Matches in SemOpenAlex for { <https://semopenalex.org/work/W3036763926> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W3036763926 endingPage "106142" @default.
- W3036763926 startingPage "106142" @default.
- W3036763926 abstract "Traditional visual relationship detection methods only use RGB information to train the semantic network, which do not match human habits that we combine RGB information with Depth information to perceive the world, thus, there is not enough generalization ability (zero-shot performance) to extract the visual relationships in practical scenes. To solve this problem, a novel visual relationship detection framework based on RGB-D images is proposed in this paper. Since it is difficult to get accurate depth maps from complex scenes, we propose a fuzzy strategy based method to represent Depth features of inaccurate depth maps which are independent of manual depth annotations. In particular, we formulate the RGB-Depth-Balanced-Network (RDBN) which can simultaneously process RGB features and the corresponding estimated depth maps to counter the inaccuracy of depth maps and extract semantic information by the only input of monocular RGB images. In experiments, we conduct ablation experiments to analyze functions of different visual components to demonstrate the effectiveness of our RDBN. Furthermore, we show that RDBN outperforms state-of-the-art visual relationship detection methods on Visual Relationship Dataset (VRD) and UnRel Dataset when tackling the visual relationship detection task of zero-shot learning in specific depth conditions, and the task of image retrieval among unusual relationships." @default.
- W3036763926 created "2020-06-25" @default.
- W3036763926 creator A5016072306 @default.
- W3036763926 creator A5050094456 @default.
- W3036763926 date "2020-09-01" @default.
- W3036763926 modified "2023-10-14" @default.
- W3036763926 title "RDBN: Visual relationship detection with inaccurate RGB-D images" @default.
- W3036763926 cites W2117539524 @default.
- W3036763926 cites W2129947832 @default.
- W3036763926 cites W2169393274 @default.
- W3036763926 cites W2462848072 @default.
- W3036763926 cites W2479423890 @default.
- W3036763926 cites W2481240925 @default.
- W3036763926 cites W2590973145 @default.
- W3036763926 cites W2735159761 @default.
- W3036763926 cites W2795378892 @default.
- W3036763926 cites W2799029629 @default.
- W3036763926 cites W2883170015 @default.
- W3036763926 cites W2904323922 @default.
- W3036763926 cites W2963514444 @default.
- W3036763926 cites W2963767186 @default.
- W3036763926 cites W2980248933 @default.
- W3036763926 cites W3100166939 @default.
- W3036763926 doi "https://doi.org/10.1016/j.knosys.2020.106142" @default.
- W3036763926 hasPublicationYear "2020" @default.
- W3036763926 type Work @default.
- W3036763926 sameAs 3036763926 @default.
- W3036763926 citedByCount "4" @default.
- W3036763926 countsByYear W30367639262021 @default.
- W3036763926 countsByYear W30367639262022 @default.
- W3036763926 crossrefType "journal-article" @default.
- W3036763926 hasAuthorship W3036763926A5016072306 @default.
- W3036763926 hasAuthorship W3036763926A5050094456 @default.
- W3036763926 hasConcept C153180895 @default.
- W3036763926 hasConcept C154945302 @default.
- W3036763926 hasConcept C162324750 @default.
- W3036763926 hasConcept C187736073 @default.
- W3036763926 hasConcept C2780451532 @default.
- W3036763926 hasConcept C31972630 @default.
- W3036763926 hasConcept C41008148 @default.
- W3036763926 hasConcept C65909025 @default.
- W3036763926 hasConcept C82990744 @default.
- W3036763926 hasConceptScore W3036763926C153180895 @default.
- W3036763926 hasConceptScore W3036763926C154945302 @default.
- W3036763926 hasConceptScore W3036763926C162324750 @default.
- W3036763926 hasConceptScore W3036763926C187736073 @default.
- W3036763926 hasConceptScore W3036763926C2780451532 @default.
- W3036763926 hasConceptScore W3036763926C31972630 @default.
- W3036763926 hasConceptScore W3036763926C41008148 @default.
- W3036763926 hasConceptScore W3036763926C65909025 @default.
- W3036763926 hasConceptScore W3036763926C82990744 @default.
- W3036763926 hasFunder F4320323110 @default.
- W3036763926 hasLocation W30367639261 @default.
- W3036763926 hasOpenAccess W3036763926 @default.
- W3036763926 hasPrimaryLocation W30367639261 @default.
- W3036763926 hasRelatedWork W2047692640 @default.
- W3036763926 hasRelatedWork W2743237568 @default.
- W3036763926 hasRelatedWork W2794771666 @default.
- W3036763926 hasRelatedWork W2891001608 @default.
- W3036763926 hasRelatedWork W2980953096 @default.
- W3036763926 hasRelatedWork W3102636071 @default.
- W3036763926 hasRelatedWork W3121363684 @default.
- W3036763926 hasRelatedWork W4298315644 @default.
- W3036763926 hasRelatedWork W4312708709 @default.
- W3036763926 hasRelatedWork W4321512589 @default.
- W3036763926 hasVolume "204" @default.
- W3036763926 isParatext "false" @default.
- W3036763926 isRetracted "false" @default.
- W3036763926 magId "3036763926" @default.
- W3036763926 workType "article" @default.