Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383820778> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4383820778 endingPage "8003" @default.
- W4383820778 startingPage "8003" @default.
- W4383820778 abstract "Introduction: Convolutional neural networks (CNNs) have maintained their dominance in deep learning methods for human action recognition (HAR) and other computer vision tasks. However, the need for a large amount of training data always restricts the performance of CNNs. Method: This paper is inspired by the two-stream network, where a CNN is deployed to train the network by using the spatial and temporal aspects of an activity, thus exploiting the strengths of both networks to achieve better accuracy. Contributions: Our contribution is twofold: first, we deploy an enhanced spatial stream, and it is demonstrated that models pre-trained on a larger dataset, when used in the spatial stream, yield good performance instead of training the entire model from scratch. Second, a dataset augmentation technique is presented to minimize overfitting of CNNs, where we increase the dataset size by performing various transformations on the images such as rotation and flipping, etc. Results: UCF101 is a standard benchmark dataset for action videos, and our architecture has been trained and validated on it. Compared with the other two-stream networks, our results outperformed them in terms of accuracy." @default.
- W4383820778 created "2023-07-11" @default.
- W4383820778 creator A5005093152 @default.
- W4383820778 creator A5014265935 @default.
- W4383820778 creator A5026348064 @default.
- W4383820778 creator A5047007749 @default.
- W4383820778 creator A5052637357 @default.
- W4383820778 creator A5058105216 @default.
- W4383820778 creator A5083084430 @default.
- W4383820778 date "2023-07-08" @default.
- W4383820778 modified "2023-09-27" @default.
- W4383820778 title "Enhanced Spatial Stream of Two-Stream Network Using Optical Flow for Human Action Recognition" @default.
- W4383820778 cites W1522734439 @default.
- W4383820778 cites W1975325338 @default.
- W4383820778 cites W1983364832 @default.
- W4383820778 cites W1983705368 @default.
- W4383820778 cites W2016053056 @default.
- W4383820778 cites W2105101328 @default.
- W4383820778 cites W2117539524 @default.
- W4383820778 cites W2128951574 @default.
- W4383820778 cites W2165698076 @default.
- W4383820778 cites W2342662179 @default.
- W4383820778 cites W2418691539 @default.
- W4383820778 cites W2508429489 @default.
- W4383820778 cites W2618530766 @default.
- W4383820778 cites W2746726611 @default.
- W4383820778 cites W2747474452 @default.
- W4383820778 cites W2804340531 @default.
- W4383820778 cites W2935741426 @default.
- W4383820778 cites W2948058585 @default.
- W4383820778 cites W2963091558 @default.
- W4383820778 cites W2963820951 @default.
- W4383820778 cites W3049318984 @default.
- W4383820778 cites W3080916918 @default.
- W4383820778 cites W3095522972 @default.
- W4383820778 cites W3209517344 @default.
- W4383820778 cites W4249279051 @default.
- W4383820778 cites W4253146657 @default.
- W4383820778 cites W4285148907 @default.
- W4383820778 doi "https://doi.org/10.3390/app13148003" @default.
- W4383820778 hasPublicationYear "2023" @default.
- W4383820778 type Work @default.
- W4383820778 citedByCount "0" @default.
- W4383820778 crossrefType "journal-article" @default.
- W4383820778 hasAuthorship W4383820778A5005093152 @default.
- W4383820778 hasAuthorship W4383820778A5014265935 @default.
- W4383820778 hasAuthorship W4383820778A5026348064 @default.
- W4383820778 hasAuthorship W4383820778A5047007749 @default.
- W4383820778 hasAuthorship W4383820778A5052637357 @default.
- W4383820778 hasAuthorship W4383820778A5058105216 @default.
- W4383820778 hasAuthorship W4383820778A5083084430 @default.
- W4383820778 hasBestOaLocation W43838207781 @default.
- W4383820778 hasConcept C119857082 @default.
- W4383820778 hasConcept C153180895 @default.
- W4383820778 hasConcept C154945302 @default.
- W4383820778 hasConcept C185798385 @default.
- W4383820778 hasConcept C205649164 @default.
- W4383820778 hasConcept C22019652 @default.
- W4383820778 hasConcept C2777212361 @default.
- W4383820778 hasConcept C2987834672 @default.
- W4383820778 hasConcept C41008148 @default.
- W4383820778 hasConcept C50644808 @default.
- W4383820778 hasConcept C58640448 @default.
- W4383820778 hasConcept C81363708 @default.
- W4383820778 hasConceptScore W4383820778C119857082 @default.
- W4383820778 hasConceptScore W4383820778C153180895 @default.
- W4383820778 hasConceptScore W4383820778C154945302 @default.
- W4383820778 hasConceptScore W4383820778C185798385 @default.
- W4383820778 hasConceptScore W4383820778C205649164 @default.
- W4383820778 hasConceptScore W4383820778C22019652 @default.
- W4383820778 hasConceptScore W4383820778C2777212361 @default.
- W4383820778 hasConceptScore W4383820778C2987834672 @default.
- W4383820778 hasConceptScore W4383820778C41008148 @default.
- W4383820778 hasConceptScore W4383820778C50644808 @default.
- W4383820778 hasConceptScore W4383820778C58640448 @default.
- W4383820778 hasConceptScore W4383820778C81363708 @default.
- W4383820778 hasIssue "14" @default.
- W4383820778 hasLocation W43838207781 @default.
- W4383820778 hasOpenAccess W4383820778 @default.
- W4383820778 hasPrimaryLocation W43838207781 @default.
- W4383820778 hasRelatedWork W2767651786 @default.
- W4383820778 hasRelatedWork W2989932438 @default.
- W4383820778 hasRelatedWork W3011996705 @default.
- W4383820778 hasRelatedWork W3081496756 @default.
- W4383820778 hasRelatedWork W3099765033 @default.
- W4383820778 hasRelatedWork W3175189414 @default.
- W4383820778 hasRelatedWork W4308353688 @default.
- W4383820778 hasRelatedWork W4309224979 @default.
- W4383820778 hasRelatedWork W4312501200 @default.
- W4383820778 hasRelatedWork W4313289428 @default.
- W4383820778 hasVolume "13" @default.
- W4383820778 isParatext "false" @default.
- W4383820778 isRetracted "false" @default.
- W4383820778 workType "article" @default.