2776705890 @default.
• W2999688610 hasConcept C41008148 @default.
• W2999688610 hasConcept C41895202 @default.
• W2999688610 hasConcept C58640448 @default.
• W2999688610 hasConcept C66905080 @default.
• W2999688610 hasConcept C75294576 @default.
• W2999688610 hasConcept C774472 @default.
• W2999688610 hasConcept C86803240 @default.
• W2999688610 hasConcept C98083399 @default.
• W2999688610 hasConceptScore W2999688610C111368507 @default.
• W2999688610 hasConceptScore W2999688610C11413529 @default.
• W2999688610 hasConceptScore W2999688610C115961682 @default.
• W2999688610 hasConceptScore W2999688610C119857082 @default.
• W2999688610 hasConceptScore W2999688610C12267149 @default.
• W2999688610 hasConceptScore W2999688610C127313418 @default.
• W2999688610 hasConceptScore W2999688610C138885662 @default.
• W2999688610 hasConceptScore W2999688610C153180895 @default.

• next