Matches in SemOpenAlex for { <https://semopenalex.org/work/W2612243891> ?p ?o ?g. }
- W2612243891 abstract "In this work, we decompose a first-person action into verb and noun. We then study how the coupling of an action's constituent verb and noun affects the learners' ability to learn them separately and to combine them to perform recognition. We compare different information fusion methods on conventional action recognition and zero-shot learning, of which the latter is a strong indication of the feature's ability to capture one concept (verb/noun) and not be confounded by the other. To achieve the decoupling of verb/noun concepts, we extract features that are specialized for each of them. Specifically, we use improved dense trajectories and convolutional neural network activations. We show that by constructing specialized features for the decomposed concepts, our method succeeds in zero-shot learning. More surprisingly, it also outperforms previous results in conventional action recognition when the performance gaps of different features on verb/noun concepts are significant." @default.
- W2612243891 created "2017-05-19" @default.
- W2612243891 creator A5002228469 @default.
- W2612243891 creator A5054794967 @default.
- W2612243891 creator A5083532124 @default.
- W2612243891 date "2017-03-01" @default.
- W2612243891 modified "2023-09-25" @default.
- W2612243891 title "First-Person Action Decomposition and Zero-Shot Learning" @default.
- W2612243891 cites W125606985 @default.
- W2612243891 cites W141352744 @default.
- W2612243891 cites W1606858007 @default.
- W2612243891 cites W1670526751 @default.
- W2612243891 cites W1748750709 @default.
- W2612243891 cites W1805946669 @default.
- W2612243891 cites W1912797782 @default.
- W2612243891 cites W1947050545 @default.
- W2612243891 cites W1967686239 @default.
- W2612243891 cites W1969363575 @default.
- W2612243891 cites W1975780119 @default.
- W2612243891 cites W1976546217 @default.
- W2612243891 cites W1977420968 @default.
- W2612243891 cites W1983364832 @default.
- W2612243891 cites W1989085630 @default.
- W2612243891 cites W2016053056 @default.
- W2612243891 cites W2038765747 @default.
- W2612243891 cites W2050230532 @default.
- W2612243891 cites W2062118960 @default.
- W2612243891 cites W2064851185 @default.
- W2612243891 cites W2100771357 @default.
- W2612243891 cites W2101039060 @default.
- W2612243891 cites W2102605133 @default.
- W2612243891 cites W2105101328 @default.
- W2612243891 cites W2118585731 @default.
- W2612243891 cites W2124033848 @default.
- W2612243891 cites W2136668269 @default.
- W2612243891 cites W2153635508 @default.
- W2612243891 cites W2155541015 @default.
- W2612243891 cites W2155983176 @default.
- W2612243891 cites W2163292664 @default.
- W2612243891 cites W2163605009 @default.
- W2612243891 cites W2165605600 @default.
- W2612243891 cites W2169393274 @default.
- W2612243891 cites W2212494831 @default.
- W2612243891 cites W2463762378 @default.
- W2612243891 cites W2496009737 @default.
- W2612243891 cites W259727857 @default.
- W2612243891 cites W2964086552 @default.
- W2612243891 cites W2964222622 @default.
- W2612243891 cites W3143107425 @default.
- W2612243891 cites W7746136 @default.
- W2612243891 doi "https://doi.org/10.1109/wacv.2017.21" @default.
- W2612243891 hasPublicationYear "2017" @default.
- W2612243891 type Work @default.
- W2612243891 sameAs 2612243891 @default.
- W2612243891 citedByCount "4" @default.
- W2612243891 countsByYear W26122438912019 @default.
- W2612243891 countsByYear W26122438912020 @default.
- W2612243891 crossrefType "proceedings-article" @default.
- W2612243891 hasAuthorship W2612243891A5002228469 @default.
- W2612243891 hasAuthorship W2612243891A5054794967 @default.
- W2612243891 hasAuthorship W2612243891A5083532124 @default.
- W2612243891 hasConcept C121332964 @default.
- W2612243891 hasConcept C121934690 @default.
- W2612243891 hasConcept C153180895 @default.
- W2612243891 hasConcept C154945302 @default.
- W2612243891 hasConcept C204321447 @default.
- W2612243891 hasConcept C2776397901 @default.
- W2612243891 hasConcept C2780791683 @default.
- W2612243891 hasConcept C41008148 @default.
- W2612243891 hasConcept C62520636 @default.
- W2612243891 hasConceptScore W2612243891C121332964 @default.
- W2612243891 hasConceptScore W2612243891C121934690 @default.
- W2612243891 hasConceptScore W2612243891C153180895 @default.
- W2612243891 hasConceptScore W2612243891C154945302 @default.
- W2612243891 hasConceptScore W2612243891C204321447 @default.
- W2612243891 hasConceptScore W2612243891C2776397901 @default.
- W2612243891 hasConceptScore W2612243891C2780791683 @default.
- W2612243891 hasConceptScore W2612243891C41008148 @default.
- W2612243891 hasConceptScore W2612243891C62520636 @default.
- W2612243891 hasLocation W26122438911 @default.
- W2612243891 hasOpenAccess W2612243891 @default.
- W2612243891 hasPrimaryLocation W26122438911 @default.
- W2612243891 hasRelatedWork W1584193343 @default.
- W2612243891 hasRelatedWork W1939171964 @default.
- W2612243891 hasRelatedWork W1966443646 @default.
- W2612243891 hasRelatedWork W1967678928 @default.
- W2612243891 hasRelatedWork W1968249707 @default.
- W2612243891 hasRelatedWork W2006265789 @default.
- W2612243891 hasRelatedWork W206455884 @default.
- W2612243891 hasRelatedWork W2082899426 @default.
- W2612243891 hasRelatedWork W2091047936 @default.
- W2612243891 hasRelatedWork W2101194084 @default.
- W2612243891 hasRelatedWork W2110271102 @default.
- W2612243891 hasRelatedWork W2120548134 @default.
- W2612243891 hasRelatedWork W2133656631 @default.
- W2612243891 hasRelatedWork W2580369806 @default.
- W2612243891 hasRelatedWork W2783628087 @default.
- W2612243891 hasRelatedWork W2890407764 @default.
- W2612243891 hasRelatedWork W2963783448 @default.
- W2612243891 hasRelatedWork W2963911773 @default.