FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2944699941> ?p ?o ?g. }

• W2944699941 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 input 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. In addition, our Cycle-IR outperforms the Multiop method and obtains the best result in the user study. Code is available at https://github.com/mintanwei/Cycle-IR." @default.
• W2944699941 created "2019-05-16" @default.
• W2944699941 creator A5048621299 @default.
• W2944699941 creator A5056340254 @default.
• W2944699941 creator A5076197979 @default.
• W2944699941 date "2019-05-09" @default.
• W2944699941 modified "2023-09-24" @default.
• W2944699941 title "Cycle-IR: Deep Cyclic Image Retargeting" @default.
• W2944699941 cites W1499162016 @default.
• W2944699941 cites W1573739146 @default.
• W2944699941 cites W1926639317 @default.
• W2944699941 cites W1963884485 @default.
• W2944699941 cites W1976391299 @default.
• W2944699941 cites W1985949187 @default.
• W2944699941 cites W2002885083 @default.
• W2944699941 cites W2005619762 @default.
• W2944699941 cites W2015038178 @default.
• W2944699941 cites W2018377917 @default.
• W2944699941 cites W2022164110 @default.
• W2944699941 cites W2031489346 @default.
• W2944699941 cites W2055307271 @default.
• W2944699941 cites W2058017216 @default.
• W2944699941 cites W2070062673 @default.
• W2944699941 cites W2080008265 @default.
• W2944699941 cites W2107645769 @default.
• W2944699941 cites W2122022994 @default.
• W2944699941 cites W2127992984 @default.
• W2944699941 cites W2143133882 @default.
• W2944699941 cites W2147032275 @default.
• W2944699941 cites W2155175457 @default.
• W2944699941 cites W2157575844 @default.
• W2944699941 cites W2166554908 @default.
• W2944699941 cites W2166828891 @default.
• W2944699941 cites W2215027725 @default.
• W2944699941 cites W2215880066 @default.
• W2944699941 cites W2219125737 @default.
• W2944699941 cites W2235636382 @default.
• W2944699941 cites W2293332611 @default.
• W2944699941 cites W2474531669 @default.
• W2944699941 cites W2505967260 @default.
• W2944699941 cites W2520707372 @default.
• W2944699941 cites W2581756885 @default.
• W2944699941 cites W2725229849 @default.
• W2944699941 cites W2748252044 @default.
• W2944699941 cites W2772783599 @default.
• W2944699941 cites W2894234546 @default.
• W2944699941 cites W2904829482 @default.
• W2944699941 cites W2962717160 @default.
• W2944699941 cites W2962835968 @default.
• W2944699941 cites W2963083275 @default.
• W2944699941 cites W74030613 @default.
• W2944699941 doi "https://doi.org/10.48550/arxiv.1905.03556" @default.
• W2944699941 hasPublicationYear "2019" @default.
• W2944699941 type Work @default.
• W2944699941 sameAs 2944699941 @default.
• W2944699941 citedByCount "0" @default.
• W2944699941 crossrefType "posted-content" @default.
• W2944699941 hasAuthorship W2944699941A5048621299 @default.
• W2944699941 hasAuthorship W2944699941A5056340254 @default.
• W2944699941 hasAuthorship W2944699941A5076197979 @default.
• W2944699941 hasBestOaLocation W29446999411 @default.
• W2944699941 hasConcept C108583219 @default.
• W2944699941 hasConcept C111919701 @default.
• W2944699941 hasConcept C115961682 @default.
• W2944699941 hasConcept C126780896 @default.
• W2944699941 hasConcept C153180895 @default.
• W2944699941 hasConcept C154945302 @default.
• W2944699941 hasConcept C194257627 @default.
• W2944699941 hasConcept C23746413 @default.
• W2944699941 hasConcept C2776257435 @default.
• W2944699941 hasConcept C2776436953 @default.
• W2944699941 hasConcept C2780575108 @default.
• W2944699941 hasConcept C31258907 @default.
• W2944699941 hasConcept C31972630 @default.
• W2944699941 hasConcept C36464697 @default.
• W2944699941 hasConcept C41008148 @default.
• W2944699941 hasConcept C98045186 @default.
• W2944699941 hasConceptScore W2944699941C108583219 @default.
• W2944699941 hasConceptScore W2944699941C111919701 @default.
• W2944699941 hasConceptScore W2944699941C115961682 @default.
• W2944699941 hasConceptScore W2944699941C126780896 @default.
• W2944699941 hasConceptScore W2944699941C153180895 @default.
• W2944699941 hasConceptScore W2944699941C154945302 @default.
• W2944699941 hasConceptScore W2944699941C194257627 @default.
• W2944699941 hasConceptScore W2944699941C23746413 @default.
• W2944699941 hasConceptScore W2944699941C2776257435 @default.
• W2944699941 hasConceptScore W2944699941C2776436953 @default.
• W2944699941 hasConceptScore W2944699941C2780575108 @default.
• W2944699941 hasConceptScore W2944699941C31258907 @default.
• W2944699941 hasConceptScore W2944699941C31972630 @default.
• W2944699941 hasConceptScore W2944699941C36464697 @default.
• W2944699941 hasConceptScore W2944699941C41008148 @default.
• W2944699941 hasConceptScore W2944699941C98045186 @default.
• W2944699941 hasLocation W29446999411 @default.
• W2944699941 hasLocation W29446999412 @default.
• W2944699941 hasOpenAccess W2944699941 @default.
• W2944699941 hasPrimaryLocation W29446999411 @default.
• W2944699941 hasRelatedWork W1536712399 @default.
• W2944699941 hasRelatedWork W1984802553 @default.
• W2944699941 hasRelatedWork W2004314856 @default.

• next