FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3142500263> ?p ?o ?g. }

• W3142500263 endingPage "4422" @default.
• W3142500263 startingPage "4409" @default.
• W3142500263 abstract "Smoke has semi-transparency property leading to highly complicated mixture of background and smoke. Sparse or small smoke is visually inconspicuous, and its boundary is often ambiguous. These reasons result in a very challenging task of separating smoke from a single image. To solve these problems, we propose a Classification-assisted Gated Recurrent Network (CGRNet) for smoke semantic segmentation. To discriminate smoke and smoke-like objects, we present a smoke segmentation strategy with dual classification assistance. Our classification module outputs two prediction probabilities for smoke. The first assistance is to use one probability to explicitly regulate the segmentation module for accuracy improvement by supervising a cross-entropy classification loss. The second one is to multiply the segmentation result by another probability for further refinement. This dual classification assistance greatly improves performance at image level. In the segmentation module, we design an Attention Convolutional GRU module (Att-ConvGRU) to learn the long-range context dependence of features. To perceive small or inconspicuous smoke, we design a Multi-scale Context Contrasted Local Feature structure (MCCL) and a Dense Pyramid Pooling Module (DPPM) for improving the representation ability of our network. Extensive experiments validate that our method significantly outperforms existing state-of-art algorithms on smoke datasets, and also obtain satisfactory results on challenging images with inconspicuous smoke and smoke-like objects." @default.
• W3142500263 created "2021-04-13" @default.
• W3142500263 creator A5012342645 @default.
• W3142500263 creator A5021541475 @default.
• W3142500263 creator A5024606637 @default.
• W3142500263 creator A5066148256 @default.
• W3142500263 creator A5068918243 @default.
• W3142500263 date "2021-01-01" @default.
• W3142500263 modified "2023-10-17" @default.
• W3142500263 title "A Gated Recurrent Network With Dual Classification Assistance for Smoke Semantic Segmentation" @default.
• W3142500263 cites W1903029394 @default.
• W3142500263 cites W1909234690 @default.
• W3142500263 cites W1922658220 @default.
• W3142500263 cites W2013300501 @default.
• W3142500263 cites W2042634646 @default.
• W3142500263 cites W2053529786 @default.
• W3142500263 cites W2064675550 @default.
• W3142500263 cites W2194775991 @default.
• W3142500263 cites W2339589954 @default.
• W3142500263 cites W2344001629 @default.
• W3142500263 cites W2412782625 @default.
• W3142500263 cites W2531409750 @default.
• W3142500263 cites W2560023338 @default.
• W3142500263 cites W2561585794 @default.
• W3142500263 cites W2563705555 @default.
• W3142500263 cites W2598666589 @default.
• W3142500263 cites W2601686579 @default.
• W3142500263 cites W2605127024 @default.
• W3142500263 cites W2623546809 @default.
• W3142500263 cites W2746174042 @default.
• W3142500263 cites W2750515003 @default.
• W3142500263 cites W2752782242 @default.
• W3142500263 cites W2756554574 @default.
• W3142500263 cites W2757028014 @default.
• W3142500263 cites W2767352048 @default.
• W3142500263 cites W2775906317 @default.
• W3142500263 cites W2777737607 @default.
• W3142500263 cites W2778764040 @default.
• W3142500263 cites W2794499044 @default.
• W3142500263 cites W2796299567 @default.
• W3142500263 cites W2798556392 @default.
• W3142500263 cites W2798791840 @default.
• W3142500263 cites W2799166040 @default.
• W3142500263 cites W2799213142 @default.
• W3142500263 cites W2799217622 @default.
• W3142500263 cites W2803990755 @default.
• W3142500263 cites W2892068485 @default.
• W3142500263 cites W2901853555 @default.
• W3142500263 cites W2906161342 @default.
• W3142500263 cites W2921536280 @default.
• W3142500263 cites W2926429807 @default.
• W3142500263 cites W2963150697 @default.
• W3142500263 cites W2963166928 @default.
• W3142500263 cites W2963253279 @default.
• W3142500263 cites W2963446712 @default.
• W3142500263 cites W2963548592 @default.
• W3142500263 cites W2963840241 @default.
• W3142500263 cites W2963881378 @default.
• W3142500263 cites W2963983744 @default.
• W3142500263 cites W2964199361 @default.
• W3142500263 cites W2980784832 @default.
• W3142500263 cites W2982182858 @default.
• W3142500263 cites W3002301267 @default.
• W3142500263 cites W3101507774 @default.
• W3142500263 doi "https://doi.org/10.1109/tip.2021.3069318" @default.
• W3142500263 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33798085" @default.
• W3142500263 hasPublicationYear "2021" @default.
• W3142500263 type Work @default.
• W3142500263 sameAs 3142500263 @default.
• W3142500263 citedByCount "30" @default.
• W3142500263 countsByYear W31425002632022 @default.
• W3142500263 countsByYear W31425002632023 @default.
• W3142500263 crossrefType "journal-article" @default.
• W3142500263 hasAuthorship W3142500263A5012342645 @default.
• W3142500263 hasAuthorship W3142500263A5021541475 @default.
• W3142500263 hasAuthorship W3142500263A5024606637 @default.
• W3142500263 hasAuthorship W3142500263A5066148256 @default.
• W3142500263 hasAuthorship W3142500263A5068918243 @default.
• W3142500263 hasConcept C115961682 @default.
• W3142500263 hasConcept C124504099 @default.
• W3142500263 hasConcept C127413603 @default.
• W3142500263 hasConcept C138885662 @default.
• W3142500263 hasConcept C142575187 @default.
• W3142500263 hasConcept C151730666 @default.
• W3142500263 hasConcept C153180895 @default.
• W3142500263 hasConcept C154945302 @default.
• W3142500263 hasConcept C2524010 @default.
• W3142500263 hasConcept C2776401178 @default.
• W3142500263 hasConcept C2779343474 @default.
• W3142500263 hasConcept C33923547 @default.
• W3142500263 hasConcept C41008148 @default.
• W3142500263 hasConcept C41895202 @default.
• W3142500263 hasConcept C548081761 @default.
• W3142500263 hasConcept C58874564 @default.
• W3142500263 hasConcept C70437156 @default.
• W3142500263 hasConcept C75294576 @default.
• W3142500263 hasConcept C81363708 @default.
• W3142500263 hasConcept C86803240 @default.

• next