Matches in SemOpenAlex for { <https://semopenalex.org/work/W2780335118> ?p ?o ?g. }
Showing items 1 to 45 of
45
with 100 items per page.
- W2780335118 abstract "Grounding language in the physical world enables humans to use words and sentences in context and to link them to actions. Several recent computer vision studies have worked on the task of expression grounding: learning to select that part of an image that depicts the referent of a multi-word expression. The task is approached by joint processing of the language expression, visual information of individual candidate referents, and in some cases the general visual context, using neural models that combine recurrent and convolutional components (Rohrbach et al., 2016; Hu et al., 2016b,a). However, there is more than just the intended referent by itself that determines how a referring expression is phrased. When referring to an element of a scene, its relations with and contrasts to other elements are taken into account in order to produce an expression that uniquely identifies the intended referent. Inspired by recent work on visual question answering using Relation Networks (Santoro et al., 2017) we build and evaluate models of expression grounding that take in account interactions between elements of the visual scene. We provide an analysis of the performance and the relational representations learned in this setting." @default.
- W2780335118 created "2018-01-05" @default.
- W2780335118 creator A5000074624 @default.
- W2780335118 creator A5022698890 @default.
- W2780335118 creator A5047382001 @default.
- W2780335118 creator A5050569769 @default.
- W2780335118 date "2017-01-01" @default.
- W2780335118 modified "2023-09-27" @default.
- W2780335118 title "Modeling relations in a referential game" @default.
- W2780335118 hasPublicationYear "2017" @default.
- W2780335118 type Work @default.
- W2780335118 sameAs 2780335118 @default.
- W2780335118 citedByCount "0" @default.
- W2780335118 crossrefType "proceedings-article" @default.
- W2780335118 hasAuthorship W2780335118A5000074624 @default.
- W2780335118 hasAuthorship W2780335118A5022698890 @default.
- W2780335118 hasAuthorship W2780335118A5047382001 @default.
- W2780335118 hasAuthorship W2780335118A5050569769 @default.
- W2780335118 hasLocation W27803351181 @default.
- W2780335118 hasOpenAccess W2780335118 @default.
- W2780335118 hasPrimaryLocation W27803351181 @default.
- W2780335118 hasRelatedWork W1296442 @default.
- W2780335118 hasRelatedWork W1821106251 @default.
- W2780335118 hasRelatedWork W1923162067 @default.
- W2780335118 hasRelatedWork W2111807093 @default.
- W2780335118 hasRelatedWork W2134211342 @default.
- W2780335118 hasRelatedWork W2489434015 @default.
- W2780335118 hasRelatedWork W2750069989 @default.
- W2780335118 hasRelatedWork W2766969354 @default.
- W2780335118 hasRelatedWork W2767800181 @default.
- W2780335118 hasRelatedWork W2962995070 @default.
- W2780335118 hasRelatedWork W2970488023 @default.
- W2780335118 hasRelatedWork W2974011685 @default.
- W2780335118 hasRelatedWork W2995156524 @default.
- W2780335118 hasRelatedWork W3023745006 @default.
- W2780335118 hasRelatedWork W3035635363 @default.
- W2780335118 hasRelatedWork W3094503863 @default.
- W2780335118 hasRelatedWork W3211756744 @default.
- W2780335118 hasRelatedWork W3212433538 @default.
- W2780335118 hasRelatedWork W3214323751 @default.
- W2780335118 hasRelatedWork W1570983904 @default.
- W2780335118 isParatext "false" @default.
- W2780335118 isRetracted "false" @default.
- W2780335118 magId "2780335118" @default.
- W2780335118 workType "article" @default.