Matches in SemOpenAlex for { <https://semopenalex.org/work/W3210832011> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W3210832011 endingPage "286" @default.
- W3210832011 startingPage "275" @default.
- W3210832011 abstract "Currently, image captioning has been widely studied with the development of deep neural networks. However, seldom work has been conducted to develop captioning models for three-dimensional (3D) visual data, for example, point clouds, which are now popularly employed for vision perception. Technically, most of these models first project the 3D shapes into multiple images, and then use the existing or similar framework for image captioning models to fulfill the task. Consequently, within such a technical framework, a large amount of useful information hidden in 3D vision is inevitably lost. In this paper, a captioning model for visual scenes directly based on point clouds is proposed. First, a deep model with densely connected point convolution is developed to extract visual features directly on point clouds, and the multi-task learning method is adopted to improve the visual features. Then, the visual features are converted into sentences through a caption generation module. As a whole, an end-to-end model is constructed for the task of 3D scene captioning. This model makes full use of the rich semantic information in point clouds, and generate more accurate captions. Since there do not exist large-scale datasets for this task, in this paper two new datasets are created on existing point cloud datasets by manually labeling captions. Comprehensive experiments conducted on three datasets (including one public benchmark) indicate the effectiveness of our model." @default.
- W3210832011 created "2021-11-08" @default.
- W3210832011 creator A5022683187 @default.
- W3210832011 creator A5040673285 @default.
- W3210832011 creator A5057613243 @default.
- W3210832011 creator A5072815126 @default.
- W3210832011 date "2021-01-01" @default.
- W3210832011 modified "2023-10-12" @default.
- W3210832011 title "3D-SceneCaptioner: Visual Scene Captioning Network for Three-Dimensional Point Clouds" @default.
- W3210832011 cites W125693051 @default.
- W3210832011 cites W1644641054 @default.
- W3210832011 cites W1895577753 @default.
- W3210832011 cites W1956340063 @default.
- W3210832011 cites W2101105183 @default.
- W3210832011 cites W2139501017 @default.
- W3210832011 cites W2594519801 @default.
- W3210832011 cites W2621571501 @default.
- W3210832011 cites W2745461083 @default.
- W3210832011 cites W2788628880 @default.
- W3210832011 cites W2949708697 @default.
- W3210832011 cites W2963048248 @default.
- W3210832011 cites W2963084599 @default.
- W3210832011 cites W2964078384 @default.
- W3210832011 cites W2983141445 @default.
- W3210832011 cites W2990613095 @default.
- W3210832011 cites W3003478339 @default.
- W3210832011 cites W3034655362 @default.
- W3210832011 cites W3093319304 @default.
- W3210832011 cites W3114244404 @default.
- W3210832011 doi "https://doi.org/10.1007/978-3-030-88007-1_23" @default.
- W3210832011 hasPublicationYear "2021" @default.
- W3210832011 type Work @default.
- W3210832011 sameAs 3210832011 @default.
- W3210832011 citedByCount "0" @default.
- W3210832011 crossrefType "book-chapter" @default.
- W3210832011 hasAuthorship W3210832011A5022683187 @default.
- W3210832011 hasAuthorship W3210832011A5040673285 @default.
- W3210832011 hasAuthorship W3210832011A5057613243 @default.
- W3210832011 hasAuthorship W3210832011A5072815126 @default.
- W3210832011 hasConcept C115961682 @default.
- W3210832011 hasConcept C121684516 @default.
- W3210832011 hasConcept C131979681 @default.
- W3210832011 hasConcept C154945302 @default.
- W3210832011 hasConcept C157657479 @default.
- W3210832011 hasConcept C2524010 @default.
- W3210832011 hasConcept C28719098 @default.
- W3210832011 hasConcept C31972630 @default.
- W3210832011 hasConcept C33923547 @default.
- W3210832011 hasConcept C41008148 @default.
- W3210832011 hasConceptScore W3210832011C115961682 @default.
- W3210832011 hasConceptScore W3210832011C121684516 @default.
- W3210832011 hasConceptScore W3210832011C131979681 @default.
- W3210832011 hasConceptScore W3210832011C154945302 @default.
- W3210832011 hasConceptScore W3210832011C157657479 @default.
- W3210832011 hasConceptScore W3210832011C2524010 @default.
- W3210832011 hasConceptScore W3210832011C28719098 @default.
- W3210832011 hasConceptScore W3210832011C31972630 @default.
- W3210832011 hasConceptScore W3210832011C33923547 @default.
- W3210832011 hasConceptScore W3210832011C41008148 @default.
- W3210832011 hasLocation W32108320111 @default.
- W3210832011 hasOpenAccess W3210832011 @default.
- W3210832011 hasPrimaryLocation W32108320111 @default.
- W3210832011 hasRelatedWork W2033574012 @default.
- W3210832011 hasRelatedWork W2111347602 @default.
- W3210832011 hasRelatedWork W2979718872 @default.
- W3210832011 hasRelatedWork W3006763290 @default.
- W3210832011 hasRelatedWork W3151946617 @default.
- W3210832011 hasRelatedWork W3202424074 @default.
- W3210832011 hasRelatedWork W3204162010 @default.
- W3210832011 hasRelatedWork W4290774832 @default.
- W3210832011 hasRelatedWork W4310007291 @default.
- W3210832011 hasRelatedWork W4323338571 @default.
- W3210832011 isParatext "false" @default.
- W3210832011 isRetracted "false" @default.
- W3210832011 magId "3210832011" @default.
- W3210832011 workType "book-chapter" @default.