Matches in SemOpenAlex for { <https://semopenalex.org/work/W3181356683> ?p ?o ?g. }
- W3181356683 endingPage "436" @default.
- W3181356683 startingPage "425" @default.
- W3181356683 abstract "Salient object detection aims to identify the most attractive objects from images. However, their boundaries are typically of poor quality when predicted using available methods. One or multiple objects may also be left undetected if the image contains multiple objects. To solve these problems, this article proposes the novel cross refinement network, which consists of a Res2Net-based backbone network; a fusion network equipped with four convolutional block attention modules and four edge-salient cross units; and a detection network with an edge enhancement unit and a residual refinement network (RNN). For RNN training, the rough salient maps generated using the DUTS-TR dataset are treated as a special training dataset. Compared to existing methods, the proposed network can effectively detect all objects as well as improve the boundaries of the detected objects by performing experiments on five benchmark datasets. Based on the experimental results, the proposed network outperforms existing methods both objectively and subjectively." @default.
- W3181356683 created "2021-07-19" @default.
- W3181356683 creator A5005723679 @default.
- W3181356683 creator A5011531008 @default.
- W3181356683 creator A5018372874 @default.
- W3181356683 creator A5037188516 @default.
- W3181356683 creator A5042365149 @default.
- W3181356683 date "2021-04-26" @default.
- W3181356683 modified "2023-09-23" @default.
- W3181356683 title "Cross refinement network with edge detection for salient object detection" @default.
- W3181356683 cites W1903029394 @default.
- W3181356683 cites W1994922096 @default.
- W3181356683 cites W2002781701 @default.
- W3181356683 cites W2039313011 @default.
- W3181356683 cites W2086791339 @default.
- W3181356683 cites W2108598243 @default.
- W3181356683 cites W2128272608 @default.
- W3181356683 cites W2518599539 @default.
- W3181356683 cites W2569272946 @default.
- W3181356683 cites W2740667773 @default.
- W3181356683 cites W2740797387 @default.
- W3181356683 cites W2744613561 @default.
- W3181356683 cites W2767623212 @default.
- W3181356683 cites W2793668851 @default.
- W3181356683 cites W2798791651 @default.
- W3181356683 cites W2884585870 @default.
- W3181356683 cites W2895251968 @default.
- W3181356683 cites W2895340898 @default.
- W3181356683 cites W2928165649 @default.
- W3181356683 cites W2938260698 @default.
- W3181356683 cites W2939217524 @default.
- W3181356683 cites W2939398001 @default.
- W3181356683 cites W2943125866 @default.
- W3181356683 cites W2948500402 @default.
- W3181356683 cites W2948510860 @default.
- W3181356683 cites W2955058313 @default.
- W3181356683 cites W2961348656 @default.
- W3181356683 cites W2963032190 @default.
- W3181356683 cites W2963112696 @default.
- W3181356683 cites W2963529609 @default.
- W3181356683 cites W2963706010 @default.
- W3181356683 cites W2963906836 @default.
- W3181356683 cites W2964775615 @default.
- W3181356683 cites W2969377765 @default.
- W3181356683 cites W2987701848 @default.
- W3181356683 cites W2997316506 @default.
- W3181356683 cites W3000281486 @default.
- W3181356683 cites W3003121299 @default.
- W3181356683 cites W3006465601 @default.
- W3181356683 cites W3015346259 @default.
- W3181356683 cites W3029368604 @default.
- W3181356683 cites W3030079400 @default.
- W3181356683 cites W3097336090 @default.
- W3181356683 cites W3102864715 @default.
- W3181356683 cites W3107944836 @default.
- W3181356683 cites W3108948422 @default.
- W3181356683 doi "https://doi.org/10.1049/sil2.12041" @default.
- W3181356683 hasPublicationYear "2021" @default.
- W3181356683 type Work @default.
- W3181356683 sameAs 3181356683 @default.
- W3181356683 citedByCount "2" @default.
- W3181356683 countsByYear W31813566832023 @default.
- W3181356683 crossrefType "journal-article" @default.
- W3181356683 hasAuthorship W3181356683A5005723679 @default.
- W3181356683 hasAuthorship W3181356683A5011531008 @default.
- W3181356683 hasAuthorship W3181356683A5018372874 @default.
- W3181356683 hasAuthorship W3181356683A5037188516 @default.
- W3181356683 hasAuthorship W3181356683A5042365149 @default.
- W3181356683 hasBestOaLocation W31813566831 @default.
- W3181356683 hasConcept C11413529 @default.
- W3181356683 hasConcept C13280743 @default.
- W3181356683 hasConcept C153180895 @default.
- W3181356683 hasConcept C154945302 @default.
- W3181356683 hasConcept C155512373 @default.
- W3181356683 hasConcept C162307627 @default.
- W3181356683 hasConcept C185798385 @default.
- W3181356683 hasConcept C193415008 @default.
- W3181356683 hasConcept C205649164 @default.
- W3181356683 hasConcept C2524010 @default.
- W3181356683 hasConcept C2776151529 @default.
- W3181356683 hasConcept C2777210771 @default.
- W3181356683 hasConcept C2780719617 @default.
- W3181356683 hasConcept C2781238097 @default.
- W3181356683 hasConcept C31258907 @default.
- W3181356683 hasConcept C31972630 @default.
- W3181356683 hasConcept C33923547 @default.
- W3181356683 hasConcept C38652104 @default.
- W3181356683 hasConcept C41008148 @default.
- W3181356683 hasConcept C81363708 @default.
- W3181356683 hasConcept C88796919 @default.
- W3181356683 hasConceptScore W3181356683C11413529 @default.
- W3181356683 hasConceptScore W3181356683C13280743 @default.
- W3181356683 hasConceptScore W3181356683C153180895 @default.
- W3181356683 hasConceptScore W3181356683C154945302 @default.
- W3181356683 hasConceptScore W3181356683C155512373 @default.
- W3181356683 hasConceptScore W3181356683C162307627 @default.
- W3181356683 hasConceptScore W3181356683C185798385 @default.
- W3181356683 hasConceptScore W3181356683C193415008 @default.