Matches in SemOpenAlex for { <https://semopenalex.org/work/W3080111863> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3080111863 endingPage "4761" @default.
- W3080111863 startingPage "4761" @default.
- W3080111863 abstract "This study proposes a framework for describing a scene change using natural language text based on indoor scene observations conducted before and after a scene change. The recognition of scene changes plays an essential role in a variety of real-world applications, such as scene anomaly detection. Most scene understanding research has focused on static scenes. Most existing scene change captioning methods detect scene changes from single-view RGB images, neglecting the underlying three-dimensional structures. Previous three-dimensional scene change captioning methods use simulated scenes consisting of geometry primitives, making it unsuitable for real-world applications. To solve these problems, we automatically generated large-scale indoor scene change caption datasets. We propose an end-to-end framework for describing scene changes from various input modalities, namely, RGB images, depth images, and point cloud data, which are available in most robot applications. We conducted experiments with various input modalities and models and evaluated model performance using datasets with various levels of complexity. Experimental results show that the models that combine RGB images and point cloud data as input achieve high performance in sentence generation and caption correctness and are robust for change type understanding for datasets with high complexity. The developed datasets and models contribute to the study of indoor scene change understanding." @default.
- W3080111863 created "2020-09-01" @default.
- W3080111863 creator A5011507481 @default.
- W3080111863 creator A5013573921 @default.
- W3080111863 creator A5029961156 @default.
- W3080111863 creator A5043995369 @default.
- W3080111863 creator A5060846465 @default.
- W3080111863 date "2020-08-23" @default.
- W3080111863 modified "2023-10-02" @default.
- W3080111863 title "Indoor Scene Change Captioning Based on Multimodality Data" @default.
- W3080111863 cites W1983364832 @default.
- W3080111863 cites W2123132313 @default.
- W3080111863 cites W2126698653 @default.
- W3080111863 cites W2136848157 @default.
- W3080111863 cites W2610961739 @default.
- W3080111863 cites W2808492412 @default.
- W3080111863 cites W2890952074 @default.
- W3080111863 cites W2941914178 @default.
- W3080111863 cites W3010257550 @default.
- W3080111863 cites W3036594286 @default.
- W3080111863 doi "https://doi.org/10.3390/s20174761" @default.
- W3080111863 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7506858" @default.
- W3080111863 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32842516" @default.
- W3080111863 hasPublicationYear "2020" @default.
- W3080111863 type Work @default.
- W3080111863 sameAs 3080111863 @default.
- W3080111863 citedByCount "14" @default.
- W3080111863 countsByYear W30801118632020 @default.
- W3080111863 countsByYear W30801118632021 @default.
- W3080111863 countsByYear W30801118632022 @default.
- W3080111863 countsByYear W30801118632023 @default.
- W3080111863 crossrefType "journal-article" @default.
- W3080111863 hasAuthorship W3080111863A5011507481 @default.
- W3080111863 hasAuthorship W3080111863A5013573921 @default.
- W3080111863 hasAuthorship W3080111863A5029961156 @default.
- W3080111863 hasAuthorship W3080111863A5043995369 @default.
- W3080111863 hasAuthorship W3080111863A5060846465 @default.
- W3080111863 hasBestOaLocation W30801118631 @default.
- W3080111863 hasConcept C115961682 @default.
- W3080111863 hasConcept C131979681 @default.
- W3080111863 hasConcept C154945302 @default.
- W3080111863 hasConcept C157657479 @default.
- W3080111863 hasConcept C199360897 @default.
- W3080111863 hasConcept C203595873 @default.
- W3080111863 hasConcept C2524010 @default.
- W3080111863 hasConcept C28719098 @default.
- W3080111863 hasConcept C31972630 @default.
- W3080111863 hasConcept C33923547 @default.
- W3080111863 hasConcept C41008148 @default.
- W3080111863 hasConcept C55439883 @default.
- W3080111863 hasConcept C82990744 @default.
- W3080111863 hasConceptScore W3080111863C115961682 @default.
- W3080111863 hasConceptScore W3080111863C131979681 @default.
- W3080111863 hasConceptScore W3080111863C154945302 @default.
- W3080111863 hasConceptScore W3080111863C157657479 @default.
- W3080111863 hasConceptScore W3080111863C199360897 @default.
- W3080111863 hasConceptScore W3080111863C203595873 @default.
- W3080111863 hasConceptScore W3080111863C2524010 @default.
- W3080111863 hasConceptScore W3080111863C28719098 @default.
- W3080111863 hasConceptScore W3080111863C31972630 @default.
- W3080111863 hasConceptScore W3080111863C33923547 @default.
- W3080111863 hasConceptScore W3080111863C41008148 @default.
- W3080111863 hasConceptScore W3080111863C55439883 @default.
- W3080111863 hasConceptScore W3080111863C82990744 @default.
- W3080111863 hasIssue "17" @default.
- W3080111863 hasLocation W30801118631 @default.
- W3080111863 hasLocation W30801118632 @default.
- W3080111863 hasLocation W30801118633 @default.
- W3080111863 hasLocation W30801118634 @default.
- W3080111863 hasOpenAccess W3080111863 @default.
- W3080111863 hasPrimaryLocation W30801118631 @default.
- W3080111863 hasRelatedWork W2052518016 @default.
- W3080111863 hasRelatedWork W2081022503 @default.
- W3080111863 hasRelatedWork W2085956791 @default.
- W3080111863 hasRelatedWork W2283162247 @default.
- W3080111863 hasRelatedWork W2314488738 @default.
- W3080111863 hasRelatedWork W2524507886 @default.
- W3080111863 hasRelatedWork W2771653066 @default.
- W3080111863 hasRelatedWork W2901949253 @default.
- W3080111863 hasRelatedWork W4212983513 @default.
- W3080111863 hasRelatedWork W4293067784 @default.
- W3080111863 hasVolume "20" @default.
- W3080111863 isParatext "false" @default.
- W3080111863 isRetracted "false" @default.
- W3080111863 magId "3080111863" @default.
- W3080111863 workType "article" @default.