Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313203673> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4313203673 endingPage "8" @default.
- W4313203673 startingPage "1" @default.
- W4313203673 abstract "Labeling is onerous for crowd counting as it should annotate each individual in crowd images. Recently, several methods have been proposed for semi-supervised crowd counting to reduce the labeling efforts. Given a limited labeling budget, they typically select a few crowd images and densely label all individuals in each of them. Despite the promising results, we argue the None-or-All labeling strategy is suboptimal as the densely labeled individuals in each crowd image usually appear similar while the massive unlabeled crowd images may contain entirely diverse individuals. To this end, we propose to break the labeling chain of previous methods and make the first attempt to reduce spatial labeling redundancy for semi-supervised crowd counting. First, instead of annotating all the regions in each crowd image, we propose to annotate the representative ones only. We analyze the region representativeness from both vertical and horizontal directions of initially estimated density maps, and formulate them as cluster centers of Gaussian Mixture Models. Additionally, to leverage the rich unlabeled regions, we exploit the similarities among individuals in each crowd image to directly supervise the unlabeled regions via feature propagation instead of the error-prone label propagation employed in the previous methods. In this way, we can transfer the original spatial labeling redundancy caused by individual similarities to effective supervision signals on the unlabeled regions. Extensive experiments on the widely-used benchmarks demonstrate that our method can outperform previous best approaches by a large margin." @default.
- W4313203673 created "2023-01-06" @default.
- W4313203673 creator A5005393674 @default.
- W4313203673 creator A5048891976 @default.
- W4313203673 creator A5052217585 @default.
- W4313203673 creator A5056103024 @default.
- W4313203673 creator A5057261945 @default.
- W4313203673 creator A5058145513 @default.
- W4313203673 creator A5012404534 @default.
- W4313203673 date "2023-01-01" @default.
- W4313203673 modified "2023-10-16" @default.
- W4313203673 title "Reducing Spatial Labeling Redundancy for Active Semi-Supervised Crowd Counting" @default.
- W4313203673 doi "https://doi.org/10.1109/tpami.2022.3232712" @default.
- W4313203673 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37015627" @default.
- W4313203673 hasPublicationYear "2023" @default.
- W4313203673 type Work @default.
- W4313203673 citedByCount "2" @default.
- W4313203673 countsByYear W43132036732023 @default.
- W4313203673 crossrefType "journal-article" @default.
- W4313203673 hasAuthorship W4313203673A5005393674 @default.
- W4313203673 hasAuthorship W4313203673A5012404534 @default.
- W4313203673 hasAuthorship W4313203673A5048891976 @default.
- W4313203673 hasAuthorship W4313203673A5052217585 @default.
- W4313203673 hasAuthorship W4313203673A5056103024 @default.
- W4313203673 hasAuthorship W4313203673A5057261945 @default.
- W4313203673 hasAuthorship W4313203673A5058145513 @default.
- W4313203673 hasConcept C105795698 @default.
- W4313203673 hasConcept C111919701 @default.
- W4313203673 hasConcept C115961682 @default.
- W4313203673 hasConcept C119857082 @default.
- W4313203673 hasConcept C152124472 @default.
- W4313203673 hasConcept C153083717 @default.
- W4313203673 hasConcept C153180895 @default.
- W4313203673 hasConcept C154945302 @default.
- W4313203673 hasConcept C165696696 @default.
- W4313203673 hasConcept C2776145971 @default.
- W4313203673 hasConcept C31972630 @default.
- W4313203673 hasConcept C33923547 @default.
- W4313203673 hasConcept C37381756 @default.
- W4313203673 hasConcept C38652104 @default.
- W4313203673 hasConcept C41008148 @default.
- W4313203673 hasConcept C61224824 @default.
- W4313203673 hasConcept C774472 @default.
- W4313203673 hasConceptScore W4313203673C105795698 @default.
- W4313203673 hasConceptScore W4313203673C111919701 @default.
- W4313203673 hasConceptScore W4313203673C115961682 @default.
- W4313203673 hasConceptScore W4313203673C119857082 @default.
- W4313203673 hasConceptScore W4313203673C152124472 @default.
- W4313203673 hasConceptScore W4313203673C153083717 @default.
- W4313203673 hasConceptScore W4313203673C153180895 @default.
- W4313203673 hasConceptScore W4313203673C154945302 @default.
- W4313203673 hasConceptScore W4313203673C165696696 @default.
- W4313203673 hasConceptScore W4313203673C2776145971 @default.
- W4313203673 hasConceptScore W4313203673C31972630 @default.
- W4313203673 hasConceptScore W4313203673C33923547 @default.
- W4313203673 hasConceptScore W4313203673C37381756 @default.
- W4313203673 hasConceptScore W4313203673C38652104 @default.
- W4313203673 hasConceptScore W4313203673C41008148 @default.
- W4313203673 hasConceptScore W4313203673C61224824 @default.
- W4313203673 hasConceptScore W4313203673C774472 @default.
- W4313203673 hasFunder F4320321001 @default.
- W4313203673 hasFunder F4320321921 @default.
- W4313203673 hasLocation W43132036731 @default.
- W4313203673 hasLocation W43132036732 @default.
- W4313203673 hasOpenAccess W4313203673 @default.
- W4313203673 hasPrimaryLocation W43132036731 @default.
- W4313203673 hasRelatedWork W1574409659 @default.
- W4313203673 hasRelatedWork W1983333094 @default.
- W4313203673 hasRelatedWork W2130228941 @default.
- W4313203673 hasRelatedWork W2161229648 @default.
- W4313203673 hasRelatedWork W2183053529 @default.
- W4313203673 hasRelatedWork W2309573947 @default.
- W4313203673 hasRelatedWork W2334388150 @default.
- W4313203673 hasRelatedWork W2787282005 @default.
- W4313203673 hasRelatedWork W2954105047 @default.
- W4313203673 hasRelatedWork W2993674027 @default.
- W4313203673 isParatext "false" @default.
- W4313203673 isRetracted "false" @default.
- W4313203673 workType "article" @default.