Matches in SemOpenAlex for { <https://semopenalex.org/work/W3198062544> ?p ?o ?g. }
- W3198062544 endingPage "7802" @default.
- W3198062544 startingPage "7790" @default.
- W3198062544 abstract "Semantic segmentation is a fundamental task in computer vision, and it has various applications in fields such as robotic sensing, video surveillance, and autonomous driving. A major research topic in urban road semantic segmentation is the proper integration and use of cross-modal information for fusion. Here, we attempt to leverage inherent multimodal information and acquire graded features to develop a novel multilabel-learning network for RGB-thermal urban scene semantic segmentation. Specifically, we propose a strategy for graded-feature extraction to split multilevel features into junior, intermediate, and senior levels. Then, we integrate RGB and thermal modalities with two distinct fusion modules, namely a shallow feature fusion module and deep feature fusion module for junior and senior features. Finally, we use multilabel supervision to optimize the network in terms of semantic, binary, and boundary characteristics. Experimental results confirm that the proposed architecture, the graded-feature multilabel-learning network, outperforms state-of-the-art methods for urban scene semantic segmentation, and it can be generalized to depth data." @default.
- W3198062544 created "2021-09-13" @default.
- W3198062544 creator A5051293671 @default.
- W3198062544 creator A5053381821 @default.
- W3198062544 creator A5063621364 @default.
- W3198062544 creator A5065496543 @default.
- W3198062544 creator A5076872319 @default.
- W3198062544 date "2021-01-01" @default.
- W3198062544 modified "2023-10-16" @default.
- W3198062544 title "GMNet: Graded-Feature Multilabel-Learning Network for RGB-Thermal Urban Scene Semantic Segmentation" @default.
- W3198062544 cites W1745334888 @default.
- W3198062544 cites W2067912884 @default.
- W3198062544 cites W2194775991 @default.
- W3198062544 cites W2395611524 @default.
- W3198062544 cites W2557406251 @default.
- W3198062544 cites W2560023338 @default.
- W3198062544 cites W2592939477 @default.
- W3198062544 cites W2774839435 @default.
- W3198062544 cites W2775906317 @default.
- W3198062544 cites W2793219235 @default.
- W3198062544 cites W2795587607 @default.
- W3198062544 cites W2798825526 @default.
- W3198062544 cites W2799166040 @default.
- W3198062544 cites W2799256316 @default.
- W3198062544 cites W2906074946 @default.
- W3198062544 cites W2916798096 @default.
- W3198062544 cites W2920827956 @default.
- W3198062544 cites W2921749009 @default.
- W3198062544 cites W2939571759 @default.
- W3198062544 cites W2943622379 @default.
- W3198062544 cites W2963163009 @default.
- W3198062544 cites W2963446712 @default.
- W3198062544 cites W2963881378 @default.
- W3198062544 cites W2971014764 @default.
- W3198062544 cites W2973505799 @default.
- W3198062544 cites W2981689412 @default.
- W3198062544 cites W2997355859 @default.
- W3198062544 cites W2999725795 @default.
- W3198062544 cites W3002301267 @default.
- W3198062544 cites W3033020497 @default.
- W3198062544 cites W3035026422 @default.
- W3198062544 cites W3080081801 @default.
- W3198062544 cites W3088365851 @default.
- W3198062544 cites W3112503277 @default.
- W3198062544 cites W3120889480 @default.
- W3198062544 cites W3137799923 @default.
- W3198062544 cites W3193498964 @default.
- W3198062544 cites W3195868619 @default.
- W3198062544 doi "https://doi.org/10.1109/tip.2021.3109518" @default.
- W3198062544 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34495832" @default.
- W3198062544 hasPublicationYear "2021" @default.
- W3198062544 type Work @default.
- W3198062544 sameAs 3198062544 @default.
- W3198062544 citedByCount "113" @default.
- W3198062544 countsByYear W31980625442021 @default.
- W3198062544 countsByYear W31980625442022 @default.
- W3198062544 countsByYear W31980625442023 @default.
- W3198062544 crossrefType "journal-article" @default.
- W3198062544 hasAuthorship W3198062544A5051293671 @default.
- W3198062544 hasAuthorship W3198062544A5053381821 @default.
- W3198062544 hasAuthorship W3198062544A5063621364 @default.
- W3198062544 hasAuthorship W3198062544A5065496543 @default.
- W3198062544 hasAuthorship W3198062544A5076872319 @default.
- W3198062544 hasConcept C124504099 @default.
- W3198062544 hasConcept C138885662 @default.
- W3198062544 hasConcept C153180895 @default.
- W3198062544 hasConcept C154945302 @default.
- W3198062544 hasConcept C2776401178 @default.
- W3198062544 hasConcept C31972630 @default.
- W3198062544 hasConcept C41008148 @default.
- W3198062544 hasConcept C41895202 @default.
- W3198062544 hasConcept C52622490 @default.
- W3198062544 hasConcept C82990744 @default.
- W3198062544 hasConcept C89600930 @default.
- W3198062544 hasConceptScore W3198062544C124504099 @default.
- W3198062544 hasConceptScore W3198062544C138885662 @default.
- W3198062544 hasConceptScore W3198062544C153180895 @default.
- W3198062544 hasConceptScore W3198062544C154945302 @default.
- W3198062544 hasConceptScore W3198062544C2776401178 @default.
- W3198062544 hasConceptScore W3198062544C31972630 @default.
- W3198062544 hasConceptScore W3198062544C41008148 @default.
- W3198062544 hasConceptScore W3198062544C41895202 @default.
- W3198062544 hasConceptScore W3198062544C52622490 @default.
- W3198062544 hasConceptScore W3198062544C82990744 @default.
- W3198062544 hasConceptScore W3198062544C89600930 @default.
- W3198062544 hasFunder F4320321001 @default.
- W3198062544 hasFunder F4320338464 @default.
- W3198062544 hasLocation W31980625441 @default.
- W3198062544 hasOpenAccess W3198062544 @default.
- W3198062544 hasPrimaryLocation W31980625441 @default.
- W3198062544 hasRelatedWork W1631910785 @default.
- W3198062544 hasRelatedWork W1669643531 @default.
- W3198062544 hasRelatedWork W2110230079 @default.
- W3198062544 hasRelatedWork W2122581818 @default.
- W3198062544 hasRelatedWork W2134924024 @default.
- W3198062544 hasRelatedWork W2159066190 @default.
- W3198062544 hasRelatedWork W2558375057 @default.
- W3198062544 hasRelatedWork W2568271872 @default.