Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308804762> ?p ?o ?g. }
- W4308804762 endingPage "119240" @default.
- W4308804762 startingPage "119240" @default.
- W4308804762 abstract "The inability to fully exploit domain-specific knowledge and the lack of an effective integration method have been the difficulties and focus of multimodal sentiment analysis. In this paper, we propose heterogeneous graph convolution with in-domain self-supervised multi-task learning for multimodal sentiment analysis (HIS-MSA) to solve these problems. Firstly, HIS-MSA carries out the second pre-trained with different self-supervised training strategies to fully mine the unique knowledge of the in-domain corpus, and give BERT the awareness of professional field. Secondly, HIS-MSA uses heterogeneous graph, which is good at integrating heterogeneous knowledge, to fuse feature from multiple sources. Finally, a unimodal label generation module is used to jointly guide multimodal tasks and unimodal tasks to balance independent and complementary information between the modalities. We conducted experiments on the datasets MOSI and MOSEI, which have 2199 and 23454 video segments respectively. The results show an average improvement of approximately 1.5 points in all metrics compared to the current state-of-the-art model." @default.
- W4308804762 created "2022-11-15" @default.
- W4308804762 creator A5041501733 @default.
- W4308804762 creator A5049801163 @default.
- W4308804762 creator A5053794277 @default.
- W4308804762 creator A5061609383 @default.
- W4308804762 creator A5087798028 @default.
- W4308804762 date "2023-03-01" @default.
- W4308804762 modified "2023-10-01" @default.
- W4308804762 title "Heterogeneous graph convolution based on In-domain Self-supervision for Multimodal Sentiment Analysis" @default.
- W4308804762 cites W1958932515 @default.
- W4308804762 cites W1998257453 @default.
- W4308804762 cites W2029996593 @default.
- W4308804762 cites W2075010670 @default.
- W4308804762 cites W2095176743 @default.
- W4308804762 cites W2250861254 @default.
- W4308804762 cites W2577325523 @default.
- W4308804762 cites W2724935142 @default.
- W4308804762 cites W2740550900 @default.
- W4308804762 cites W2788776247 @default.
- W4308804762 cites W2883409523 @default.
- W4308804762 cites W2886193235 @default.
- W4308804762 cites W2899197626 @default.
- W4308804762 cites W2925618549 @default.
- W4308804762 cites W2946218857 @default.
- W4308804762 cites W2963341956 @default.
- W4308804762 cites W2963710346 @default.
- W4308804762 cites W2964010806 @default.
- W4308804762 cites W2964051877 @default.
- W4308804762 cites W2964216663 @default.
- W4308804762 cites W2964346351 @default.
- W4308804762 cites W2969078176 @default.
- W4308804762 cites W2970398671 @default.
- W4308804762 cites W2970583420 @default.
- W4308804762 cites W2971152344 @default.
- W4308804762 cites W2984452801 @default.
- W4308804762 cites W2997026866 @default.
- W4308804762 cites W3034266838 @default.
- W4308804762 cites W3034353423 @default.
- W4308804762 cites W3034849760 @default.
- W4308804762 cites W3035431747 @default.
- W4308804762 cites W3037572520 @default.
- W4308804762 cites W3048195943 @default.
- W4308804762 cites W3093051361 @default.
- W4308804762 cites W3093400813 @default.
- W4308804762 cites W3101998545 @default.
- W4308804762 cites W3105484484 @default.
- W4308804762 cites W3128412859 @default.
- W4308804762 cites W3167136668 @default.
- W4308804762 cites W3171536535 @default.
- W4308804762 cites W3173549566 @default.
- W4308804762 cites W3176028309 @default.
- W4308804762 cites W3197510788 @default.
- W4308804762 cites W3199093474 @default.
- W4308804762 cites W3199305386 @default.
- W4308804762 cites W3206529771 @default.
- W4308804762 cites W3214432797 @default.
- W4308804762 doi "https://doi.org/10.1016/j.eswa.2022.119240" @default.
- W4308804762 hasPublicationYear "2023" @default.
- W4308804762 type Work @default.
- W4308804762 citedByCount "2" @default.
- W4308804762 countsByYear W43088047622023 @default.
- W4308804762 crossrefType "journal-article" @default.
- W4308804762 hasAuthorship W4308804762A5041501733 @default.
- W4308804762 hasAuthorship W4308804762A5049801163 @default.
- W4308804762 hasAuthorship W4308804762A5053794277 @default.
- W4308804762 hasAuthorship W4308804762A5061609383 @default.
- W4308804762 hasAuthorship W4308804762A5087798028 @default.
- W4308804762 hasConcept C119857082 @default.
- W4308804762 hasConcept C132525143 @default.
- W4308804762 hasConcept C134306372 @default.
- W4308804762 hasConcept C153180895 @default.
- W4308804762 hasConcept C154945302 @default.
- W4308804762 hasConcept C165696696 @default.
- W4308804762 hasConcept C202444582 @default.
- W4308804762 hasConcept C207685749 @default.
- W4308804762 hasConcept C33923547 @default.
- W4308804762 hasConcept C36503486 @default.
- W4308804762 hasConcept C38652104 @default.
- W4308804762 hasConcept C41008148 @default.
- W4308804762 hasConcept C45347329 @default.
- W4308804762 hasConcept C50644808 @default.
- W4308804762 hasConcept C66402592 @default.
- W4308804762 hasConcept C80444323 @default.
- W4308804762 hasConcept C9652623 @default.
- W4308804762 hasConceptScore W4308804762C119857082 @default.
- W4308804762 hasConceptScore W4308804762C132525143 @default.
- W4308804762 hasConceptScore W4308804762C134306372 @default.
- W4308804762 hasConceptScore W4308804762C153180895 @default.
- W4308804762 hasConceptScore W4308804762C154945302 @default.
- W4308804762 hasConceptScore W4308804762C165696696 @default.
- W4308804762 hasConceptScore W4308804762C202444582 @default.
- W4308804762 hasConceptScore W4308804762C207685749 @default.
- W4308804762 hasConceptScore W4308804762C33923547 @default.
- W4308804762 hasConceptScore W4308804762C36503486 @default.
- W4308804762 hasConceptScore W4308804762C38652104 @default.
- W4308804762 hasConceptScore W4308804762C41008148 @default.
- W4308804762 hasConceptScore W4308804762C45347329 @default.