Matches in SemOpenAlex for { <https://semopenalex.org/work/W2937887488> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W2937887488 abstract "Videos have become widespread due to the ease of obtaining and going share via social platform. Event recognition in video has gained more and more attention in computer vision. This is a hard task that requires extracting meaningful spatiotemporal features for event recognition, mainly due to complexity and diversity of video events. Many proposed networks learn spatial features and temporal separately. In this paper, we propose a simple, yet effective approach for spatio-temporal features' learning: using deep spatial-temporal neural networks based on convolution 3D. The architecture is shown in Fig. 1. The network can capture the motion information in multiple adjacent frames and appearance information simultaneously. Most of the famous 2D CNN networks follow a regular pattern: the former of convolution kernel size is bigger and the number of channel in latter layers increase, such as alexnet. So we choose the way that contacting two continuous convolutional layers to instead of a convolutional layer which its kernel size is bigger through synthetical consideration. We carry out experiments on KTH dataset, and evaluate them using 5-fold method. And this paper introduce two simple method of increasing the amount of training data and improving the performance on both. Experimental result shows that our model achieve an accuracy of 95.33% on KTH dataset, we further demonstrate that our model is a general and effective architecture through compared to other algorithms, including hand-crafted algorithms and other CNNs." @default.
- W2937887488 created "2019-04-25" @default.
- W2937887488 creator A5019270002 @default.
- W2937887488 creator A5043577877 @default.
- W2937887488 creator A5053193108 @default.
- W2937887488 date "2018-07-01" @default.
- W2937887488 modified "2023-09-27" @default.
- W2937887488 title "Event Recognition Based on 3D Convolutional Networks" @default.
- W2937887488 cites W1900913856 @default.
- W2937887488 cites W2962790054 @default.
- W2937887488 cites W2964191259 @default.
- W2937887488 cites W2964214371 @default.
- W2937887488 cites W2964227963 @default.
- W2937887488 doi "https://doi.org/10.1109/cyber.2018.8688320" @default.
- W2937887488 hasPublicationYear "2018" @default.
- W2937887488 type Work @default.
- W2937887488 sameAs 2937887488 @default.
- W2937887488 citedByCount "1" @default.
- W2937887488 countsByYear W29378874882021 @default.
- W2937887488 crossrefType "proceedings-article" @default.
- W2937887488 hasAuthorship W2937887488A5019270002 @default.
- W2937887488 hasAuthorship W2937887488A5043577877 @default.
- W2937887488 hasAuthorship W2937887488A5053193108 @default.
- W2937887488 hasConcept C108583219 @default.
- W2937887488 hasConcept C111472728 @default.
- W2937887488 hasConcept C114614502 @default.
- W2937887488 hasConcept C119857082 @default.
- W2937887488 hasConcept C121332964 @default.
- W2937887488 hasConcept C138885662 @default.
- W2937887488 hasConcept C153180895 @default.
- W2937887488 hasConcept C154945302 @default.
- W2937887488 hasConcept C2779662365 @default.
- W2937887488 hasConcept C2780586882 @default.
- W2937887488 hasConcept C33923547 @default.
- W2937887488 hasConcept C41008148 @default.
- W2937887488 hasConcept C45347329 @default.
- W2937887488 hasConcept C50644808 @default.
- W2937887488 hasConcept C62520636 @default.
- W2937887488 hasConcept C74193536 @default.
- W2937887488 hasConcept C81363708 @default.
- W2937887488 hasConceptScore W2937887488C108583219 @default.
- W2937887488 hasConceptScore W2937887488C111472728 @default.
- W2937887488 hasConceptScore W2937887488C114614502 @default.
- W2937887488 hasConceptScore W2937887488C119857082 @default.
- W2937887488 hasConceptScore W2937887488C121332964 @default.
- W2937887488 hasConceptScore W2937887488C138885662 @default.
- W2937887488 hasConceptScore W2937887488C153180895 @default.
- W2937887488 hasConceptScore W2937887488C154945302 @default.
- W2937887488 hasConceptScore W2937887488C2779662365 @default.
- W2937887488 hasConceptScore W2937887488C2780586882 @default.
- W2937887488 hasConceptScore W2937887488C33923547 @default.
- W2937887488 hasConceptScore W2937887488C41008148 @default.
- W2937887488 hasConceptScore W2937887488C45347329 @default.
- W2937887488 hasConceptScore W2937887488C50644808 @default.
- W2937887488 hasConceptScore W2937887488C62520636 @default.
- W2937887488 hasConceptScore W2937887488C74193536 @default.
- W2937887488 hasConceptScore W2937887488C81363708 @default.
- W2937887488 hasLocation W29378874881 @default.
- W2937887488 hasOpenAccess W2937887488 @default.
- W2937887488 hasPrimaryLocation W29378874881 @default.
- W2937887488 hasRelatedWork W2163969215 @default.
- W2937887488 hasRelatedWork W2572787276 @default.
- W2937887488 hasRelatedWork W2755968140 @default.
- W2937887488 hasRelatedWork W2901435809 @default.
- W2937887488 hasRelatedWork W3110443126 @default.
- W2937887488 hasRelatedWork W3193641238 @default.
- W2937887488 hasRelatedWork W4205549623 @default.
- W2937887488 hasRelatedWork W4214895820 @default.
- W2937887488 hasRelatedWork W4245792239 @default.
- W2937887488 hasRelatedWork W4285816666 @default.
- W2937887488 isParatext "false" @default.
- W2937887488 isRetracted "false" @default.
- W2937887488 magId "2937887488" @default.
- W2937887488 workType "article" @default.