Matches in SemOpenAlex for { <https://semopenalex.org/work/W2803017656> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2803017656 abstract "Depression is a serious mental disorder that affects millions of people all over the world. Traditional clinical diagnosis methods are subjective, complicated and need extensive participation of experts. Audio-visual automatic depression analysis systems predominantly base their predictions on very brief sequential segments, sometimes as little as one frame. Such data contains much redundant information, causes a high computational load, and negatively affects the detection accuracy. Final decision making at the sequence level is then based on the fusion of frame or segment level predictions. However, this approach loses longer term behavioural correlations, as the behaviours themselves are abstracted away by the frame-level predictions. We propose to on the one hand use automatically detected human behaviour primitives such as Gaze directions, Facial action units (AU), etc. as low-dimensional multi-channel time series data, which can then be used to create two sequence descriptors. The first calculates the sequence-level statistics of the behaviour primitives and the second casts the problem as a Convolutional Neural Network problem operating on a spectral representation of the multichannel behaviour signals. The results of depression detection (binary classification) and severity estimation (regression) experiments conducted on the AVEC 2016 DAIC-WOZ database show that both methods achieved significant improvement compared to the previous state of the art in terms of the depression severity estimation." @default.
- W2803017656 created "2018-05-17" @default.
- W2803017656 creator A5019313200 @default.
- W2803017656 creator A5053061988 @default.
- W2803017656 creator A5089151131 @default.
- W2803017656 date "2018-05-01" @default.
- W2803017656 modified "2023-10-17" @default.
- W2803017656 title "Human Behaviour-Based Automatic Depression Analysis Using Hand-Crafted Statistics and Deep Learned Spectral Features" @default.
- W2803017656 cites W1488266690 @default.
- W2803017656 cites W1606858007 @default.
- W2803017656 cites W1976066595 @default.
- W2803017656 cites W1991060033 @default.
- W2803017656 cites W1995562189 @default.
- W2803017656 cites W2000149402 @default.
- W2803017656 cites W2043080619 @default.
- W2803017656 cites W2056403322 @default.
- W2803017656 cites W2077684629 @default.
- W2803017656 cites W2084242110 @default.
- W2803017656 cites W2096976598 @default.
- W2803017656 cites W2097792098 @default.
- W2803017656 cites W2136409902 @default.
- W2803017656 cites W2157735101 @default.
- W2803017656 cites W2163928333 @default.
- W2803017656 cites W2280620570 @default.
- W2803017656 cites W2291466689 @default.
- W2803017656 cites W2346454595 @default.
- W2803017656 cites W2530305026 @default.
- W2803017656 cites W2530421149 @default.
- W2803017656 cites W2530431529 @default.
- W2803017656 cites W2531271152 @default.
- W2803017656 cites W2551393996 @default.
- W2803017656 cites W3148981562 @default.
- W2803017656 doi "https://doi.org/10.1109/fg.2018.00032" @default.
- W2803017656 hasPublicationYear "2018" @default.
- W2803017656 type Work @default.
- W2803017656 sameAs 2803017656 @default.
- W2803017656 citedByCount "60" @default.
- W2803017656 countsByYear W28030176562018 @default.
- W2803017656 countsByYear W28030176562019 @default.
- W2803017656 countsByYear W28030176562020 @default.
- W2803017656 countsByYear W28030176562021 @default.
- W2803017656 countsByYear W28030176562022 @default.
- W2803017656 countsByYear W28030176562023 @default.
- W2803017656 crossrefType "proceedings-article" @default.
- W2803017656 hasAuthorship W2803017656A5019313200 @default.
- W2803017656 hasAuthorship W2803017656A5053061988 @default.
- W2803017656 hasAuthorship W2803017656A5089151131 @default.
- W2803017656 hasBestOaLocation W28030176562 @default.
- W2803017656 hasConcept C126042441 @default.
- W2803017656 hasConcept C153180895 @default.
- W2803017656 hasConcept C154945302 @default.
- W2803017656 hasConcept C17744445 @default.
- W2803017656 hasConcept C199539241 @default.
- W2803017656 hasConcept C2776359362 @default.
- W2803017656 hasConcept C2778112365 @default.
- W2803017656 hasConcept C41008148 @default.
- W2803017656 hasConcept C54355233 @default.
- W2803017656 hasConcept C76155785 @default.
- W2803017656 hasConcept C81363708 @default.
- W2803017656 hasConcept C86803240 @default.
- W2803017656 hasConcept C94625758 @default.
- W2803017656 hasConceptScore W2803017656C126042441 @default.
- W2803017656 hasConceptScore W2803017656C153180895 @default.
- W2803017656 hasConceptScore W2803017656C154945302 @default.
- W2803017656 hasConceptScore W2803017656C17744445 @default.
- W2803017656 hasConceptScore W2803017656C199539241 @default.
- W2803017656 hasConceptScore W2803017656C2776359362 @default.
- W2803017656 hasConceptScore W2803017656C2778112365 @default.
- W2803017656 hasConceptScore W2803017656C41008148 @default.
- W2803017656 hasConceptScore W2803017656C54355233 @default.
- W2803017656 hasConceptScore W2803017656C76155785 @default.
- W2803017656 hasConceptScore W2803017656C81363708 @default.
- W2803017656 hasConceptScore W2803017656C86803240 @default.
- W2803017656 hasConceptScore W2803017656C94625758 @default.
- W2803017656 hasLocation W28030176561 @default.
- W2803017656 hasLocation W28030176562 @default.
- W2803017656 hasLocation W28030176563 @default.
- W2803017656 hasOpenAccess W2803017656 @default.
- W2803017656 hasPrimaryLocation W28030176561 @default.
- W2803017656 hasRelatedWork W2735477435 @default.
- W2803017656 hasRelatedWork W2748454020 @default.
- W2803017656 hasRelatedWork W2767651786 @default.
- W2803017656 hasRelatedWork W2912288872 @default.
- W2803017656 hasRelatedWork W3016958897 @default.
- W2803017656 hasRelatedWork W3119610945 @default.
- W2803017656 hasRelatedWork W3181746755 @default.
- W2803017656 hasRelatedWork W4283379348 @default.
- W2803017656 hasRelatedWork W4312417841 @default.
- W2803017656 hasRelatedWork W564581980 @default.
- W2803017656 isParatext "false" @default.
- W2803017656 isRetracted "false" @default.
- W2803017656 magId "2803017656" @default.
- W2803017656 workType "article" @default.