Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387186411> ?p ?o ?g. }
- W4387186411 endingPage "204" @default.
- W4387186411 startingPage "204" @default.
- W4387186411 abstract "The problem of gathering sufficiently representative data, such as those about human actions, shapes, and facial expressions, is costly and time-consuming and also requires training robust models. This has led to the creation of techniques such as transfer learning or data augmentation. However, these are often insufficient. To address this, we propose a semi-automated mechanism that allows the generation and editing of visual scenes with synthetic humans performing various actions, with features such as background modification and manual adjustments of the 3D avatars to allow users to create data with greater variability. We also propose an evaluation methodology for assessing the results obtained using our method, which is two-fold: (i) the usage of an action classifier on the output data resulting from the mechanism and (ii) the generation of masks of the avatars and the actors to compare them through segmentation. The avatars were robust to occlusion, and their actions were recognizable and accurate to their respective input actors. The results also showed that even though the action classifier concentrates on the pose and movement of the synthetic humans, it strongly depends on contextual information to precisely recognize the actions. Generating the avatars for complex activities also proved problematic for action recognition and the clean and precise formation of the masks." @default.
- W4387186411 created "2023-09-30" @default.
- W4387186411 creator A5016372118 @default.
- W4387186411 creator A5041379293 @default.
- W4387186411 creator A5058749114 @default.
- W4387186411 creator A5080307019 @default.
- W4387186411 date "2023-09-29" @default.
- W4387186411 modified "2023-10-16" @default.
- W4387186411 title "Synthesizing Human Activity for Data Generation" @default.
- W4387186411 cites W1861492603 @default.
- W4387186411 cites W1943191679 @default.
- W4387186411 cites W1967320926 @default.
- W4387186411 cites W1967554269 @default.
- W4387186411 cites W2017107803 @default.
- W4387186411 cites W2090994350 @default.
- W4387186411 cites W2099333815 @default.
- W4387186411 cites W2100993058 @default.
- W4387186411 cites W2101032778 @default.
- W4387186411 cites W2107037917 @default.
- W4387186411 cites W2126579184 @default.
- W4387186411 cites W2137940226 @default.
- W4387186411 cites W2143478373 @default.
- W4387186411 cites W2150059981 @default.
- W4387186411 cites W2163844242 @default.
- W4387186411 cites W2194775991 @default.
- W4387186411 cites W2483862638 @default.
- W4387186411 cites W2576289912 @default.
- W4387186411 cites W2756050327 @default.
- W4387186411 cites W2768683308 @default.
- W4387186411 cites W2769666294 @default.
- W4387186411 cites W2781181706 @default.
- W4387186411 cites W2895748257 @default.
- W4387186411 cites W2900753655 @default.
- W4387186411 cites W2904657185 @default.
- W4387186411 cites W2910628332 @default.
- W4387186411 cites W2962895364 @default.
- W4387186411 cites W2963150697 @default.
- W4387186411 cites W2963839617 @default.
- W4387186411 cites W2963876278 @default.
- W4387186411 cites W2963995996 @default.
- W4387186411 cites W2978956737 @default.
- W4387186411 cites W2982335979 @default.
- W4387186411 cites W3000322757 @default.
- W4387186411 cites W3035492592 @default.
- W4387186411 cites W3035551320 @default.
- W4387186411 cites W3106838237 @default.
- W4387186411 cites W3204956438 @default.
- W4387186411 cites W4206341720 @default.
- W4387186411 cites W4214770715 @default.
- W4387186411 cites W4283735406 @default.
- W4387186411 cites W4385263018 @default.
- W4387186411 cites W4386066388 @default.
- W4387186411 doi "https://doi.org/10.3390/jimaging9100204" @default.
- W4387186411 hasPublicationYear "2023" @default.
- W4387186411 type Work @default.
- W4387186411 citedByCount "0" @default.
- W4387186411 crossrefType "journal-article" @default.
- W4387186411 hasAuthorship W4387186411A5016372118 @default.
- W4387186411 hasAuthorship W4387186411A5041379293 @default.
- W4387186411 hasAuthorship W4387186411A5058749114 @default.
- W4387186411 hasAuthorship W4387186411A5080307019 @default.
- W4387186411 hasBestOaLocation W43871864111 @default.
- W4387186411 hasConcept C104114177 @default.
- W4387186411 hasConcept C107457646 @default.
- W4387186411 hasConcept C119857082 @default.
- W4387186411 hasConcept C154945302 @default.
- W4387186411 hasConcept C160920958 @default.
- W4387186411 hasConcept C2776145971 @default.
- W4387186411 hasConcept C2777212361 @default.
- W4387186411 hasConcept C2987834672 @default.
- W4387186411 hasConcept C31972630 @default.
- W4387186411 hasConcept C41008148 @default.
- W4387186411 hasConcept C48007421 @default.
- W4387186411 hasConcept C51632099 @default.
- W4387186411 hasConcept C89600930 @default.
- W4387186411 hasConcept C95623464 @default.
- W4387186411 hasConceptScore W4387186411C104114177 @default.
- W4387186411 hasConceptScore W4387186411C107457646 @default.
- W4387186411 hasConceptScore W4387186411C119857082 @default.
- W4387186411 hasConceptScore W4387186411C154945302 @default.
- W4387186411 hasConceptScore W4387186411C160920958 @default.
- W4387186411 hasConceptScore W4387186411C2776145971 @default.
- W4387186411 hasConceptScore W4387186411C2777212361 @default.
- W4387186411 hasConceptScore W4387186411C2987834672 @default.
- W4387186411 hasConceptScore W4387186411C31972630 @default.
- W4387186411 hasConceptScore W4387186411C41008148 @default.
- W4387186411 hasConceptScore W4387186411C48007421 @default.
- W4387186411 hasConceptScore W4387186411C51632099 @default.
- W4387186411 hasConceptScore W4387186411C89600930 @default.
- W4387186411 hasConceptScore W4387186411C95623464 @default.
- W4387186411 hasFunder F4320334779 @default.
- W4387186411 hasIssue "10" @default.
- W4387186411 hasLocation W43871864111 @default.
- W4387186411 hasOpenAccess W4387186411 @default.
- W4387186411 hasPrimaryLocation W43871864111 @default.
- W4387186411 hasRelatedWork W1963135442 @default.
- W4387186411 hasRelatedWork W2033364610 @default.
- W4387186411 hasRelatedWork W2130553454 @default.