FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3109709077> ?p ?o ?g. }

• W3109709077 endingPage "163" @default.
• W3109709077 startingPage "145" @default.
• W3109709077 abstract "We present an autoencoder-based semi-supervised approach to classify perceived human emotions from walking styles obtained from videos or motion-captured data and represented as sequences of 3D poses. Given the motion on each joint in the pose at each time step extracted from 3D pose sequences, we hierarchically pool these joint motions in a bottom-up manner in the encoder, following the kinematic chains in the human body. We also constrain the latent embeddings of the encoder to contain the space of psychologically-motivated affective features underlying the gaits. We train the decoder to reconstruct the motions per joint per time step in a top-down manner from the latent embeddings. For the annotated data, we also train a classifier to map the latent embeddings to emotion labels. Our semi-supervised approach achieves a mean average precision of 0.84 on the Emotion-Gait benchmark dataset, which contains both labeled and unlabeled gaits collected from multiple sources. We outperform current state-of-art algorithms for both emotion recognition and action recognition from 3D gaits by 7%--23% on the absolute. More importantly, we improve the average precision by 10%--50% on the absolute on classes that each makes up less than 25% of the labeled part of the Emotion-Gait benchmark dataset." @default.
• W3109709077 created "2020-12-07" @default.
• W3109709077 creator A5003468447 @default.
• W3109709077 creator A5016704715 @default.
• W3109709077 creator A5022353920 @default.
• W3109709077 creator A5042584669 @default.
• W3109709077 creator A5042883150 @default.
• W3109709077 creator A5058453308 @default.
• W3109709077 creator A5062298460 @default.
• W3109709077 creator A5086565759 @default.
• W3109709077 date "2020-01-01" @default.
• W3109709077 modified "2023-10-17" @default.
• W3109709077 title "Take an Emotion Walk: Perceiving Emotions from Gaits Using Hierarchical Attention Pooling and Affective Mapping" @default.
• W3109709077 cites W1536003180 @default.
• W3109709077 cites W1963552095 @default.
• W3109709077 cites W1965306520 @default.
• W3109709077 cites W1965868009 @default.
• W3109709077 cites W1977259876 @default.
• W3109709077 cites W1977841100 @default.
• W3109709077 cites W1984867139 @default.
• W3109709077 cites W1990120076 @default.
• W3109709077 cites W2024221294 @default.
• W3109709077 cites W2030292036 @default.
• W3109709077 cites W2069002413 @default.
• W3109709077 cites W2079521622 @default.
• W3109709077 cites W2082981966 @default.
• W3109709077 cites W2101032778 @default.
• W3109709077 cites W2105119762 @default.
• W3109709077 cites W2137409775 @default.
• W3109709077 cites W2142597810 @default.
• W3109709077 cites W2147449317 @default.
• W3109709077 cites W2164558494 @default.
• W3109709077 cites W2274886583 @default.
• W3109709077 cites W2436394355 @default.
• W3109709077 cites W2469134594 @default.
• W3109709077 cites W2473032611 @default.
• W3109709077 cites W2535925890 @default.
• W3109709077 cites W2573985267 @default.
• W3109709077 cites W2619612160 @default.
• W3109709077 cites W2739353222 @default.
• W3109709077 cites W2792345332 @default.
• W3109709077 cites W2796633859 @default.
• W3109709077 cites W2802441648 @default.
• W3109709077 cites W2883938080 @default.
• W3109709077 cites W2890114324 @default.
• W3109709077 cites W2899930323 @default.
• W3109709077 cites W2948058585 @default.
• W3109709077 cites W2948246283 @default.
• W3109709077 cites W2962896489 @default.
• W3109709077 cites W2963076818 @default.
• W3109709077 cites W2963180222 @default.
• W3109709077 cites W2963465695 @default.
• W3109709077 cites W2963524571 @default.
• W3109709077 cites W2964134613 @default.
• W3109709077 cites W2964298190 @default.
• W3109709077 cites W2971866817 @default.
• W3109709077 cites W2974177253 @default.
• W3109709077 cites W2975420824 @default.
• W3109709077 cites W2983796203 @default.
• W3109709077 cites W2986708244 @default.
• W3109709077 cites W2991332406 @default.
• W3109709077 cites W3001529617 @default.
• W3109709077 cites W3034520808 @default.
• W3109709077 cites W3035225512 @default.
• W3109709077 cites W3098699623 @default.
• W3109709077 cites W3098745339 @default.
• W3109709077 cites W3102937540 @default.
• W3109709077 cites W3131085900 @default.
• W3109709077 cites W322218806 @default.
• W3109709077 cites W4233419748 @default.
• W3109709077 doi "https://doi.org/10.1007/978-3-030-58607-2_9" @default.
• W3109709077 hasPublicationYear "2020" @default.
• W3109709077 type Work @default.
• W3109709077 sameAs 3109709077 @default.
• W3109709077 citedByCount "15" @default.
• W3109709077 countsByYear W31097090772020 @default.
• W3109709077 countsByYear W31097090772021 @default.
• W3109709077 countsByYear W31097090772022 @default.
• W3109709077 countsByYear W31097090772023 @default.
• W3109709077 crossrefType "book-chapter" @default.
• W3109709077 hasAuthorship W3109709077A5003468447 @default.
• W3109709077 hasAuthorship W3109709077A5016704715 @default.
• W3109709077 hasAuthorship W3109709077A5022353920 @default.
• W3109709077 hasAuthorship W3109709077A5042584669 @default.
• W3109709077 hasAuthorship W3109709077A5042883150 @default.
• W3109709077 hasAuthorship W3109709077A5058453308 @default.
• W3109709077 hasAuthorship W3109709077A5062298460 @default.
• W3109709077 hasAuthorship W3109709077A5086565759 @default.
• W3109709077 hasBestOaLocation W31097090772 @default.
• W3109709077 hasConcept C101738243 @default.
• W3109709077 hasConcept C104114177 @default.
• W3109709077 hasConcept C121332964 @default.
• W3109709077 hasConcept C13280743 @default.
• W3109709077 hasConcept C151800584 @default.
• W3109709077 hasConcept C153180895 @default.
• W3109709077 hasConcept C154945302 @default.
• W3109709077 hasConcept C185798385 @default.
• W3109709077 hasConcept C205649164 @default.

• next