Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312937345> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4312937345 abstract "The KL divergence loss function commonly used in existing models can represent a single mapping relationship of length distribution by learning specific visual content features, but it cannot accurately predict the length distribution of sentences in a one-to-many mapping relationship, resulting in the description of semantic information. incomplete. Second, the loss is calculated using a character-level negative log-likelihood function, ignoring sentence-level semantics, resulting in inaccurate semantic information of the generated descriptions. In this paper, a new length loss function is designed to adaptively adjust the error penalty by measuring the distance between the prediction and the reference length, so that the model can learn the optimal description length distribution in highly similar visual content. Secondly, through the semantic hidden state calculation of the decoding layer, a description generation loss function based on sentence semantics is designed, and the optimal sentence semantic description is iteratively obtained by comparing the semantics of the prediction and the reference description at the sentence level. The experimental results show that the model is tested on the MSVD and MSR-VTT datasets, and various indicators are significantly improved, which are better than the existing models." @default.
- W4312937345 created "2023-01-05" @default.
- W4312937345 creator A5033018056 @default.
- W4312937345 creator A5052256402 @default.
- W4312937345 creator A5058769847 @default.
- W4312937345 creator A5082625452 @default.
- W4312937345 date "2022-09-23" @default.
- W4312937345 modified "2023-09-23" @default.
- W4312937345 title "Video description method based on sentence semantics and length loss calculation" @default.
- W4312937345 cites W1573040851 @default.
- W4312937345 cites W2194775991 @default.
- W4312937345 cites W2951390634 @default.
- W4312937345 cites W2962990649 @default.
- W4312937345 cites W2984862483 @default.
- W4312937345 cites W2988753485 @default.
- W4312937345 cites W3034221024 @default.
- W4312937345 cites W3035365026 @default.
- W4312937345 cites W3035372819 @default.
- W4312937345 cites W3035725000 @default.
- W4312937345 cites W3039060838 @default.
- W4312937345 cites W3176425931 @default.
- W4312937345 cites W3190350044 @default.
- W4312937345 cites W4213152894 @default.
- W4312937345 doi "https://doi.org/10.1109/cei57409.2022.9950086" @default.
- W4312937345 hasPublicationYear "2022" @default.
- W4312937345 type Work @default.
- W4312937345 citedByCount "0" @default.
- W4312937345 crossrefType "proceedings-article" @default.
- W4312937345 hasAuthorship W4312937345A5033018056 @default.
- W4312937345 hasAuthorship W4312937345A5052256402 @default.
- W4312937345 hasAuthorship W4312937345A5058769847 @default.
- W4312937345 hasAuthorship W4312937345A5082625452 @default.
- W4312937345 hasConcept C11413529 @default.
- W4312937345 hasConcept C138885662 @default.
- W4312937345 hasConcept C14036430 @default.
- W4312937345 hasConcept C153180895 @default.
- W4312937345 hasConcept C154945302 @default.
- W4312937345 hasConcept C184337299 @default.
- W4312937345 hasConcept C199360897 @default.
- W4312937345 hasConcept C204321447 @default.
- W4312937345 hasConcept C207390915 @default.
- W4312937345 hasConcept C2777530160 @default.
- W4312937345 hasConcept C41008148 @default.
- W4312937345 hasConcept C41895202 @default.
- W4312937345 hasConcept C57273362 @default.
- W4312937345 hasConcept C78458016 @default.
- W4312937345 hasConcept C86803240 @default.
- W4312937345 hasConceptScore W4312937345C11413529 @default.
- W4312937345 hasConceptScore W4312937345C138885662 @default.
- W4312937345 hasConceptScore W4312937345C14036430 @default.
- W4312937345 hasConceptScore W4312937345C153180895 @default.
- W4312937345 hasConceptScore W4312937345C154945302 @default.
- W4312937345 hasConceptScore W4312937345C184337299 @default.
- W4312937345 hasConceptScore W4312937345C199360897 @default.
- W4312937345 hasConceptScore W4312937345C204321447 @default.
- W4312937345 hasConceptScore W4312937345C207390915 @default.
- W4312937345 hasConceptScore W4312937345C2777530160 @default.
- W4312937345 hasConceptScore W4312937345C41008148 @default.
- W4312937345 hasConceptScore W4312937345C41895202 @default.
- W4312937345 hasConceptScore W4312937345C57273362 @default.
- W4312937345 hasConceptScore W4312937345C78458016 @default.
- W4312937345 hasConceptScore W4312937345C86803240 @default.
- W4312937345 hasLocation W43129373451 @default.
- W4312937345 hasOpenAccess W4312937345 @default.
- W4312937345 hasPrimaryLocation W43129373451 @default.
- W4312937345 hasRelatedWork W1517743118 @default.
- W4312937345 hasRelatedWork W1541271503 @default.
- W4312937345 hasRelatedWork W1567338489 @default.
- W4312937345 hasRelatedWork W159132833 @default.
- W4312937345 hasRelatedWork W1978971213 @default.
- W4312937345 hasRelatedWork W2033261979 @default.
- W4312937345 hasRelatedWork W2998299629 @default.
- W4312937345 hasRelatedWork W3107474891 @default.
- W4312937345 hasRelatedWork W3185439372 @default.
- W4312937345 hasRelatedWork W38394648 @default.
- W4312937345 isParatext "false" @default.
- W4312937345 isRetracted "false" @default.
- W4312937345 workType "article" @default.