Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381186388> ?p ?o ?g. }
- W4381186388 endingPage "366" @default.
- W4381186388 startingPage "357" @default.
- W4381186388 abstract "Trajectory representation learning aims to embed trajectory sequences into fixed-length vector representations while preserving their original spatio-temporal feature proximity. Existing works either learn trajectory representations for specific mining tasks or fail to utilize large amounts of unlabeled trajectory data for representation learning. In this work, we propose a self-supervised Trajectory representation learning based on Reconstruction Contrastive Learning called TrajRCL. To be specific, TrajRCL first obtains low-distortion and high-fidelity views of trajectories through trajectory augmentation. Then, TrajRCL leverages a Transformer based encoder–decoder network to reconstruct low-distortion view trajectories to approximate high-fidelity trajectories. Self-supervised contrastive learning is finally used to enhance the consistency of the two view’s trajectory representations. Extensive experiments on two real-world demonstrate the superiority of our model over state-of-the-art baselines and significant efficiency on similarity trajectory search and k-NN query." @default.
- W4381186388 created "2023-06-20" @default.
- W4381186388 creator A5003545631 @default.
- W4381186388 creator A5010444377 @default.
- W4381186388 creator A5021981732 @default.
- W4381186388 creator A5044307720 @default.
- W4381186388 creator A5072125449 @default.
- W4381186388 creator A5079377634 @default.
- W4381186388 date "2023-11-01" @default.
- W4381186388 modified "2023-10-12" @default.
- W4381186388 title "Self-supervised contrastive representation learning for large-scale trajectories" @default.
- W4381186388 cites W1597504361 @default.
- W4381186388 cites W1990588199 @default.
- W4381186388 cites W2057135445 @default.
- W4381186388 cites W2100668339 @default.
- W4381186388 cites W2118371392 @default.
- W4381186388 cites W2124299914 @default.
- W4381186388 cites W2313076811 @default.
- W4381186388 cites W2603192734 @default.
- W4381186388 cites W2604411573 @default.
- W4381186388 cites W2613997951 @default.
- W4381186388 cites W2739805805 @default.
- W4381186388 cites W2762529682 @default.
- W4381186388 cites W2783272285 @default.
- W4381186388 cites W2795402696 @default.
- W4381186388 cites W2808425487 @default.
- W4381186388 cites W2841091033 @default.
- W4381186388 cites W2947144452 @default.
- W4381186388 cites W2951431594 @default.
- W4381186388 cites W2965122367 @default.
- W4381186388 cites W2997605985 @default.
- W4381186388 cites W2997646554 @default.
- W4381186388 cites W3012510853 @default.
- W4381186388 cites W3016404289 @default.
- W4381186388 cites W3021364764 @default.
- W4381186388 cites W3035524453 @default.
- W4381186388 cites W3035705826 @default.
- W4381186388 cites W3080292238 @default.
- W4381186388 cites W3087124270 @default.
- W4381186388 cites W3104097132 @default.
- W4381186388 cites W3128267727 @default.
- W4381186388 cites W3167652394 @default.
- W4381186388 cites W3169134134 @default.
- W4381186388 cites W3169978599 @default.
- W4381186388 cites W3173650575 @default.
- W4381186388 cites W3187467055 @default.
- W4381186388 cites W3188202574 @default.
- W4381186388 cites W3189729741 @default.
- W4381186388 cites W3207160263 @default.
- W4381186388 cites W3210395416 @default.
- W4381186388 cites W3210938103 @default.
- W4381186388 cites W3211072770 @default.
- W4381186388 cites W4206397113 @default.
- W4381186388 cites W4283366068 @default.
- W4381186388 cites W4285603440 @default.
- W4381186388 cites W4285604412 @default.
- W4381186388 cites W4290927668 @default.
- W4381186388 cites W4290943973 @default.
- W4381186388 cites W4306317480 @default.
- W4381186388 cites W4320009727 @default.
- W4381186388 doi "https://doi.org/10.1016/j.future.2023.05.033" @default.
- W4381186388 hasPublicationYear "2023" @default.
- W4381186388 type Work @default.
- W4381186388 citedByCount "0" @default.
- W4381186388 crossrefType "journal-article" @default.
- W4381186388 hasAuthorship W4381186388A5003545631 @default.
- W4381186388 hasAuthorship W4381186388A5010444377 @default.
- W4381186388 hasAuthorship W4381186388A5021981732 @default.
- W4381186388 hasAuthorship W4381186388A5044307720 @default.
- W4381186388 hasAuthorship W4381186388A5072125449 @default.
- W4381186388 hasAuthorship W4381186388A5079377634 @default.
- W4381186388 hasConcept C103278499 @default.
- W4381186388 hasConcept C111919701 @default.
- W4381186388 hasConcept C115961682 @default.
- W4381186388 hasConcept C118505674 @default.
- W4381186388 hasConcept C119857082 @default.
- W4381186388 hasConcept C121332964 @default.
- W4381186388 hasConcept C1276947 @default.
- W4381186388 hasConcept C13662910 @default.
- W4381186388 hasConcept C153180895 @default.
- W4381186388 hasConcept C154945302 @default.
- W4381186388 hasConcept C17744445 @default.
- W4381186388 hasConcept C199539241 @default.
- W4381186388 hasConcept C2776359362 @default.
- W4381186388 hasConcept C2776459999 @default.
- W4381186388 hasConcept C41008148 @default.
- W4381186388 hasConcept C59404180 @default.
- W4381186388 hasConcept C76155785 @default.
- W4381186388 hasConcept C94625758 @default.
- W4381186388 hasConceptScore W4381186388C103278499 @default.
- W4381186388 hasConceptScore W4381186388C111919701 @default.
- W4381186388 hasConceptScore W4381186388C115961682 @default.
- W4381186388 hasConceptScore W4381186388C118505674 @default.
- W4381186388 hasConceptScore W4381186388C119857082 @default.
- W4381186388 hasConceptScore W4381186388C121332964 @default.
- W4381186388 hasConceptScore W4381186388C1276947 @default.
- W4381186388 hasConceptScore W4381186388C13662910 @default.
- W4381186388 hasConceptScore W4381186388C153180895 @default.