Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890140145> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2890140145 abstract "Group emotion recognition in the wild has received much attention in computer vision community. It is a very challenge issue, due to interactions taking place between various numbers of people, different occlusions. According to human cognitive and behavioral researches, background and facial expression play a dominating role in the perception of group’s mood. Hence, in this paper, we propose a novel approach that combined these two features for image-based group emotion recognition with feature correlation enhancement. The feature enhancement is mainly reflected in two parts. For facial expression feature extraction, we plug non-local blocks into Xception network to enhance the feature correlation of different positions in low-level, which can avoid the fast loss of position information of the traditional CNNs and effectively enhance the network’s feature representation capability. For global scene information, we build a bilinear convolutional neural network (B-CNN) consisting of VGG16 networks to model local pairwise feature interactions in a translationally invariant manner. The experimental results show that the fused feature could effectively improve the performance." @default.
- W2890140145 created "2018-09-27" @default.
- W2890140145 creator A5007282525 @default.
- W2890140145 creator A5036119391 @default.
- W2890140145 creator A5045081171 @default.
- W2890140145 date "2018-01-01" @default.
- W2890140145 modified "2023-09-23" @default.
- W2890140145 title "Enhancing Feature Correlation for Bi-Modal Group Emotion Recognition" @default.
- W2890140145 cites W1603712378 @default.
- W2890140145 cites W2082627290 @default.
- W2890140145 cites W2104657103 @default.
- W2890140145 cites W2148718796 @default.
- W2890140145 cites W2194775991 @default.
- W2890140145 cites W2246249023 @default.
- W2890140145 cites W2253728219 @default.
- W2890140145 cites W2293617031 @default.
- W2890140145 cites W2527646968 @default.
- W2890140145 cites W2531409750 @default.
- W2890140145 cites W2767348466 @default.
- W2890140145 cites W2963091558 @default.
- W2890140145 cites W2963826257 @default.
- W2890140145 cites W3101314801 @default.
- W2890140145 doi "https://doi.org/10.1007/978-3-030-00767-6_3" @default.
- W2890140145 hasPublicationYear "2018" @default.
- W2890140145 type Work @default.
- W2890140145 sameAs 2890140145 @default.
- W2890140145 citedByCount "3" @default.
- W2890140145 countsByYear W28901401452021 @default.
- W2890140145 countsByYear W28901401452022 @default.
- W2890140145 crossrefType "book-chapter" @default.
- W2890140145 hasAuthorship W2890140145A5007282525 @default.
- W2890140145 hasAuthorship W2890140145A5036119391 @default.
- W2890140145 hasAuthorship W2890140145A5045081171 @default.
- W2890140145 hasConcept C117220453 @default.
- W2890140145 hasConcept C138885662 @default.
- W2890140145 hasConcept C153180895 @default.
- W2890140145 hasConcept C154945302 @default.
- W2890140145 hasConcept C184898388 @default.
- W2890140145 hasConcept C195704467 @default.
- W2890140145 hasConcept C2524010 @default.
- W2890140145 hasConcept C2776401178 @default.
- W2890140145 hasConcept C31972630 @default.
- W2890140145 hasConcept C33923547 @default.
- W2890140145 hasConcept C41008148 @default.
- W2890140145 hasConcept C41895202 @default.
- W2890140145 hasConcept C52622490 @default.
- W2890140145 hasConcept C81363708 @default.
- W2890140145 hasConceptScore W2890140145C117220453 @default.
- W2890140145 hasConceptScore W2890140145C138885662 @default.
- W2890140145 hasConceptScore W2890140145C153180895 @default.
- W2890140145 hasConceptScore W2890140145C154945302 @default.
- W2890140145 hasConceptScore W2890140145C184898388 @default.
- W2890140145 hasConceptScore W2890140145C195704467 @default.
- W2890140145 hasConceptScore W2890140145C2524010 @default.
- W2890140145 hasConceptScore W2890140145C2776401178 @default.
- W2890140145 hasConceptScore W2890140145C31972630 @default.
- W2890140145 hasConceptScore W2890140145C33923547 @default.
- W2890140145 hasConceptScore W2890140145C41008148 @default.
- W2890140145 hasConceptScore W2890140145C41895202 @default.
- W2890140145 hasConceptScore W2890140145C52622490 @default.
- W2890140145 hasConceptScore W2890140145C81363708 @default.
- W2890140145 hasLocation W28901401451 @default.
- W2890140145 hasOpenAccess W2890140145 @default.
- W2890140145 hasPrimaryLocation W28901401451 @default.
- W2890140145 hasRelatedWork W1523070616 @default.
- W2890140145 hasRelatedWork W2293804193 @default.
- W2890140145 hasRelatedWork W2537247313 @default.
- W2890140145 hasRelatedWork W2548264631 @default.
- W2890140145 hasRelatedWork W2786177995 @default.
- W2890140145 hasRelatedWork W2800840848 @default.
- W2890140145 hasRelatedWork W2891182955 @default.
- W2890140145 hasRelatedWork W2893554742 @default.
- W2890140145 hasRelatedWork W2900164843 @default.
- W2890140145 hasRelatedWork W2907656006 @default.
- W2890140145 hasRelatedWork W2947975382 @default.
- W2890140145 hasRelatedWork W2979659646 @default.
- W2890140145 hasRelatedWork W2980175391 @default.
- W2890140145 hasRelatedWork W2980393359 @default.
- W2890140145 hasRelatedWork W3000704572 @default.
- W2890140145 hasRelatedWork W3017147892 @default.
- W2890140145 hasRelatedWork W3085545042 @default.
- W2890140145 hasRelatedWork W3158294847 @default.
- W2890140145 hasRelatedWork W3161599401 @default.
- W2890140145 hasRelatedWork W3209569059 @default.
- W2890140145 isParatext "false" @default.
- W2890140145 isRetracted "false" @default.
- W2890140145 magId "2890140145" @default.
- W2890140145 workType "book-chapter" @default.