Matches in SemOpenAlex for { <https://semopenalex.org/work/W2969355215> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2969355215 abstract "Recognizing human actions is a vital task for a humanoid robot, especially in domains like programming by demonstration. Previous approaches on action recognition primarily focused on the overall prevalent action being executed, but we argue that bimanual human motion cannot always be described sufficiently with a single action label. We present a system for frame-wise action classification and segmentation in bimanual human demonstrations. The system extracts symbolic spatial object relations from raw RGB-D video data captured from the robot's point of view in order to build graph-based scene representations. To learn object-action relations, a graph network classifier is trained using these representations together with ground truth action labels to predict the action executed by each hand. We evaluated the proposed classifier on a new RGB-D video dataset showing daily action sequences focusing on bimanual manipulation actions. It consists of 6 subjects performing 9 tasks with 10 repetitions each, which leads to 540 video recordings with 2 hours and 18 minutes total playtime and per-hand ground truth action labels for each frame. We show that the classifier is able to reliably identify (action classification macro F1-score of 0.86) the true executed action of each hand within its top 3 predictions on a frame-by-frame basis without prior temporal action segmentation." @default.
- W2969355215 created "2019-08-29" @default.
- W2969355215 creator A5012730104 @default.
- W2969355215 creator A5037778920 @default.
- W2969355215 creator A5082150620 @default.
- W2969355215 date "2019-08-22" @default.
- W2969355215 modified "2023-09-27" @default.
- W2969355215 title "Learning Object-Action Relations from Bimanual Human Demonstration Using Graph Networks" @default.
- W2969355215 cites W1483019628 @default.
- W2969355215 cites W1492952184 @default.
- W2969355215 cites W1684361744 @default.
- W2969355215 cites W1898340191 @default.
- W2969355215 cites W1970065037 @default.
- W2969355215 cites W1975325338 @default.
- W2969355215 cites W1983364832 @default.
- W2969355215 cites W2010399676 @default.
- W2969355215 cites W2045225768 @default.
- W2969355215 cites W2065692216 @default.
- W2969355215 cites W2078046413 @default.
- W2969355215 cites W2098339052 @default.
- W2969355215 cites W2099614498 @default.
- W2969355215 cites W2101194540 @default.
- W2969355215 cites W2106996050 @default.
- W2969355215 cites W2132734311 @default.
- W2969355215 cites W2143267104 @default.
- W2969355215 cites W2145546283 @default.
- W2969355215 cites W2146055337 @default.
- W2969355215 cites W2148939146 @default.
- W2969355215 cites W2149173366 @default.
- W2969355215 cites W2166112783 @default.
- W2969355215 cites W2294438834 @default.
- W2969355215 cites W2784025607 @default.
- W2969355215 cites W2796347433 @default.
- W2969355215 cites W2805516822 @default.
- W2969355215 cites W2896736483 @default.
- W2969355215 cites W2962730651 @default.
- W2969355215 cites W2963218601 @default.
- W2969355215 cites W2964242760 @default.
- W2969355215 hasPublicationYear "2019" @default.
- W2969355215 type Work @default.
- W2969355215 sameAs 2969355215 @default.
- W2969355215 citedByCount "0" @default.
- W2969355215 crossrefType "posted-content" @default.
- W2969355215 hasAuthorship W2969355215A5012730104 @default.
- W2969355215 hasAuthorship W2969355215A5037778920 @default.
- W2969355215 hasAuthorship W2969355215A5082150620 @default.
- W2969355215 hasConcept C146849305 @default.
- W2969355215 hasConcept C153180895 @default.
- W2969355215 hasConcept C154945302 @default.
- W2969355215 hasConcept C31972630 @default.
- W2969355215 hasConcept C41008148 @default.
- W2969355215 hasConcept C82990744 @default.
- W2969355215 hasConcept C89600930 @default.
- W2969355215 hasConcept C95623464 @default.
- W2969355215 hasConceptScore W2969355215C146849305 @default.
- W2969355215 hasConceptScore W2969355215C153180895 @default.
- W2969355215 hasConceptScore W2969355215C154945302 @default.
- W2969355215 hasConceptScore W2969355215C31972630 @default.
- W2969355215 hasConceptScore W2969355215C41008148 @default.
- W2969355215 hasConceptScore W2969355215C82990744 @default.
- W2969355215 hasConceptScore W2969355215C89600930 @default.
- W2969355215 hasConceptScore W2969355215C95623464 @default.
- W2969355215 hasLocation W29693552151 @default.
- W2969355215 hasOpenAccess W2969355215 @default.
- W2969355215 hasPrimaryLocation W29693552151 @default.
- W2969355215 hasRelatedWork W1725366614 @default.
- W2969355215 hasRelatedWork W1973688192 @default.
- W2969355215 hasRelatedWork W2008662704 @default.
- W2969355215 hasRelatedWork W2100771357 @default.
- W2969355215 hasRelatedWork W2107443860 @default.
- W2969355215 hasRelatedWork W2156392723 @default.
- W2969355215 hasRelatedWork W2157355671 @default.
- W2969355215 hasRelatedWork W2230000137 @default.
- W2969355215 hasRelatedWork W2518191187 @default.
- W2969355215 hasRelatedWork W2746692960 @default.
- W2969355215 hasRelatedWork W2889280005 @default.
- W2969355215 hasRelatedWork W2889796430 @default.
- W2969355215 hasRelatedWork W2934616134 @default.
- W2969355215 hasRelatedWork W2951330332 @default.
- W2969355215 hasRelatedWork W3108432914 @default.
- W2969355215 hasRelatedWork W3113141731 @default.
- W2969355215 hasRelatedWork W3114281301 @default.
- W2969355215 hasRelatedWork W3133835534 @default.
- W2969355215 hasRelatedWork W3135697481 @default.
- W2969355215 hasRelatedWork W3128930327 @default.
- W2969355215 isParatext "false" @default.
- W2969355215 isRetracted "false" @default.
- W2969355215 magId "2969355215" @default.
- W2969355215 workType "article" @default.