Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208509992> ?p ?o ?g. }
- W3208509992 abstract "Automatic action identification from video and kinematic data is an important machine learning problem with applications ranging from robotics to smart health. Most existing works focus on identifying coarse actions such as running, climbing, or cutting a vegetable, which have relatively long durations. This is an important limitation for applications that require the identification of subtle motions at high temporal resolution. For example, in stroke recovery, quantifying rehabilitation dose requires differentiating motions with sub-second durations. Our goal is to bridge this gap. To this end, we introduce a large-scale, multimodal dataset, StrokeRehab, as a new action-recognition benchmark that includes subtle short-duration actions labeled at a high temporal resolution. These short-duration actions are called functional primitives, and consist of reaches, transports, repositions, stabilizations, and idles. The dataset consists of high-quality Inertial Measurement Unit sensors and video data of 41 stroke-impaired patients performing activities of daily living like feeding, brushing teeth, etc. We show that current state-of-the-art models based on segmentation produce noisy predictions when applied to these data, which often leads to overcounting of actions. To address this, we propose a novel approach for high-resolution action identification, inspired by speech-recognition techniques, which is based on a sequence-to-sequence model that directly predicts the sequence of actions. This approach outperforms current state-of-the-art methods on the StrokeRehab dataset, as well as on the standard benchmark datasets 50Salads, Breakfast, and Jigsaws." @default.
- W3208509992 created "2021-11-08" @default.
- W3208509992 creator A5023326521 @default.
- W3208509992 creator A5034482431 @default.
- W3208509992 creator A5034743298 @default.
- W3208509992 creator A5040903251 @default.
- W3208509992 creator A5044336556 @default.
- W3208509992 creator A5049535028 @default.
- W3208509992 creator A5067129067 @default.
- W3208509992 creator A5079568025 @default.
- W3208509992 creator A5082609747 @default.
- W3208509992 creator A5000301950 @default.
- W3208509992 date "2021-11-03" @default.
- W3208509992 modified "2023-10-01" @default.
- W3208509992 title "Sequence-to-Sequence Modeling for Action Identification at High Temporal Resolution" @default.
- W3208509992 cites W1497431575 @default.
- W3208509992 cites W1522734439 @default.
- W3208509992 cites W1828163288 @default.
- W3208509992 cites W1855892484 @default.
- W3208509992 cites W1895577753 @default.
- W3208509992 cites W1982491333 @default.
- W3208509992 cites W1993533771 @default.
- W3208509992 cites W2041311794 @default.
- W3208509992 cites W2045098731 @default.
- W3208509992 cites W2053041901 @default.
- W3208509992 cites W2075739165 @default.
- W3208509992 cites W2078991143 @default.
- W3208509992 cites W2099614498 @default.
- W3208509992 cites W2109698606 @default.
- W3208509992 cites W2118893727 @default.
- W3208509992 cites W2127141656 @default.
- W3208509992 cites W2131467344 @default.
- W3208509992 cites W2144633987 @default.
- W3208509992 cites W2195342085 @default.
- W3208509992 cites W2314362175 @default.
- W3208509992 cites W2550143307 @default.
- W3208509992 cites W2619947201 @default.
- W3208509992 cites W2742577082 @default.
- W3208509992 cites W2750499125 @default.
- W3208509992 cites W2770168316 @default.
- W3208509992 cites W2770804203 @default.
- W3208509992 cites W2784015950 @default.
- W3208509992 cites W2917462181 @default.
- W3208509992 cites W2940096514 @default.
- W3208509992 cites W2947464817 @default.
- W3208509992 cites W2950304420 @default.
- W3208509992 cites W2950580142 @default.
- W3208509992 cites W2953022181 @default.
- W3208509992 cites W2962746000 @default.
- W3208509992 cites W2962824709 @default.
- W3208509992 cites W2963315828 @default.
- W3208509992 cites W2963524571 @default.
- W3208509992 cites W2963853051 @default.
- W3208509992 cites W2964308564 @default.
- W3208509992 cites W2990152177 @default.
- W3208509992 cites W2990503944 @default.
- W3208509992 cites W3034572008 @default.
- W3208509992 cites W3035180180 @default.
- W3208509992 cites W3083550439 @default.
- W3208509992 cites W3107066728 @default.
- W3208509992 cites W3108772932 @default.
- W3208509992 doi "https://doi.org/10.48550/arxiv.2111.02521" @default.
- W3208509992 hasPublicationYear "2021" @default.
- W3208509992 type Work @default.
- W3208509992 sameAs 3208509992 @default.
- W3208509992 citedByCount "0" @default.
- W3208509992 crossrefType "posted-content" @default.
- W3208509992 hasAuthorship W3208509992A5000301950 @default.
- W3208509992 hasAuthorship W3208509992A5023326521 @default.
- W3208509992 hasAuthorship W3208509992A5034482431 @default.
- W3208509992 hasAuthorship W3208509992A5034743298 @default.
- W3208509992 hasAuthorship W3208509992A5040903251 @default.
- W3208509992 hasAuthorship W3208509992A5044336556 @default.
- W3208509992 hasAuthorship W3208509992A5049535028 @default.
- W3208509992 hasAuthorship W3208509992A5067129067 @default.
- W3208509992 hasAuthorship W3208509992A5079568025 @default.
- W3208509992 hasAuthorship W3208509992A5082609747 @default.
- W3208509992 hasBestOaLocation W32085099921 @default.
- W3208509992 hasConcept C116834253 @default.
- W3208509992 hasConcept C119857082 @default.
- W3208509992 hasConcept C121332964 @default.
- W3208509992 hasConcept C13280743 @default.
- W3208509992 hasConcept C153180895 @default.
- W3208509992 hasConcept C154945302 @default.
- W3208509992 hasConcept C185798385 @default.
- W3208509992 hasConcept C205649164 @default.
- W3208509992 hasConcept C2778112365 @default.
- W3208509992 hasConcept C2780791683 @default.
- W3208509992 hasConcept C41008148 @default.
- W3208509992 hasConcept C54355233 @default.
- W3208509992 hasConcept C59822182 @default.
- W3208509992 hasConcept C62520636 @default.
- W3208509992 hasConcept C86803240 @default.
- W3208509992 hasConcept C89600930 @default.
- W3208509992 hasConceptScore W3208509992C116834253 @default.
- W3208509992 hasConceptScore W3208509992C119857082 @default.
- W3208509992 hasConceptScore W3208509992C121332964 @default.
- W3208509992 hasConceptScore W3208509992C13280743 @default.
- W3208509992 hasConceptScore W3208509992C153180895 @default.
- W3208509992 hasConceptScore W3208509992C154945302 @default.