Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202722484> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3202722484 endingPage "2380" @default.
- W3202722484 startingPage "2380" @default.
- W3202722484 abstract "Recently, people’s demand for action recognition has extended from the initial high classification accuracy to the high accuracy of the temporal action detection. It is challenging to meet the two requirements simultaneously. The key to behavior recognition lies in the quantity and quality of the extracted features. In this paper, a two-stream convolutional network is used. A three-dimensional convolutional neural network (3D-CNN) is used to extract spatiotemporal features from the consecutive frames. A two-dimensional convolutional neural network (2D-CNN) is used to extract spatial features from the key-frames. The integration of the two networks is excellent for improving the model’s accuracy and can complete the task of distinguishing the start–stop frame. In this paper, a multi-scale feature extraction method is presented to extract more abundant feature information. At the same time, a multi-task learning model is introduced. It can further improve the accuracy of classification via sharing the data between multiple tasks. The experimental result shows that the accuracy of the modified model is improved by 10%. Meanwhile, we propose the confidence gradient, which can optimize the distinguishing method of the start–stop frame to improve the temporal action detection accuracy. The experimental result shows that the accuracy has been enhanced by 11%." @default.
- W3202722484 created "2021-10-11" @default.
- W3202722484 creator A5017297950 @default.
- W3202722484 creator A5019479187 @default.
- W3202722484 creator A5048113245 @default.
- W3202722484 creator A5087098914 @default.
- W3202722484 creator A5087205961 @default.
- W3202722484 date "2021-09-29" @default.
- W3202722484 modified "2023-09-25" @default.
- W3202722484 title "Optimization of Action Recognition Model Based on Multi-Task Learning and Boundary Gradient" @default.
- W3202722484 cites W2322020277 @default.
- W3202722484 cites W2514340250 @default.
- W3202722484 cites W2716916105 @default.
- W3202722484 cites W2791307013 @default.
- W3202722484 cites W2907214745 @default.
- W3202722484 cites W2926527602 @default.
- W3202722484 cites W2929000277 @default.
- W3202722484 cites W2940791172 @default.
- W3202722484 cites W2940791683 @default.
- W3202722484 cites W3049318984 @default.
- W3202722484 cites W3119381934 @default.
- W3202722484 cites W3122458082 @default.
- W3202722484 cites W3123784868 @default.
- W3202722484 cites W3168279297 @default.
- W3202722484 doi "https://doi.org/10.3390/electronics10192380" @default.
- W3202722484 hasPublicationYear "2021" @default.
- W3202722484 type Work @default.
- W3202722484 sameAs 3202722484 @default.
- W3202722484 citedByCount "2" @default.
- W3202722484 countsByYear W32027224842021 @default.
- W3202722484 countsByYear W32027224842022 @default.
- W3202722484 crossrefType "journal-article" @default.
- W3202722484 hasAuthorship W3202722484A5017297950 @default.
- W3202722484 hasAuthorship W3202722484A5019479187 @default.
- W3202722484 hasAuthorship W3202722484A5048113245 @default.
- W3202722484 hasAuthorship W3202722484A5087098914 @default.
- W3202722484 hasAuthorship W3202722484A5087205961 @default.
- W3202722484 hasBestOaLocation W32027224841 @default.
- W3202722484 hasConcept C119857082 @default.
- W3202722484 hasConcept C126042441 @default.
- W3202722484 hasConcept C127413603 @default.
- W3202722484 hasConcept C138885662 @default.
- W3202722484 hasConcept C153180895 @default.
- W3202722484 hasConcept C154945302 @default.
- W3202722484 hasConcept C201995342 @default.
- W3202722484 hasConcept C26517878 @default.
- W3202722484 hasConcept C2776401178 @default.
- W3202722484 hasConcept C2780139006 @default.
- W3202722484 hasConcept C2780451532 @default.
- W3202722484 hasConcept C38652104 @default.
- W3202722484 hasConcept C41008148 @default.
- W3202722484 hasConcept C41895202 @default.
- W3202722484 hasConcept C50644808 @default.
- W3202722484 hasConcept C52622490 @default.
- W3202722484 hasConcept C76155785 @default.
- W3202722484 hasConcept C81363708 @default.
- W3202722484 hasConceptScore W3202722484C119857082 @default.
- W3202722484 hasConceptScore W3202722484C126042441 @default.
- W3202722484 hasConceptScore W3202722484C127413603 @default.
- W3202722484 hasConceptScore W3202722484C138885662 @default.
- W3202722484 hasConceptScore W3202722484C153180895 @default.
- W3202722484 hasConceptScore W3202722484C154945302 @default.
- W3202722484 hasConceptScore W3202722484C201995342 @default.
- W3202722484 hasConceptScore W3202722484C26517878 @default.
- W3202722484 hasConceptScore W3202722484C2776401178 @default.
- W3202722484 hasConceptScore W3202722484C2780139006 @default.
- W3202722484 hasConceptScore W3202722484C2780451532 @default.
- W3202722484 hasConceptScore W3202722484C38652104 @default.
- W3202722484 hasConceptScore W3202722484C41008148 @default.
- W3202722484 hasConceptScore W3202722484C41895202 @default.
- W3202722484 hasConceptScore W3202722484C50644808 @default.
- W3202722484 hasConceptScore W3202722484C52622490 @default.
- W3202722484 hasConceptScore W3202722484C76155785 @default.
- W3202722484 hasConceptScore W3202722484C81363708 @default.
- W3202722484 hasFunder F4320321001 @default.
- W3202722484 hasIssue "19" @default.
- W3202722484 hasLocation W32027224841 @default.
- W3202722484 hasOpenAccess W3202722484 @default.
- W3202722484 hasPrimaryLocation W32027224841 @default.
- W3202722484 hasRelatedWork W2059299633 @default.
- W3202722484 hasRelatedWork W2546942002 @default.
- W3202722484 hasRelatedWork W2732542196 @default.
- W3202722484 hasRelatedWork W2760085659 @default.
- W3202722484 hasRelatedWork W2767651786 @default.
- W3202722484 hasRelatedWork W2940977206 @default.
- W3202722484 hasRelatedWork W2969680539 @default.
- W3202722484 hasRelatedWork W2977314777 @default.
- W3202722484 hasRelatedWork W2995914718 @default.
- W3202722484 hasRelatedWork W3156786002 @default.
- W3202722484 hasVolume "10" @default.
- W3202722484 isParatext "false" @default.
- W3202722484 isRetracted "false" @default.
- W3202722484 magId "3202722484" @default.
- W3202722484 workType "article" @default.