Matches in SemOpenAlex for { <https://semopenalex.org/work/W3000273670> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W3000273670 endingPage "147" @default.
- W3000273670 startingPage "147" @default.
- W3000273670 abstract "Action recognition is an active research field that aims to recognize human actions and intentions from a series of observations of human behavior and the environment. Unlike image-based action recognition mainly using a two-dimensional (2D) convolutional neural network (CNN), one of the difficulties in video-based action recognition is that video action behavior should be able to characterize both short-term small movements and long-term temporal appearance information. Previous methods aim at analyzing video action behavior only using a basic framework of 3D CNN. However, these approaches have a limitation on analyzing fast action movements or abruptly appearing objects because of the limited coverage of convolutional filter. In this paper, we propose the aggregation of squeeze-and-excitation (SE) and self-attention (SA) modules with 3D CNN to analyze both short and long-term temporal action behavior efficiently. We successfully implemented SE and SA modules to present a novel approach to video action recognition that builds upon the current state-of-the-art methods and demonstrates better performance with UCF-101 and HMDB51 datasets. For example, we get accuracies of 92.5% (16f-clip) and 95.6% (64f-clip) with the UCF-101 dataset, and 68.1% (16f-clip) and 74.1% (64f-clip) with HMDB51 for the ResNext-101 architecture in a 3D CNN." @default.
- W3000273670 created "2020-01-23" @default.
- W3000273670 creator A5046569732 @default.
- W3000273670 creator A5065677543 @default.
- W3000273670 creator A5084129126 @default.
- W3000273670 date "2020-01-12" @default.
- W3000273670 modified "2023-10-16" @default.
- W3000273670 title "Action Recognition Using Deep 3D CNNs with Sequential Feature Aggregation and Attention" @default.
- W3000273670 cites W2884376066 @default.
- W3000273670 cites W2971355295 @default.
- W3000273670 doi "https://doi.org/10.3390/electronics9010147" @default.
- W3000273670 hasPublicationYear "2020" @default.
- W3000273670 type Work @default.
- W3000273670 sameAs 3000273670 @default.
- W3000273670 citedByCount "4" @default.
- W3000273670 countsByYear W30002736702020 @default.
- W3000273670 countsByYear W30002736702021 @default.
- W3000273670 crossrefType "journal-article" @default.
- W3000273670 hasAuthorship W3000273670A5046569732 @default.
- W3000273670 hasAuthorship W3000273670A5065677543 @default.
- W3000273670 hasAuthorship W3000273670A5084129126 @default.
- W3000273670 hasBestOaLocation W30002736701 @default.
- W3000273670 hasConcept C121332964 @default.
- W3000273670 hasConcept C138885662 @default.
- W3000273670 hasConcept C153180895 @default.
- W3000273670 hasConcept C154945302 @default.
- W3000273670 hasConcept C202444582 @default.
- W3000273670 hasConcept C2776401178 @default.
- W3000273670 hasConcept C2777212361 @default.
- W3000273670 hasConcept C2780791683 @default.
- W3000273670 hasConcept C2987834672 @default.
- W3000273670 hasConcept C31972630 @default.
- W3000273670 hasConcept C33923547 @default.
- W3000273670 hasConcept C41008148 @default.
- W3000273670 hasConcept C41895202 @default.
- W3000273670 hasConcept C61797465 @default.
- W3000273670 hasConcept C62520636 @default.
- W3000273670 hasConcept C81363708 @default.
- W3000273670 hasConcept C9652623 @default.
- W3000273670 hasConceptScore W3000273670C121332964 @default.
- W3000273670 hasConceptScore W3000273670C138885662 @default.
- W3000273670 hasConceptScore W3000273670C153180895 @default.
- W3000273670 hasConceptScore W3000273670C154945302 @default.
- W3000273670 hasConceptScore W3000273670C202444582 @default.
- W3000273670 hasConceptScore W3000273670C2776401178 @default.
- W3000273670 hasConceptScore W3000273670C2777212361 @default.
- W3000273670 hasConceptScore W3000273670C2780791683 @default.
- W3000273670 hasConceptScore W3000273670C2987834672 @default.
- W3000273670 hasConceptScore W3000273670C31972630 @default.
- W3000273670 hasConceptScore W3000273670C33923547 @default.
- W3000273670 hasConceptScore W3000273670C41008148 @default.
- W3000273670 hasConceptScore W3000273670C41895202 @default.
- W3000273670 hasConceptScore W3000273670C61797465 @default.
- W3000273670 hasConceptScore W3000273670C62520636 @default.
- W3000273670 hasConceptScore W3000273670C81363708 @default.
- W3000273670 hasConceptScore W3000273670C9652623 @default.
- W3000273670 hasFunder F4320321370 @default.
- W3000273670 hasFunder F4320321681 @default.
- W3000273670 hasIssue "1" @default.
- W3000273670 hasLocation W30002736701 @default.
- W3000273670 hasLocation W30002736702 @default.
- W3000273670 hasOpenAccess W3000273670 @default.
- W3000273670 hasPrimaryLocation W30002736701 @default.
- W3000273670 hasRelatedWork W1504288058 @default.
- W3000273670 hasRelatedWork W2017205855 @default.
- W3000273670 hasRelatedWork W2048505601 @default.
- W3000273670 hasRelatedWork W2116675934 @default.
- W3000273670 hasRelatedWork W2167293474 @default.
- W3000273670 hasRelatedWork W2175746458 @default.
- W3000273670 hasRelatedWork W2331674254 @default.
- W3000273670 hasRelatedWork W2760085659 @default.
- W3000273670 hasRelatedWork W3042897387 @default.
- W3000273670 hasRelatedWork W3093612317 @default.
- W3000273670 hasVolume "9" @default.
- W3000273670 isParatext "false" @default.
- W3000273670 isRetracted "false" @default.
- W3000273670 magId "3000273670" @default.
- W3000273670 workType "article" @default.