FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3211934549> ?p ?o ?g. }

• W3211934549 abstract "Automatically understanding and recognising human affective states using images and computer vision can improve human-computer and human-robot interaction. However, privacy has become an issue of great concern, as the identities of people used to train affective models can be exposed in the process. For instance, malicious individuals could exploit images from users and assume their identities. In addition, affect recognition using images can lead to discriminatory and algorithmic bias, as certain information such as race, gender, and age could be assumed based on facial features. Possible solutions to protect the privacy of users and avoid misuse of their identities are to: (1) extract anonymised facial features, namely action units (AU) from a database of images, discard the images and use AUs for processing and training, and (2) federated learning (FL) i.e. process raw images in users' local machines (local processing) and send the locally trained models to the main processing machine for aggregation (central processing). In this paper, we propose a two-level deep learning architecture for affect recognition that uses AUs in level 1 and FL in level 2 to protect users' identities. The architecture consists of recurrent neural networks to capture the temporal relationships amongst the features and predict valence and arousal affective states. In our experiments, we evaluate the performance of our privacy-preserving architecture using different variations of recurrent neural networks on RECOLA, a comprehensive multimodal affective database. Our results show state-of-the-art performance of $0.426$ for valence and $0.401$ for arousal using the Concordance Correlation Coefficient evaluation metric, demonstrating the feasibility of developing models for affect recognition that are both accurate and ensure privacy." @default.
• W3211934549 created "2021-11-22" @default.
• W3211934549 creator A5024981509 @default.
• W3211934549 creator A5051446557 @default.
• W3211934549 creator A5052071646 @default.
• W3211934549 creator A5069160503 @default.
• W3211934549 creator A5075663444 @default.
• W3211934549 date "2021-11-14" @default.
• W3211934549 modified "2023-09-27" @default.
• W3211934549 title "Towards Privacy-Preserving Affect Recognition: A Two-Level Deep Learning Architecture." @default.
• W3211934549 cites W1847088711 @default.
• W3211934549 cites W1964757081 @default.
• W3211934549 cites W1998808035 @default.
• W3211934549 cites W2041861657 @default.
• W3211934549 cites W2045528981 @default.
• W3211934549 cites W2065168079 @default.
• W3211934549 cites W2107878631 @default.
• W3211934549 cites W2117539524 @default.
• W3211934549 cites W2165794993 @default.
• W3211934549 cites W2281407413 @default.
• W3211934549 cites W2346454595 @default.
• W3211934549 cites W2554978171 @default.
• W3211934549 cites W2560025328 @default.
• W3211934549 cites W2584561145 @default.
• W3211934549 cites W2606933083 @default.
• W3211934549 cites W2610961739 @default.
• W3211934549 cites W2611154248 @default.
• W3211934549 cites W2740046088 @default.
• W3211934549 cites W2796830519 @default.
• W3211934549 cites W2807126412 @default.
• W3211934549 cites W2887068828 @default.
• W3211934549 cites W2954869531 @default.
• W3211934549 cites W2963789946 @default.
• W3211934549 cites W3003850414 @default.
• W3211934549 cites W3013109186 @default.
• W3211934549 cites W3085279808 @default.
• W3211934549 cites W3094524767 @default.
• W3211934549 cites W3100506742 @default.
• W3211934549 cites W3101275766 @default.
• W3211934549 cites W3118626025 @default.
• W3211934549 cites W3133785125 @default.
• W3211934549 cites W3135801263 @default.
• W3211934549 cites W3202873716 @default.
• W3211934549 hasPublicationYear "2021" @default.
• W3211934549 type Work @default.
• W3211934549 sameAs 3211934549 @default.
• W3211934549 citedByCount "0" @default.
• W3211934549 crossrefType "posted-content" @default.
• W3211934549 hasAuthorship W3211934549A5024981509 @default.
• W3211934549 hasAuthorship W3211934549A5051446557 @default.
• W3211934549 hasAuthorship W3211934549A5052071646 @default.
• W3211934549 hasAuthorship W3211934549A5069160503 @default.
• W3211934549 hasAuthorship W3211934549A5075663444 @default.
• W3211934549 hasConcept C107457646 @default.
• W3211934549 hasConcept C119857082 @default.
• W3211934549 hasConcept C121332964 @default.
• W3211934549 hasConcept C123657996 @default.
• W3211934549 hasConcept C142362112 @default.
• W3211934549 hasConcept C153349607 @default.
• W3211934549 hasConcept C154945302 @default.
• W3211934549 hasConcept C15744967 @default.
• W3211934549 hasConcept C165696696 @default.
• W3211934549 hasConcept C168900304 @default.
• W3211934549 hasConcept C169760540 @default.
• W3211934549 hasConcept C195704467 @default.
• W3211934549 hasConcept C2776035688 @default.
• W3211934549 hasConcept C36951298 @default.
• W3211934549 hasConcept C38652104 @default.
• W3211934549 hasConcept C41008148 @default.
• W3211934549 hasConcept C46312422 @default.
• W3211934549 hasConcept C50644808 @default.
• W3211934549 hasConcept C62520636 @default.
• W3211934549 hasConceptScore W3211934549C107457646 @default.
• W3211934549 hasConceptScore W3211934549C119857082 @default.
• W3211934549 hasConceptScore W3211934549C121332964 @default.
• W3211934549 hasConceptScore W3211934549C123657996 @default.
• W3211934549 hasConceptScore W3211934549C142362112 @default.
• W3211934549 hasConceptScore W3211934549C153349607 @default.
• W3211934549 hasConceptScore W3211934549C154945302 @default.
• W3211934549 hasConceptScore W3211934549C15744967 @default.
• W3211934549 hasConceptScore W3211934549C165696696 @default.
• W3211934549 hasConceptScore W3211934549C168900304 @default.
• W3211934549 hasConceptScore W3211934549C169760540 @default.
• W3211934549 hasConceptScore W3211934549C195704467 @default.
• W3211934549 hasConceptScore W3211934549C2776035688 @default.
• W3211934549 hasConceptScore W3211934549C36951298 @default.
• W3211934549 hasConceptScore W3211934549C38652104 @default.
• W3211934549 hasConceptScore W3211934549C41008148 @default.
• W3211934549 hasConceptScore W3211934549C46312422 @default.
• W3211934549 hasConceptScore W3211934549C50644808 @default.
• W3211934549 hasConceptScore W3211934549C62520636 @default.
• W3211934549 hasLocation W32119345491 @default.
• W3211934549 hasOpenAccess W3211934549 @default.
• W3211934549 hasPrimaryLocation W32119345491 @default.
• W3211934549 hasRelatedWork W2080183512 @default.
• W3211934549 hasRelatedWork W2258555827 @default.
• W3211934549 hasRelatedWork W2604613829 @default.
• W3211934549 hasRelatedWork W2750317709 @default.
• W3211934549 hasRelatedWork W2767364446 @default.
• W3211934549 hasRelatedWork W2783038397 @default.

• next