Matches in SemOpenAlex for { <https://semopenalex.org/work/W2018832017> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W2018832017 abstract "Multimedia Event Detection (MED) aims to identify events-also called scenes-in videos, such as a flash mob or a wedding ceremony. Audio content information complements cues such as visual content and text. In this paper, we explore the optimization of neural networks (NNs) for audio-based multimedia event classification, and discuss some insights towards more effectively using this paradigm for MED. We explore different architectures, in terms of number of layers and number of neurons. We also assess the performance impact of pre-training with Restricted Boltzmann Machines (RBMs) in contrast with random initialization, and explore the effect of varying the context window for the input to the NNs. Lastly, we compare the performance of Hidden Markov Models (HMMs) with a discriminative classifier for the event classification. We used the publicly available event-annotated YLI-MED dataset. Our results showed a performance improvement of more than 6% absolute accuracy compared to the latest results reported in the literature. Interestingly, these results were obtained with a single-layer neural network with random initialization, suggesting that standard approaches with deep learning and RBM pre-training are not fully adequate to address the high-level video event-classification task." @default.
- W2018832017 created "2016-06-24" @default.
- W2018832017 creator A5040811098 @default.
- W2018832017 creator A5062323483 @default.
- W2018832017 creator A5073250019 @default.
- W2018832017 creator A5083402055 @default.
- W2018832017 date "2015-10-30" @default.
- W2018832017 modified "2023-10-14" @default.
- W2018832017 title "Insights into Audio-Based Multimedia Event Classification with Neural Networks" @default.
- W2018832017 cites W2008415856 @default.
- W2018832017 cites W2022011789 @default.
- W2018832017 cites W2036931953 @default.
- W2018832017 cites W2125838338 @default.
- W2018832017 cites W2136922672 @default.
- W2018832017 cites W2147627917 @default.
- W2018832017 cites W2147768505 @default.
- W2018832017 cites W2913932916 @default.
- W2018832017 doi "https://doi.org/10.1145/2814815.2814816" @default.
- W2018832017 hasPublicationYear "2015" @default.
- W2018832017 type Work @default.
- W2018832017 sameAs 2018832017 @default.
- W2018832017 citedByCount "3" @default.
- W2018832017 countsByYear W20188320172016 @default.
- W2018832017 countsByYear W20188320172017 @default.
- W2018832017 crossrefType "proceedings-article" @default.
- W2018832017 hasAuthorship W2018832017A5040811098 @default.
- W2018832017 hasAuthorship W2018832017A5062323483 @default.
- W2018832017 hasAuthorship W2018832017A5073250019 @default.
- W2018832017 hasAuthorship W2018832017A5083402055 @default.
- W2018832017 hasConcept C121332964 @default.
- W2018832017 hasConcept C127220857 @default.
- W2018832017 hasConcept C13895895 @default.
- W2018832017 hasConcept C154945302 @default.
- W2018832017 hasConcept C2779662365 @default.
- W2018832017 hasConcept C28490314 @default.
- W2018832017 hasConcept C41008148 @default.
- W2018832017 hasConcept C49774154 @default.
- W2018832017 hasConcept C50644808 @default.
- W2018832017 hasConcept C62520636 @default.
- W2018832017 hasConcept C64922751 @default.
- W2018832017 hasConceptScore W2018832017C121332964 @default.
- W2018832017 hasConceptScore W2018832017C127220857 @default.
- W2018832017 hasConceptScore W2018832017C13895895 @default.
- W2018832017 hasConceptScore W2018832017C154945302 @default.
- W2018832017 hasConceptScore W2018832017C2779662365 @default.
- W2018832017 hasConceptScore W2018832017C28490314 @default.
- W2018832017 hasConceptScore W2018832017C41008148 @default.
- W2018832017 hasConceptScore W2018832017C49774154 @default.
- W2018832017 hasConceptScore W2018832017C50644808 @default.
- W2018832017 hasConceptScore W2018832017C62520636 @default.
- W2018832017 hasConceptScore W2018832017C64922751 @default.
- W2018832017 hasLocation W20188320171 @default.
- W2018832017 hasOpenAccess W2018832017 @default.
- W2018832017 hasPrimaryLocation W20188320171 @default.
- W2018832017 hasRelatedWork W2355862304 @default.
- W2018832017 hasRelatedWork W2356108042 @default.
- W2018832017 hasRelatedWork W2376796979 @default.
- W2018832017 hasRelatedWork W2379285345 @default.
- W2018832017 hasRelatedWork W2379418341 @default.
- W2018832017 hasRelatedWork W2380054981 @default.
- W2018832017 hasRelatedWork W2386387936 @default.
- W2018832017 hasRelatedWork W2393110101 @default.
- W2018832017 hasRelatedWork W3107474891 @default.
- W2018832017 hasRelatedWork W4239328682 @default.
- W2018832017 isParatext "false" @default.
- W2018832017 isRetracted "false" @default.
- W2018832017 magId "2018832017" @default.
- W2018832017 workType "article" @default.