Matches in SemOpenAlex for { <https://semopenalex.org/work/W3207082488> ?p ?o ?g. }
- W3207082488 abstract "Recent RGBD-based models for saliency detection have attracted research attention. The depth clues such as boundary clues, surface normal, shape attribute, etc., contribute to the identification of salient objects with complicated scenarios. However, most RGBD networks require multi-modalities from the input side and feed them separately through a two-stream design, which inevitably results in extra costs on depth sensors and computation. To tackle these inconveniences, we present in this paper a novel fusion design named modality-guided subnetwork (MGSnet). It has the following superior designs: 1) Our model works for both RGB and RGBD data, and dynamically estimating depth if not available. Taking the inner workings of depth-prediction networks into account, we propose to estimate the pseudo-geometry maps from RGB input - essentially mimicking the multi-modality input. 2) Our MGSnet for RGB SOD results in real-time inference but achieves state-of-the-art performance compared to other RGB models. 3) The flexible and lightweight design of MGS facilitates the integration into RGBD two-streaming models. The introduced fusion design enables a cross-modality interaction to enable further progress but with a minimal cost." @default.
- W3207082488 created "2021-10-25" @default.
- W3207082488 creator A5036455193 @default.
- W3207082488 creator A5038700866 @default.
- W3207082488 creator A5043000838 @default.
- W3207082488 creator A5058105016 @default.
- W3207082488 creator A5088809198 @default.
- W3207082488 date "2021-12-01" @default.
- W3207082488 modified "2023-09-25" @default.
- W3207082488 title "Modality-Guided Subnetwork for Salient Object Detection" @default.
- W3207082488 cites W1903029394 @default.
- W3207082488 cites W1966025376 @default.
- W3207082488 cites W1976409045 @default.
- W3207082488 cites W1993713494 @default.
- W3207082488 cites W2033959528 @default.
- W3207082488 cites W2039298799 @default.
- W3207082488 cites W20683899 @default.
- W3207082488 cites W2090518410 @default.
- W3207082488 cites W2100470808 @default.
- W3207082488 cites W2194775991 @default.
- W3207082488 cites W2293332611 @default.
- W3207082488 cites W2601564443 @default.
- W3207082488 cites W2766315367 @default.
- W3207082488 cites W2807746031 @default.
- W3207082488 cites W2895251968 @default.
- W3207082488 cites W2939217524 @default.
- W3207082488 cites W2948510860 @default.
- W3207082488 cites W2957414648 @default.
- W3207082488 cites W2962835968 @default.
- W3207082488 cites W2963112696 @default.
- W3207082488 cites W2963529609 @default.
- W3207082488 cites W2963604034 @default.
- W3207082488 cites W2963906836 @default.
- W3207082488 cites W2964738399 @default.
- W3207082488 cites W2990984982 @default.
- W3207082488 cites W3002301267 @default.
- W3207082488 cites W3035284915 @default.
- W3207082488 cites W3035357085 @default.
- W3207082488 cites W3081167590 @default.
- W3207082488 cites W3089452245 @default.
- W3207082488 cites W3093213431 @default.
- W3207082488 cites W3108421143 @default.
- W3207082488 cites W3108608656 @default.
- W3207082488 cites W3108822985 @default.
- W3207082488 cites W3114152269 @default.
- W3207082488 cites W3124434019 @default.
- W3207082488 cites W3173882198 @default.
- W3207082488 cites W3177040887 @default.
- W3207082488 hasPublicationYear "2021" @default.
- W3207082488 type Work @default.
- W3207082488 sameAs 3207082488 @default.
- W3207082488 citedByCount "0" @default.
- W3207082488 crossrefType "proceedings-article" @default.
- W3207082488 hasAuthorship W3207082488A5036455193 @default.
- W3207082488 hasAuthorship W3207082488A5038700866 @default.
- W3207082488 hasAuthorship W3207082488A5043000838 @default.
- W3207082488 hasAuthorship W3207082488A5058105016 @default.
- W3207082488 hasAuthorship W3207082488A5088809198 @default.
- W3207082488 hasBestOaLocation W32070824881 @default.
- W3207082488 hasConcept C116834253 @default.
- W3207082488 hasConcept C144024400 @default.
- W3207082488 hasConcept C153180895 @default.
- W3207082488 hasConcept C154945302 @default.
- W3207082488 hasConcept C2776214188 @default.
- W3207082488 hasConcept C2779903281 @default.
- W3207082488 hasConcept C2780186347 @default.
- W3207082488 hasConcept C2780226545 @default.
- W3207082488 hasConcept C2780719617 @default.
- W3207082488 hasConcept C31972630 @default.
- W3207082488 hasConcept C36289849 @default.
- W3207082488 hasConcept C38652104 @default.
- W3207082488 hasConcept C41008148 @default.
- W3207082488 hasConcept C59822182 @default.
- W3207082488 hasConcept C82990744 @default.
- W3207082488 hasConcept C86803240 @default.
- W3207082488 hasConceptScore W3207082488C116834253 @default.
- W3207082488 hasConceptScore W3207082488C144024400 @default.
- W3207082488 hasConceptScore W3207082488C153180895 @default.
- W3207082488 hasConceptScore W3207082488C154945302 @default.
- W3207082488 hasConceptScore W3207082488C2776214188 @default.
- W3207082488 hasConceptScore W3207082488C2779903281 @default.
- W3207082488 hasConceptScore W3207082488C2780186347 @default.
- W3207082488 hasConceptScore W3207082488C2780226545 @default.
- W3207082488 hasConceptScore W3207082488C2780719617 @default.
- W3207082488 hasConceptScore W3207082488C31972630 @default.
- W3207082488 hasConceptScore W3207082488C36289849 @default.
- W3207082488 hasConceptScore W3207082488C38652104 @default.
- W3207082488 hasConceptScore W3207082488C41008148 @default.
- W3207082488 hasConceptScore W3207082488C59822182 @default.
- W3207082488 hasConceptScore W3207082488C82990744 @default.
- W3207082488 hasConceptScore W3207082488C86803240 @default.
- W3207082488 hasLocation W32070824881 @default.
- W3207082488 hasLocation W320708248810 @default.
- W3207082488 hasLocation W32070824882 @default.
- W3207082488 hasLocation W32070824883 @default.
- W3207082488 hasLocation W32070824884 @default.
- W3207082488 hasLocation W32070824885 @default.
- W3207082488 hasLocation W32070824886 @default.
- W3207082488 hasLocation W32070824887 @default.
- W3207082488 hasLocation W32070824888 @default.