Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385482616> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4385482616 abstract "Anchor-free temporal action detection methods have recently achieved many good results in solving the problem of flexible boundaries and different duration of actions. But the anchor-free methods use local features to predict the action boundaries so that it is sensitive to noises and prone to generate incomplete action proposals. Moreover, there exist long-term temporal dependencies between actions and temporal semantic consistency between action primitives in the same classes of actions. Therefore, we propose a snippet-level supervised contrastive learning-based transformer (SSCL-T) model for temporal action detection, which can learn semantically local and global temporal relationships in actions. This model learns the local temporal dynamic features of actions through local temporal coding and uses the transformer to model the global semantic dependencies between long-term actions. In addition, we utilize the action class information to learn the high-level semantic features of actions by designing a snippet-level supervised contrastive learning, forcing the temporal dynamic features of the same class of actions to be as close as possible and the features of different classes of actions to be as far away as possible, thus effectively realizing accurate prediction of action boundaries. Our model has been verified on two benchmark datasets ActivityNet-v1.3 and THUMOS14. The experimental results demonstrate that the proposed model has significantly improved on both datasets. Compared with the benchmark method BMN, the average mAP value has increased by 2.91% and 8.4% on ActivityNet-v1.3 and THUMOS14, respectively." @default.
- W4385482616 created "2023-08-03" @default.
- W4385482616 creator A5014341726 @default.
- W4385482616 creator A5067302737 @default.
- W4385482616 creator A5069470708 @default.
- W4385482616 creator A5085462851 @default.
- W4385482616 date "2023-06-18" @default.
- W4385482616 modified "2023-09-26" @default.
- W4385482616 title "Snippet-level Supervised Contrastive Learning-based Transformer for Temporal Action Detection" @default.
- W4385482616 cites W1927052826 @default.
- W4385482616 cites W2336403884 @default.
- W4385482616 cites W2461621749 @default.
- W4385482616 cites W2597958930 @default.
- W4385482616 cites W2755876276 @default.
- W4385482616 cites W2962876901 @default.
- W4385482616 cites W2964214371 @default.
- W4385482616 cites W2964216549 @default.
- W4385482616 cites W2983918066 @default.
- W4385482616 cites W2986407524 @default.
- W4385482616 cites W2997314266 @default.
- W4385482616 cites W2997706915 @default.
- W4385482616 cites W2998486508 @default.
- W4385482616 cites W2998582438 @default.
- W4385482616 cites W3034623254 @default.
- W4385482616 cites W3035251589 @default.
- W4385482616 cites W3092820804 @default.
- W4385482616 cites W3106041614 @default.
- W4385482616 cites W3128626728 @default.
- W4385482616 cites W3145586615 @default.
- W4385482616 cites W3176444885 @default.
- W4385482616 cites W3176641851 @default.
- W4385482616 cites W3202003978 @default.
- W4385482616 cites W4206706211 @default.
- W4385482616 cites W4213019189 @default.
- W4385482616 doi "https://doi.org/10.1109/ijcnn54540.2023.10191802" @default.
- W4385482616 hasPublicationYear "2023" @default.
- W4385482616 type Work @default.
- W4385482616 citedByCount "0" @default.
- W4385482616 crossrefType "proceedings-article" @default.
- W4385482616 hasAuthorship W4385482616A5014341726 @default.
- W4385482616 hasAuthorship W4385482616A5067302737 @default.
- W4385482616 hasAuthorship W4385482616A5069470708 @default.
- W4385482616 hasAuthorship W4385482616A5085462851 @default.
- W4385482616 hasConcept C119857082 @default.
- W4385482616 hasConcept C121332964 @default.
- W4385482616 hasConcept C13280743 @default.
- W4385482616 hasConcept C153180895 @default.
- W4385482616 hasConcept C154945302 @default.
- W4385482616 hasConcept C165801399 @default.
- W4385482616 hasConcept C185798385 @default.
- W4385482616 hasConcept C199360897 @default.
- W4385482616 hasConcept C205649164 @default.
- W4385482616 hasConcept C2777822670 @default.
- W4385482616 hasConcept C41008148 @default.
- W4385482616 hasConcept C62520636 @default.
- W4385482616 hasConcept C66322947 @default.
- W4385482616 hasConceptScore W4385482616C119857082 @default.
- W4385482616 hasConceptScore W4385482616C121332964 @default.
- W4385482616 hasConceptScore W4385482616C13280743 @default.
- W4385482616 hasConceptScore W4385482616C153180895 @default.
- W4385482616 hasConceptScore W4385482616C154945302 @default.
- W4385482616 hasConceptScore W4385482616C165801399 @default.
- W4385482616 hasConceptScore W4385482616C185798385 @default.
- W4385482616 hasConceptScore W4385482616C199360897 @default.
- W4385482616 hasConceptScore W4385482616C205649164 @default.
- W4385482616 hasConceptScore W4385482616C2777822670 @default.
- W4385482616 hasConceptScore W4385482616C41008148 @default.
- W4385482616 hasConceptScore W4385482616C62520636 @default.
- W4385482616 hasConceptScore W4385482616C66322947 @default.
- W4385482616 hasFunder F4320321001 @default.
- W4385482616 hasLocation W43854826161 @default.
- W4385482616 hasOpenAccess W4385482616 @default.
- W4385482616 hasPrimaryLocation W43854826161 @default.
- W4385482616 hasRelatedWork W112744582 @default.
- W4385482616 hasRelatedWork W1485630101 @default.
- W4385482616 hasRelatedWork W2030059621 @default.
- W4385482616 hasRelatedWork W2498017833 @default.
- W4385482616 hasRelatedWork W2961085424 @default.
- W4385482616 hasRelatedWork W4285260836 @default.
- W4385482616 hasRelatedWork W4286629047 @default.
- W4385482616 hasRelatedWork W4306321456 @default.
- W4385482616 hasRelatedWork W4306674287 @default.
- W4385482616 hasRelatedWork W4224009465 @default.
- W4385482616 isParatext "false" @default.
- W4385482616 isRetracted "false" @default.
- W4385482616 workType "article" @default.