Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200612769> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4200612769 endingPage "41" @default.
- W4200612769 startingPage "25" @default.
- W4200612769 abstract "Despite Convolutional Neural Networks (CNNs) based approaches have been successful in objects detection, they predominantly focus on positioning discriminative regions while overlooking the internal holistic part-whole associations within objects. This would ultimately lead to the neglect of feature relationships between object and its parts as well as among those parts, both of which are significantly helpful for detecting discriminative parts. In this paper, we propose to look insider the objects by digging into part-whole feature correlations and take the attempts to leverage those correlations endowed by the Capsule Network (CapsNet) for robust object detection. Actually, highly correlated capsules across adjacent layers share high familiarity, which will be more likely to be routed together. In light of this, we take such correlations between different capsules of the preceding training samples as an awareness to constrain the subsequent candidate voting scope during the routing procedure, and a Feature Correlation-Steered CapsNet (FCS-CapsNet) with Locally-Constrained Expectation-Maximum (EM) Routing Agreement (LCEMRA) is proposed. Different from conventional EM routing, LCEMRA stipulates that only those relevant low-level capsules (parts) meeting the requirement of quantified intra-object cohesiveness can be clustered to make up high-level capsules (objects). In doing so, part-object associations can be dug by transformation weighting matrixes between capsules layers during such part backtracking procedure. LCEMRA enables low-level capsules to selectively gather projections from a non-spatially-fixed set of high-level capsules. Experiments on VOC2007, VOC2012, HKU-IS, DUTS, and COCO show that FCS-CapsNet can achieve promising object detection effects across multiple evaluation metrics, which are on-par with state-of-the-arts." @default.
- W4200612769 created "2021-12-31" @default.
- W4200612769 creator A5013019306 @default.
- W4200612769 creator A5038344148 @default.
- W4200612769 creator A5039297893 @default.
- W4200612769 creator A5078092833 @default.
- W4200612769 date "2022-03-01" @default.
- W4200612769 modified "2023-10-15" @default.
- W4200612769 title "Feature Correlation-Steered Capsule Network for object detection" @default.
- W4200612769 cites W2031489346 @default.
- W4200612769 cites W2071821890 @default.
- W4200612769 cites W2088049833 @default.
- W4200612769 cites W2109255472 @default.
- W4200612769 cites W2618530766 @default.
- W4200612769 cites W2806070179 @default.
- W4200612769 cites W2884367402 @default.
- W4200612769 cites W2895526696 @default.
- W4200612769 cites W2910363199 @default.
- W4200612769 cites W2911968856 @default.
- W4200612769 cites W2919352650 @default.
- W4200612769 cites W2944401411 @default.
- W4200612769 cites W2964775615 @default.
- W4200612769 cites W2988472227 @default.
- W4200612769 cites W2988916019 @default.
- W4200612769 cites W2991363140 @default.
- W4200612769 cites W2994144150 @default.
- W4200612769 cites W3033059362 @default.
- W4200612769 cites W3054755450 @default.
- W4200612769 cites W3102701618 @default.
- W4200612769 cites W3104979525 @default.
- W4200612769 cites W3105291825 @default.
- W4200612769 cites W4239147634 @default.
- W4200612769 cites W4300655869 @default.
- W4200612769 cites W639708223 @default.
- W4200612769 doi "https://doi.org/10.1016/j.neunet.2021.12.003" @default.
- W4200612769 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34953299" @default.
- W4200612769 hasPublicationYear "2022" @default.
- W4200612769 type Work @default.
- W4200612769 citedByCount "12" @default.
- W4200612769 countsByYear W42006127692022 @default.
- W4200612769 countsByYear W42006127692023 @default.
- W4200612769 crossrefType "journal-article" @default.
- W4200612769 hasAuthorship W4200612769A5013019306 @default.
- W4200612769 hasAuthorship W4200612769A5038344148 @default.
- W4200612769 hasAuthorship W4200612769A5039297893 @default.
- W4200612769 hasAuthorship W4200612769A5078092833 @default.
- W4200612769 hasConcept C126838900 @default.
- W4200612769 hasConcept C138885662 @default.
- W4200612769 hasConcept C153180895 @default.
- W4200612769 hasConcept C154945302 @default.
- W4200612769 hasConcept C183115368 @default.
- W4200612769 hasConcept C2776151529 @default.
- W4200612769 hasConcept C2776401178 @default.
- W4200612769 hasConcept C31972630 @default.
- W4200612769 hasConcept C41008148 @default.
- W4200612769 hasConcept C41895202 @default.
- W4200612769 hasConcept C71924100 @default.
- W4200612769 hasConcept C81363708 @default.
- W4200612769 hasConcept C97931131 @default.
- W4200612769 hasConceptScore W4200612769C126838900 @default.
- W4200612769 hasConceptScore W4200612769C138885662 @default.
- W4200612769 hasConceptScore W4200612769C153180895 @default.
- W4200612769 hasConceptScore W4200612769C154945302 @default.
- W4200612769 hasConceptScore W4200612769C183115368 @default.
- W4200612769 hasConceptScore W4200612769C2776151529 @default.
- W4200612769 hasConceptScore W4200612769C2776401178 @default.
- W4200612769 hasConceptScore W4200612769C31972630 @default.
- W4200612769 hasConceptScore W4200612769C41008148 @default.
- W4200612769 hasConceptScore W4200612769C41895202 @default.
- W4200612769 hasConceptScore W4200612769C71924100 @default.
- W4200612769 hasConceptScore W4200612769C81363708 @default.
- W4200612769 hasConceptScore W4200612769C97931131 @default.
- W4200612769 hasFunder F4320313895 @default.
- W4200612769 hasFunder F4320321001 @default.
- W4200612769 hasFunder F4320321106 @default.
- W4200612769 hasLocation W42006127691 @default.
- W4200612769 hasLocation W42006127692 @default.
- W4200612769 hasOpenAccess W4200612769 @default.
- W4200612769 hasPrimaryLocation W42006127691 @default.
- W4200612769 hasRelatedWork W2049003611 @default.
- W4200612769 hasRelatedWork W2052835778 @default.
- W4200612769 hasRelatedWork W2153315159 @default.
- W4200612769 hasRelatedWork W2180954594 @default.
- W4200612769 hasRelatedWork W2283145973 @default.
- W4200612769 hasRelatedWork W2965546495 @default.
- W4200612769 hasRelatedWork W3103844505 @default.
- W4200612769 hasRelatedWork W3131692135 @default.
- W4200612769 hasRelatedWork W4205463238 @default.
- W4200612769 hasRelatedWork W2969228573 @default.
- W4200612769 hasVolume "147" @default.
- W4200612769 isParatext "false" @default.
- W4200612769 isRetracted "false" @default.
- W4200612769 workType "article" @default.