Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285407946> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W4285407946 abstract "We explore the effect of auxiliary labels in improving the classification accuracy of wearable sensor-based human activity recognition (HAR) systems, which are primarily trained with the supervision of the activity labels (e.g. running, walking, jumping). Supplemental meta-data are often available during the data collection process such as body positions of the wearable sensors, subjects' demographic information (e.g. gender, age), and the type of wearable used (e.g. smartphone, smart-watch). This information, while not directly related to the activity classification task, can nonetheless provide auxiliary supervision and has the potential to significantly improve the HAR accuracy by providing extra guidance on how to handle the introduced sample heterogeneity from the change in domains (i.e positions, persons, or sensors), especially in the presence of limited activity labels. However, integrating such meta-data information in the classification pipeline is non-trivial - (i) the complex interaction between the activity and domain label space is hard to capture with a simple multi-task and/or adversarial learning setup, (ii) meta-data and activity labels might not be simultaneously available for all collected samples. To address these issues, we propose a novel framework Conditional Domain Embeddings (CoDEm). From the available unlabeled raw samples and their domain meta-data, we first learn a set of domain embeddings using a contrastive learning methodology to handle inter-domain variability and inter-domain similarity. To classify the activities, CoDEm then learns the label embeddings in a contrastive fashion, conditioned on domain embeddings with a novel attention mechanism, enforcing the model to learn the complex domain-activity relationships. We extensively evaluate CoDEm in three benchmark datasets against a number of multi-task and adversarial learning baselines and achieve state-of-the-art nerformance in each avenue." @default.
- W4285407946 created "2022-07-14" @default.
- W4285407946 creator A5004571893 @default.
- W4285407946 creator A5011127345 @default.
- W4285407946 creator A5054849647 @default.
- W4285407946 creator A5068320631 @default.
- W4285407946 creator A5073506699 @default.
- W4285407946 date "2022-06-01" @default.
- W4285407946 modified "2023-09-27" @default.
- W4285407946 title "CoDEm: Conditional Domain Embeddings for Scalable Human Activity Recognition" @default.
- W4285407946 cites W1902237438 @default.
- W4285407946 cites W1987971958 @default.
- W4285407946 cites W2026297770 @default.
- W4285407946 cites W2126511896 @default.
- W4285407946 cites W2138621090 @default.
- W4285407946 cites W2145421913 @default.
- W4285407946 cites W2555209581 @default.
- W4285407946 cites W2831903526 @default.
- W4285407946 cites W2909500108 @default.
- W4285407946 cites W2949843150 @default.
- W4285407946 cites W2963430102 @default.
- W4285407946 cites W2965024236 @default.
- W4285407946 cites W2984702021 @default.
- W4285407946 cites W3005684631 @default.
- W4285407946 cites W3011236446 @default.
- W4285407946 cites W3012250720 @default.
- W4285407946 cites W3128981305 @default.
- W4285407946 cites W3144294392 @default.
- W4285407946 cites W3216277515 @default.
- W4285407946 doi "https://doi.org/10.1109/smartcomp55677.2022.00017" @default.
- W4285407946 hasPublicationYear "2022" @default.
- W4285407946 type Work @default.
- W4285407946 citedByCount "0" @default.
- W4285407946 crossrefType "proceedings-article" @default.
- W4285407946 hasAuthorship W4285407946A5004571893 @default.
- W4285407946 hasAuthorship W4285407946A5011127345 @default.
- W4285407946 hasAuthorship W4285407946A5054849647 @default.
- W4285407946 hasAuthorship W4285407946A5068320631 @default.
- W4285407946 hasAuthorship W4285407946A5073506699 @default.
- W4285407946 hasConcept C103278499 @default.
- W4285407946 hasConcept C115961682 @default.
- W4285407946 hasConcept C119857082 @default.
- W4285407946 hasConcept C121687571 @default.
- W4285407946 hasConcept C124101348 @default.
- W4285407946 hasConcept C134306372 @default.
- W4285407946 hasConcept C149635348 @default.
- W4285407946 hasConcept C150594956 @default.
- W4285407946 hasConcept C153180895 @default.
- W4285407946 hasConcept C154945302 @default.
- W4285407946 hasConcept C162324750 @default.
- W4285407946 hasConcept C177264268 @default.
- W4285407946 hasConcept C187736073 @default.
- W4285407946 hasConcept C199360897 @default.
- W4285407946 hasConcept C2780451532 @default.
- W4285407946 hasConcept C33923547 @default.
- W4285407946 hasConcept C36503486 @default.
- W4285407946 hasConcept C41008148 @default.
- W4285407946 hasConcept C43521106 @default.
- W4285407946 hasConcept C48044578 @default.
- W4285407946 hasConcept C77088390 @default.
- W4285407946 hasConceptScore W4285407946C103278499 @default.
- W4285407946 hasConceptScore W4285407946C115961682 @default.
- W4285407946 hasConceptScore W4285407946C119857082 @default.
- W4285407946 hasConceptScore W4285407946C121687571 @default.
- W4285407946 hasConceptScore W4285407946C124101348 @default.
- W4285407946 hasConceptScore W4285407946C134306372 @default.
- W4285407946 hasConceptScore W4285407946C149635348 @default.
- W4285407946 hasConceptScore W4285407946C150594956 @default.
- W4285407946 hasConceptScore W4285407946C153180895 @default.
- W4285407946 hasConceptScore W4285407946C154945302 @default.
- W4285407946 hasConceptScore W4285407946C162324750 @default.
- W4285407946 hasConceptScore W4285407946C177264268 @default.
- W4285407946 hasConceptScore W4285407946C187736073 @default.
- W4285407946 hasConceptScore W4285407946C199360897 @default.
- W4285407946 hasConceptScore W4285407946C2780451532 @default.
- W4285407946 hasConceptScore W4285407946C33923547 @default.
- W4285407946 hasConceptScore W4285407946C36503486 @default.
- W4285407946 hasConceptScore W4285407946C41008148 @default.
- W4285407946 hasConceptScore W4285407946C43521106 @default.
- W4285407946 hasConceptScore W4285407946C48044578 @default.
- W4285407946 hasConceptScore W4285407946C77088390 @default.
- W4285407946 hasFunder F4320320709 @default.
- W4285407946 hasFunder F4320332447 @default.
- W4285407946 hasLocation W42854079461 @default.
- W4285407946 hasOpenAccess W4285407946 @default.
- W4285407946 hasPrimaryLocation W42854079461 @default.
- W4285407946 hasRelatedWork W2593269787 @default.
- W4285407946 hasRelatedWork W2621310892 @default.
- W4285407946 hasRelatedWork W2900794075 @default.
- W4285407946 hasRelatedWork W2999645641 @default.
- W4285407946 hasRelatedWork W3011192796 @default.
- W4285407946 hasRelatedWork W3048726935 @default.
- W4285407946 hasRelatedWork W3183633970 @default.
- W4285407946 hasRelatedWork W3208309985 @default.
- W4285407946 hasRelatedWork W4210679107 @default.
- W4285407946 hasRelatedWork W4281386417 @default.
- W4285407946 isParatext "false" @default.
- W4285407946 isRetracted "false" @default.
- W4285407946 workType "article" @default.