FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4214858694> ?p ?o ?g. }

• W4214858694 endingPage "116674" @default.
• W4214858694 startingPage "116674" @default.
• W4214858694 abstract "RGB-D saliency detection aims to identify the most attractive objects in a pair of color and depth images. However, most existing models adopt classic U-Net framework which progressively decodes two-stream features. In this paper, we decode the cross-modal and multi-level features in a unified unit, named Attention Gated Recurrent Unit (AGRU). It can reduce the influence of low-quality depth image, and retain more semantic features in the progressive fusion process. Specifically, the features of different modalities and different levels are organized as the sequential input, recurrently fed into AGRU which consists of reset gate, update gate and memory unit to be selectively fused and adaptively memorized based on attention mechanism. Further, two-stage AGRU serves as the decoder of RGB-D salient object detection network, named AGRFNet. Due to the recurrent nature, it achieves the best performance with the little parameters. In order to further improve the performance, three auxiliary modules are designed to better fuse semantic information, refine the features of the shallow layer and enhance the local detail. Extensive experiments on seven widely used benchmark datasets demonstrate that AGRFNet performs favorably against 18 state-of-the-art RGB-D SOD approaches." @default.
• W4214858694 created "2022-03-05" @default.
• W4214858694 creator A5003301022 @default.
• W4214858694 creator A5017774638 @default.
• W4214858694 creator A5050469485 @default.
• W4214858694 creator A5057432797 @default.
• W4214858694 creator A5057821256 @default.
• W4214858694 date "2022-05-01" @default.
• W4214858694 modified "2023-10-01" @default.
• W4214858694 title "AGRFNet: Two-stage cross-modal and multi-level attention gated recurrent fusion network for RGB-D saliency detection" @default.
• W4214858694 cites W1966025376 @default.
• W4214858694 cites W2014328297 @default.
• W4214858694 cites W2064675550 @default.
• W4214858694 cites W2121378474 @default.
• W4214858694 cites W2157331557 @default.
• W4214858694 cites W2194775991 @default.
• W4214858694 cites W2607011617 @default.
• W4214858694 cites W2765934933 @default.
• W4214858694 cites W2767623212 @default.
• W4214858694 cites W2798857366 @default.
• W4214858694 cites W2804743778 @default.
• W4214858694 cites W2884585870 @default.
• W4214858694 cites W2898694935 @default.
• W4214858694 cites W2907643346 @default.
• W4214858694 cites W2948300571 @default.
• W4214858694 cites W2951559648 @default.
• W4214858694 cites W2957414648 @default.
• W4214858694 cites W2962159375 @default.
• W4214858694 cites W2963091558 @default.
• W4214858694 cites W2963112696 @default.
• W4214858694 cites W2963446712 @default.
• W4214858694 cites W2963529609 @default.
• W4214858694 cites W2963868681 @default.
• W4214858694 cites W2963897031 @default.
• W4214858694 cites W2964429685 @default.
• W4214858694 cites W2969377765 @default.
• W4214858694 cites W2989161706 @default.
• W4214858694 cites W2990201021 @default.
• W4214858694 cites W2990844506 @default.
• W4214858694 cites W2998449272 @default.
• W4214858694 cites W2999281281 @default.
• W4214858694 cites W3002301267 @default.
• W4214858694 cites W3006465601 @default.
• W4214858694 cites W3010616503 @default.
• W4214858694 cites W3021142045 @default.
• W4214858694 cites W3021737479 @default.
• W4214858694 cites W3031719679 @default.
• W4214858694 cites W3034310225 @default.
• W4214858694 cites W3034320133 @default.
• W4214858694 cites W3035284915 @default.
• W4214858694 cites W3035357085 @default.
• W4214858694 cites W3035460038 @default.
• W4214858694 cites W3035633116 @default.
• W4214858694 cites W3035687312 @default.
• W4214858694 cites W3048216881 @default.
• W4214858694 cites W3049194477 @default.
• W4214858694 cites W3085908110 @default.
• W4214858694 cites W3087912695 @default.
• W4214858694 cites W3092729213 @default.
• W4214858694 cites W3092974849 @default.
• W4214858694 cites W3093213431 @default.
• W4214858694 cites W3093360435 @default.
• W4214858694 cites W3094802760 @default.
• W4214858694 cites W3095831308 @default.
• W4214858694 cites W3097336090 @default.
• W4214858694 cites W3101066727 @default.
• W4214858694 cites W3101839051 @default.
• W4214858694 cites W3104979525 @default.
• W4214858694 cites W3106587394 @default.
• W4214858694 cites W3108948422 @default.
• W4214858694 cites W3109067620 @default.
• W4214858694 cites W3109196171 @default.
• W4214858694 cites W3118710621 @default.
• W4214858694 cites W3119667975 @default.
• W4214858694 cites W3120113457 @default.
• W4214858694 cites W3121523901 @default.
• W4214858694 cites W3126725132 @default.
• W4214858694 cites W3131182250 @default.
• W4214858694 cites W3134912427 @default.
• W4214858694 cites W3155677196 @default.
• W4214858694 cites W3173882198 @default.
• W4214858694 cites W3177040887 @default.
• W4214858694 cites W3203040502 @default.
• W4214858694 cites W3204197760 @default.
• W4214858694 cites W4214561053 @default.
• W4214858694 cites W4214696292 @default.
• W4214858694 doi "https://doi.org/10.1016/j.image.2022.116674" @default.
• W4214858694 hasPublicationYear "2022" @default.
• W4214858694 type Work @default.
• W4214858694 citedByCount "1" @default.
• W4214858694 countsByYear W42148586942023 @default.
• W4214858694 crossrefType "journal-article" @default.
• W4214858694 hasAuthorship W4214858694A5003301022 @default.
• W4214858694 hasAuthorship W4214858694A5017774638 @default.
• W4214858694 hasAuthorship W4214858694A5050469485 @default.
• W4214858694 hasAuthorship W4214858694A5057432797 @default.
• W4214858694 hasAuthorship W4214858694A5057821256 @default.
• W4214858694 hasConcept C111919701 @default.

• next