Matches in SemOpenAlex for { <https://semopenalex.org/work/W2902912462> ?p ?o ?g. }
- W2902912462 abstract "Most of the existing work on automatic facial expression analysis focuses on discrete emotion recognition, or facial action unit detection. However, facial expressions do not always fall neatly into pre-defined semantic categories. Also, the similarity between expressions measured in the action unit space need not correspond to how humans perceive expression similarity. Different from previous work, our goal is to describe facial expressions in a continuous fashion using a compact embedding space that mimics human visual preferences. To achieve this goal, we collect a large-scale faces-in-the-wild dataset with human annotations in the form: Expressions A and B are visually more similar when compared to expression C, and use this dataset to train a neural network that produces a compact (16-dimensional) expression embedding. We experimentally demonstrate that the learned embedding can be successfully used for various applications such as expression retrieval, photo album summarization, and emotion recognition. We also show that the embedding learned using the proposed dataset performs better than several other embeddings learned using existing emotion or action unit datasets." @default.
- W2902912462 created "2018-12-11" @default.
- W2902912462 creator A5027379477 @default.
- W2902912462 creator A5071825172 @default.
- W2902912462 date "2018-11-27" @default.
- W2902912462 modified "2023-09-27" @default.
- W2902912462 title "A Compact Embedding for Facial Expression Similarity" @default.
- W2902912462 cites W1532499126 @default.
- W2902912462 cites W1533861849 @default.
- W2902912462 cites W1834627138 @default.
- W2902912462 cites W1836465849 @default.
- W2902912462 cites W1975517671 @default.
- W2902912462 cites W2002055708 @default.
- W2902912462 cites W2008933718 @default.
- W2902912462 cites W2035372623 @default.
- W2902912462 cites W2040431151 @default.
- W2902912462 cites W2041616772 @default.
- W2902912462 cites W2045528981 @default.
- W2902912462 cites W2103943262 @default.
- W2902912462 cites W2106053110 @default.
- W2902912462 cites W2145287260 @default.
- W2902912462 cites W2149628368 @default.
- W2902912462 cites W2161634108 @default.
- W2902912462 cites W2243226955 @default.
- W2902912462 cites W2391561377 @default.
- W2902912462 cites W2436394355 @default.
- W2902912462 cites W2470322391 @default.
- W2902912462 cites W2515770085 @default.
- W2902912462 cites W2598634450 @default.
- W2902912462 cites W2737559518 @default.
- W2902912462 cites W2752234108 @default.
- W2902912462 cites W2767348466 @default.
- W2902912462 cites W2889978276 @default.
- W2902912462 cites W2895347732 @default.
- W2902912462 cites W2962950337 @default.
- W2902912462 cites W2963026686 @default.
- W2902912462 cites W2963446712 @default.
- W2902912462 cites W2963671154 @default.
- W2902912462 cites W2963744743 @default.
- W2902912462 cites W2963988212 @default.
- W2902912462 cites W2964007075 @default.
- W2902912462 cites W2964076257 @default.
- W2902912462 cites W2964121744 @default.
- W2902912462 cites W2964135029 @default.
- W2902912462 cites W2964347177 @default.
- W2902912462 cites W3101614002 @default.
- W2902912462 cites W652662681 @default.
- W2902912462 hasPublicationYear "2018" @default.
- W2902912462 type Work @default.
- W2902912462 sameAs 2902912462 @default.
- W2902912462 citedByCount "1" @default.
- W2902912462 countsByYear W29029124622021 @default.
- W2902912462 crossrefType "posted-content" @default.
- W2902912462 hasAuthorship W2902912462A5027379477 @default.
- W2902912462 hasAuthorship W2902912462A5071825172 @default.
- W2902912462 hasConcept C103278499 @default.
- W2902912462 hasConcept C111919701 @default.
- W2902912462 hasConcept C115961682 @default.
- W2902912462 hasConcept C121332964 @default.
- W2902912462 hasConcept C144024400 @default.
- W2902912462 hasConcept C153180895 @default.
- W2902912462 hasConcept C154945302 @default.
- W2902912462 hasConcept C170858558 @default.
- W2902912462 hasConcept C195704467 @default.
- W2902912462 hasConcept C199360897 @default.
- W2902912462 hasConcept C2778572836 @default.
- W2902912462 hasConcept C2779304628 @default.
- W2902912462 hasConcept C2780791683 @default.
- W2902912462 hasConcept C36289849 @default.
- W2902912462 hasConcept C41008148 @default.
- W2902912462 hasConcept C41608201 @default.
- W2902912462 hasConcept C62520636 @default.
- W2902912462 hasConcept C90559484 @default.
- W2902912462 hasConceptScore W2902912462C103278499 @default.
- W2902912462 hasConceptScore W2902912462C111919701 @default.
- W2902912462 hasConceptScore W2902912462C115961682 @default.
- W2902912462 hasConceptScore W2902912462C121332964 @default.
- W2902912462 hasConceptScore W2902912462C144024400 @default.
- W2902912462 hasConceptScore W2902912462C153180895 @default.
- W2902912462 hasConceptScore W2902912462C154945302 @default.
- W2902912462 hasConceptScore W2902912462C170858558 @default.
- W2902912462 hasConceptScore W2902912462C195704467 @default.
- W2902912462 hasConceptScore W2902912462C199360897 @default.
- W2902912462 hasConceptScore W2902912462C2778572836 @default.
- W2902912462 hasConceptScore W2902912462C2779304628 @default.
- W2902912462 hasConceptScore W2902912462C2780791683 @default.
- W2902912462 hasConceptScore W2902912462C36289849 @default.
- W2902912462 hasConceptScore W2902912462C41008148 @default.
- W2902912462 hasConceptScore W2902912462C41608201 @default.
- W2902912462 hasConceptScore W2902912462C62520636 @default.
- W2902912462 hasConceptScore W2902912462C90559484 @default.
- W2902912462 hasLocation W29029124621 @default.
- W2902912462 hasOpenAccess W2902912462 @default.
- W2902912462 hasPrimaryLocation W29029124621 @default.
- W2902912462 hasRelatedWork W1621414035 @default.
- W2902912462 hasRelatedWork W2155568050 @default.
- W2902912462 hasRelatedWork W2293804193 @default.
- W2902912462 hasRelatedWork W2749105138 @default.
- W2902912462 hasRelatedWork W2750901647 @default.
- W2902912462 hasRelatedWork W2798351401 @default.