FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2997421813> ?p ?o ?g. }

• W2997421813 endingPage "1743" @default.
• W2997421813 startingPage "1730" @default.
• W2997421813 abstract "Supervised deep learning techniques have achieved great success in various fields due to getting rid of the limitation of handcrafted representations. However, most previous image retargeting algorithms still employ fixed design principles such as using gradient map or handcrafted features to compute saliency map, which inevitably restricts its generality. Deep learning techniques may help to address this issue, but the challenging problem is that we need to build a large-scale image retargeting dataset for the training of deep retargeting models. However, building such a dataset requires huge human efforts. In this paper, we propose a novel deep cyclic image retargeting approach, called Cycle-IR, to firstly implement image retargeting with a single deep model, without relying on any explicit user annotations. Our idea is built on the reverse mapping from the retargeted images to the given images. If the retargeted image has serious distortion or excessive loss of important visual information, the reverse mapping is unlikely to restore the input image well. We constrain this forward-reverse consistency by introducing a cyclic perception coherence loss. In addition, we propose a simple yet effective image retargeting network (IRNet) to implement the image retargeting process. Our IRNet contains a spatial and channel attention layer, which is able to discriminate visually important regions of input images effectively, especially in cluttered images. Given arbitrary sizes of input images and desired aspect ratios, our Cycle-IR can produce visually pleasing target images directly. Extensive experiments on the standard RetargetMe dataset show the superiority of our Cycle-IR." @default.
• W2997421813 created "2020-01-10" @default.
• W2997421813 creator A5017876584 @default.
• W2997421813 creator A5076197979 @default.
• W2997421813 creator A5081115024 @default.
• W2997421813 creator A5090180766 @default.
• W2997421813 date "2020-07-01" @default.
• W2997421813 modified "2023-10-17" @default.
• W2997421813 title "Cycle-IR: Deep Cyclic Image Retargeting" @default.
• W2997421813 cites W1499162016 @default.
• W2997421813 cites W1573739146 @default.
• W2997421813 cites W1963884485 @default.
• W2997421813 cites W1972735298 @default.
• W2997421813 cites W1976391299 @default.
• W2997421813 cites W2002885083 @default.
• W2997421813 cites W2005619762 @default.
• W2997421813 cites W2018765149 @default.
• W2997421813 cites W2031489346 @default.
• W2997421813 cites W2055307271 @default.
• W2997421813 cites W2058017216 @default.
• W2997421813 cites W2070062673 @default.
• W2997421813 cites W2103450397 @default.
• W2997421813 cites W2107645769 @default.
• W2997421813 cites W2122022994 @default.
• W2997421813 cites W2127992984 @default.
• W2997421813 cites W2139144545 @default.
• W2997421813 cites W2147032275 @default.
• W2997421813 cites W2157575844 @default.
• W2997421813 cites W2166554908 @default.
• W2997421813 cites W2166828891 @default.
• W2997421813 cites W2215027725 @default.
• W2997421813 cites W2215880066 @default.
• W2997421813 cites W2219125737 @default.
• W2997421813 cites W2235636382 @default.
• W2997421813 cites W2293332611 @default.
• W2997421813 cites W2474531669 @default.
• W2997421813 cites W2505967260 @default.
• W2997421813 cites W2520707372 @default.
• W2997421813 cites W2581756885 @default.
• W2997421813 cites W2596178522 @default.
• W2997421813 cites W2725229849 @default.
• W2997421813 cites W2748252044 @default.
• W2997421813 cites W2772783599 @default.
• W2997421813 cites W2894234546 @default.
• W2997421813 cites W2904829482 @default.
• W2997421813 cites W2962717160 @default.
• W2997421813 cites W2963083275 @default.
• W2997421813 cites W3136413417 @default.
• W2997421813 cites W3137241515 @default.
• W2997421813 cites W4230371388 @default.
• W2997421813 cites W4237734377 @default.
• W2997421813 cites W4241425637 @default.
• W2997421813 cites W74030613 @default.
• W2997421813 doi "https://doi.org/10.1109/tmm.2019.2959925" @default.
• W2997421813 hasPublicationYear "2020" @default.
• W2997421813 type Work @default.
• W2997421813 sameAs 2997421813 @default.
• W2997421813 citedByCount "21" @default.
• W2997421813 countsByYear W29974218132021 @default.
• W2997421813 countsByYear W29974218132022 @default.
• W2997421813 countsByYear W29974218132023 @default.
• W2997421813 crossrefType "journal-article" @default.
• W2997421813 hasAuthorship W2997421813A5017876584 @default.
• W2997421813 hasAuthorship W2997421813A5076197979 @default.
• W2997421813 hasAuthorship W2997421813A5081115024 @default.
• W2997421813 hasAuthorship W2997421813A5090180766 @default.
• W2997421813 hasBestOaLocation W29974218132 @default.
• W2997421813 hasConcept C108583219 @default.
• W2997421813 hasConcept C111919701 @default.
• W2997421813 hasConcept C115961682 @default.
• W2997421813 hasConcept C126780896 @default.
• W2997421813 hasConcept C153180895 @default.
• W2997421813 hasConcept C154945302 @default.
• W2997421813 hasConcept C194257627 @default.
• W2997421813 hasConcept C23746413 @default.
• W2997421813 hasConcept C2776257435 @default.
• W2997421813 hasConcept C2776436953 @default.
• W2997421813 hasConcept C2780575108 @default.
• W2997421813 hasConcept C31258907 @default.
• W2997421813 hasConcept C31972630 @default.
• W2997421813 hasConcept C36464697 @default.
• W2997421813 hasConcept C41008148 @default.
• W2997421813 hasConcept C98045186 @default.
• W2997421813 hasConceptScore W2997421813C108583219 @default.
• W2997421813 hasConceptScore W2997421813C111919701 @default.
• W2997421813 hasConceptScore W2997421813C115961682 @default.
• W2997421813 hasConceptScore W2997421813C126780896 @default.
• W2997421813 hasConceptScore W2997421813C153180895 @default.
• W2997421813 hasConceptScore W2997421813C154945302 @default.
• W2997421813 hasConceptScore W2997421813C194257627 @default.
• W2997421813 hasConceptScore W2997421813C23746413 @default.
• W2997421813 hasConceptScore W2997421813C2776257435 @default.
• W2997421813 hasConceptScore W2997421813C2776436953 @default.
• W2997421813 hasConceptScore W2997421813C2780575108 @default.
• W2997421813 hasConceptScore W2997421813C31258907 @default.
• W2997421813 hasConceptScore W2997421813C31972630 @default.
• W2997421813 hasConceptScore W2997421813C36464697 @default.
• W2997421813 hasConceptScore W2997421813C41008148 @default.

• next