Matches in SemOpenAlex for { <https://semopenalex.org/work/W2883275382> ?p ?o ?g. }
- W2883275382 endingPage "351" @default.
- W2883275382 startingPage "335" @default.
- W2883275382 abstract "Current state-of-the-art approaches for spatio-temporal action localization rely on detections at the frame level and model temporal context with 3D ConvNets. Here, we go one step further and model spatio-temporal relations to capture the interactions between human actors, relevant objects and scene elements essential to differentiate similar human actions. Our approach is weakly supervised and mines the relevant elements automatically with an actor-centric relational network (ACRN). ACRN computes and accumulates pair-wise relation information from actor and global scene features, and generates relation features for action classification. It is implemented as neural networks and can be trained jointly with an existing action detection system. We show that ACRN outperforms alternative approaches which capture relation information, and that the proposed framework improves upon the state-of-the-art performance on JHMDB and AVA. A visualization of the learned relation features confirms that our approach is able to attend to the relevant relations for each action." @default.
- W2883275382 created "2018-08-03" @default.
- W2883275382 creator A5002713363 @default.
- W2883275382 creator A5031745411 @default.
- W2883275382 creator A5045217258 @default.
- W2883275382 creator A5051997905 @default.
- W2883275382 creator A5060145891 @default.
- W2883275382 creator A5066107323 @default.
- W2883275382 date "2018-01-01" @default.
- W2883275382 modified "2023-10-13" @default.
- W2883275382 title "Actor-Centric Relation Network" @default.
- W2883275382 cites W1516887802 @default.
- W2883275382 cites W1522734439 @default.
- W2883275382 cites W1536680647 @default.
- W2883275382 cites W1566135517 @default.
- W2883275382 cites W1797109199 @default.
- W2883275382 cites W1923332106 @default.
- W2883275382 cites W2016053056 @default.
- W2883275382 cites W2034014085 @default.
- W2883275382 cites W2046589395 @default.
- W2883275382 cites W2081293863 @default.
- W2883275382 cites W2097117768 @default.
- W2883275382 cites W2102605133 @default.
- W2883275382 cites W2117539524 @default.
- W2883275382 cites W2125215748 @default.
- W2883275382 cites W2128554449 @default.
- W2883275382 cites W2163292664 @default.
- W2883275382 cites W2194775991 @default.
- W2883275382 cites W2235034809 @default.
- W2883275382 cites W2288122362 @default.
- W2883275382 cites W2295107390 @default.
- W2883275382 cites W2337252826 @default.
- W2883275382 cites W2479423890 @default.
- W2883275382 cites W2519080876 @default.
- W2883275382 cites W2520951797 @default.
- W2883275382 cites W2557728737 @default.
- W2883275382 cites W2560474170 @default.
- W2883275382 cites W2561715562 @default.
- W2883275382 cites W2605111198 @default.
- W2883275382 cites W2611596598 @default.
- W2883275382 cites W2612076919 @default.
- W2883275382 cites W2618799552 @default.
- W2883275382 cites W2740962769 @default.
- W2883275382 cites W2755876276 @default.
- W2883275382 cites W2951183276 @default.
- W2883275382 cites W2962722947 @default.
- W2883275382 cites W2962790054 @default.
- W2883275382 cites W2962803561 @default.
- W2883275382 cites W2963091558 @default.
- W2883275382 cites W2963097937 @default.
- W2883275382 cites W2963247196 @default.
- W2883275382 cites W2963420272 @default.
- W2883275382 cites W2963524571 @default.
- W2883275382 cites W2964008341 @default.
- W2883275382 cites W2964225075 @default.
- W2883275382 cites W3106250896 @default.
- W2883275382 cites W343636949 @default.
- W2883275382 doi "https://doi.org/10.1007/978-3-030-01252-6_20" @default.
- W2883275382 hasPublicationYear "2018" @default.
- W2883275382 type Work @default.
- W2883275382 sameAs 2883275382 @default.
- W2883275382 citedByCount "132" @default.
- W2883275382 countsByYear W28832753822018 @default.
- W2883275382 countsByYear W28832753822019 @default.
- W2883275382 countsByYear W28832753822020 @default.
- W2883275382 countsByYear W28832753822021 @default.
- W2883275382 countsByYear W28832753822022 @default.
- W2883275382 countsByYear W28832753822023 @default.
- W2883275382 crossrefType "book-chapter" @default.
- W2883275382 hasAuthorship W2883275382A5002713363 @default.
- W2883275382 hasAuthorship W2883275382A5031745411 @default.
- W2883275382 hasAuthorship W2883275382A5045217258 @default.
- W2883275382 hasAuthorship W2883275382A5051997905 @default.
- W2883275382 hasAuthorship W2883275382A5060145891 @default.
- W2883275382 hasAuthorship W2883275382A5066107323 @default.
- W2883275382 hasBestOaLocation W28832753822 @default.
- W2883275382 hasConcept C11413529 @default.
- W2883275382 hasConcept C119857082 @default.
- W2883275382 hasConcept C121332964 @default.
- W2883275382 hasConcept C124101348 @default.
- W2883275382 hasConcept C126042441 @default.
- W2883275382 hasConcept C151730666 @default.
- W2883275382 hasConcept C154945302 @default.
- W2883275382 hasConcept C25343380 @default.
- W2883275382 hasConcept C2779343474 @default.
- W2883275382 hasConcept C2780791683 @default.
- W2883275382 hasConcept C36464697 @default.
- W2883275382 hasConcept C41008148 @default.
- W2883275382 hasConcept C48103436 @default.
- W2883275382 hasConcept C50644808 @default.
- W2883275382 hasConcept C62520636 @default.
- W2883275382 hasConcept C76155785 @default.
- W2883275382 hasConcept C86803240 @default.
- W2883275382 hasConceptScore W2883275382C11413529 @default.
- W2883275382 hasConceptScore W2883275382C119857082 @default.
- W2883275382 hasConceptScore W2883275382C121332964 @default.
- W2883275382 hasConceptScore W2883275382C124101348 @default.
- W2883275382 hasConceptScore W2883275382C126042441 @default.