Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200095085> ?p ?o ?g. }
- W4200095085 endingPage "8356" @default.
- W4200095085 startingPage "8356" @default.
- W4200095085 abstract "In this paper, we tackle the problem of predicting the affective responses of movie viewers, based on the content of the movies. Current studies on this topic focus on video representation learning and fusion techniques to combine the extracted features for predicting affect. Yet, these typically, while ignoring the correlation between multiple modality inputs, ignore the correlation between temporal inputs (i.e., sequential features). To explore these correlations, a neural network architecture-namely AttendAffectNet (AAN)-uses the self-attention mechanism for predicting the emotions of movie viewers from different input modalities. Particularly, visual, audio, and text features are considered for predicting emotions (and expressed in terms of valence and arousal). We analyze three variants of our proposed AAN: Feature AAN, Temporal AAN, and Mixed AAN. The Feature AAN applies the self-attention mechanism in an innovative way on the features extracted from the different modalities (including video, audio, and movie subtitles) of a whole movie to, thereby, capture the relationships between them. The Temporal AAN takes the time domain of the movies and the sequential dependency of affective responses into account. In the Temporal AAN, self-attention is applied on the concatenated (multimodal) feature vectors representing different subsequent movie segments. In the Mixed AAN, we combine the strong points of the Feature AAN and the Temporal AAN, by applying self-attention first on vectors of features obtained from different modalities in each movie segment and then on the feature representations of all subsequent (temporal) movie segments. We extensively trained and validated our proposed AAN on both the MediaEval 2016 dataset for the Emotional Impact of Movies Task and the extended COGNIMUSE dataset. Our experiments demonstrate that audio features play a more influential role than those extracted from video and movie subtitles when predicting the emotions of movie viewers on these datasets. The models that use all visual, audio, and text features simultaneously as their inputs performed better than those using features extracted from each modality separately. In addition, the Feature AAN outperformed other AAN variants on the above-mentioned datasets, highlighting the importance of taking different features as context to one another when fusing them. The Feature AAN also performed better than the baseline models when predicting the valence dimension." @default.
- W4200095085 created "2021-12-31" @default.
- W4200095085 creator A5025034643 @default.
- W4200095085 creator A5069548004 @default.
- W4200095085 creator A5074019528 @default.
- W4200095085 creator A5084445353 @default.
- W4200095085 date "2021-12-14" @default.
- W4200095085 modified "2023-10-18" @default.
- W4200095085 title "AttendAffectNet–Emotion Prediction of Movie Viewers Using Multimodal Fusion with Self-Attention" @default.
- W4200095085 cites W1480583224 @default.
- W4200095085 cites W1483662103 @default.
- W4200095085 cites W1973976002 @default.
- W4200095085 cites W1983364832 @default.
- W4200095085 cites W2018431463 @default.
- W4200095085 cites W2044807399 @default.
- W4200095085 cites W2075953807 @default.
- W4200095085 cites W2084793887 @default.
- W4200095085 cites W2109606373 @default.
- W4200095085 cites W2114025269 @default.
- W4200095085 cites W2115505341 @default.
- W4200095085 cites W2117450581 @default.
- W4200095085 cites W2123260696 @default.
- W4200095085 cites W2123504579 @default.
- W4200095085 cites W2126890968 @default.
- W4200095085 cites W2127023913 @default.
- W4200095085 cites W2127236700 @default.
- W4200095085 cites W2143197238 @default.
- W4200095085 cites W2147863532 @default.
- W4200095085 cites W2149628368 @default.
- W4200095085 cites W2162418306 @default.
- W4200095085 cites W2164480306 @default.
- W4200095085 cites W2168031754 @default.
- W4200095085 cites W2203271703 @default.
- W4200095085 cites W2493916176 @default.
- W4200095085 cites W2584561145 @default.
- W4200095085 cites W2585658440 @default.
- W4200095085 cites W2605649771 @default.
- W4200095085 cites W2624340939 @default.
- W4200095085 cites W2731964405 @default.
- W4200095085 cites W2742409927 @default.
- W4200095085 cites W2752234108 @default.
- W4200095085 cites W2790495655 @default.
- W4200095085 cites W2951975883 @default.
- W4200095085 cites W2979860911 @default.
- W4200095085 cites W2990604978 @default.
- W4200095085 cites W2990786216 @default.
- W4200095085 cites W2991856582 @default.
- W4200095085 cites W3140110584 @default.
- W4200095085 cites W4213206451 @default.
- W4200095085 cites W4243499798 @default.
- W4200095085 cites W4294877277 @default.
- W4200095085 doi "https://doi.org/10.3390/s21248356" @default.
- W4200095085 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34960450" @default.
- W4200095085 hasPublicationYear "2021" @default.
- W4200095085 type Work @default.
- W4200095085 citedByCount "8" @default.
- W4200095085 countsByYear W42000950852022 @default.
- W4200095085 countsByYear W42000950852023 @default.
- W4200095085 crossrefType "journal-article" @default.
- W4200095085 hasAuthorship W4200095085A5025034643 @default.
- W4200095085 hasAuthorship W4200095085A5069548004 @default.
- W4200095085 hasAuthorship W4200095085A5074019528 @default.
- W4200095085 hasAuthorship W4200095085A5084445353 @default.
- W4200095085 hasBestOaLocation W42000950851 @default.
- W4200095085 hasConcept C117220453 @default.
- W4200095085 hasConcept C120665830 @default.
- W4200095085 hasConcept C121332964 @default.
- W4200095085 hasConcept C138885662 @default.
- W4200095085 hasConcept C144024400 @default.
- W4200095085 hasConcept C153180895 @default.
- W4200095085 hasConcept C154945302 @default.
- W4200095085 hasConcept C15744967 @default.
- W4200095085 hasConcept C168900304 @default.
- W4200095085 hasConcept C169760540 @default.
- W4200095085 hasConcept C169900460 @default.
- W4200095085 hasConcept C192209626 @default.
- W4200095085 hasConcept C2524010 @default.
- W4200095085 hasConcept C2776401178 @default.
- W4200095085 hasConcept C2779903281 @default.
- W4200095085 hasConcept C2780226545 @default.
- W4200095085 hasConcept C28490314 @default.
- W4200095085 hasConcept C3020774634 @default.
- W4200095085 hasConcept C33923547 @default.
- W4200095085 hasConcept C36289849 @default.
- W4200095085 hasConcept C41008148 @default.
- W4200095085 hasConcept C41895202 @default.
- W4200095085 hasConcept C62520636 @default.
- W4200095085 hasConcept C6438553 @default.
- W4200095085 hasConcept C66402592 @default.
- W4200095085 hasConceptScore W4200095085C117220453 @default.
- W4200095085 hasConceptScore W4200095085C120665830 @default.
- W4200095085 hasConceptScore W4200095085C121332964 @default.
- W4200095085 hasConceptScore W4200095085C138885662 @default.
- W4200095085 hasConceptScore W4200095085C144024400 @default.
- W4200095085 hasConceptScore W4200095085C153180895 @default.
- W4200095085 hasConceptScore W4200095085C154945302 @default.
- W4200095085 hasConceptScore W4200095085C15744967 @default.
- W4200095085 hasConceptScore W4200095085C168900304 @default.