Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313886688> ?p ?o ?g. }
- W4313886688 endingPage "16" @default.
- W4313886688 startingPage "1" @default.
- W4313886688 abstract "Compared with current RGB or RGB-D saliency detection datasets, those for light field saliency detection often suffer from many defects, e.g., insufficient data amount and diversity, incomplete data formats, and rough annotations, thus impeding the prosperity of this field. To settle these issues, we elaborately build a large-scale light field dataset, dubbed PKU-LF, comprising 5,000 light fields and covering diverse indoor and outdoor scenes. Our PKU-LF provides all-inclusive representation formats of light fields and offers a unified platform for comparing algorithms utilizing different input formats. For sparking new vitality in saliency detection tasks, we present many unexplored scenarios (such as underwater and high-resolution scenes) and the richest annotations (such as scribble annotations, bounding boxes, object-/instance-level annotations, and edge annotations), on which many potential attention modeling tasks can be investigated. To facilitate the development of saliency detection, we systematically evaluate and analyze 16 representative 2D, 3D, and 4D methods on four existing datasets and the proposed dataset, furnishing a thorough benchmark. Furthermore, tailored to the distinct structural characteristics of light fields, a novel symmetric two-stream architecture (STSA) network is proposed to predict the saliency of light fields more accurately. Specifically, our STSA incorporates a focalness interweavement module (FIM) and three partial decoder modules (PDM). The former is designed to efficiently establish long-range dependencies across focal slices, while the latter aims to effectively aggregate the extracted coadjutant features in a mutual-enhancement way. Extensive experiments demonstrate that our method can significantly outperform the competitors." @default.
- W4313886688 created "2023-01-10" @default.
- W4313886688 creator A5002485153 @default.
- W4313886688 creator A5050309466 @default.
- W4313886688 creator A5053275663 @default.
- W4313886688 creator A5057436575 @default.
- W4313886688 date "2023-01-01" @default.
- W4313886688 modified "2023-10-17" @default.
- W4313886688 title "A Thorough Benchmark and a New Model for Light Field Saliency Detection" @default.
- W4313886688 cites W1920234547 @default.
- W4313886688 cites W1942214758 @default.
- W4313886688 cites W1948751323 @default.
- W4313886688 cites W1966025376 @default.
- W4313886688 cites W1976754232 @default.
- W4313886688 cites W1982075130 @default.
- W4313886688 cites W1994922096 @default.
- W4313886688 cites W2000946514 @default.
- W4313886688 cites W2020523103 @default.
- W4313886688 cites W2031342017 @default.
- W4313886688 cites W20683899 @default.
- W4313886688 cites W2086791339 @default.
- W4313886688 cites W2100470808 @default.
- W4313886688 cites W21025885 @default.
- W4313886688 cites W2116724443 @default.
- W4313886688 cites W2128268941 @default.
- W4313886688 cites W2128272608 @default.
- W4313886688 cites W2128340050 @default.
- W4313886688 cites W2161185676 @default.
- W4313886688 cites W2194775991 @default.
- W4313886688 cites W2519882742 @default.
- W4313886688 cites W2565639579 @default.
- W4313886688 cites W2569272946 @default.
- W4313886688 cites W2620998106 @default.
- W4313886688 cites W2740667773 @default.
- W4313886688 cites W2741745116 @default.
- W4313886688 cites W2798791651 @default.
- W4313886688 cites W2798857366 @default.
- W4313886688 cites W2808442315 @default.
- W4313886688 cites W2887522866 @default.
- W4313886688 cites W2909381593 @default.
- W4313886688 cites W2913602965 @default.
- W4313886688 cites W2921653116 @default.
- W4313886688 cites W2939217524 @default.
- W4313886688 cites W2957414648 @default.
- W4313886688 cites W2962741298 @default.
- W4313886688 cites W2962954185 @default.
- W4313886688 cites W2963032190 @default.
- W4313886688 cites W2963091558 @default.
- W4313886688 cites W2963112696 @default.
- W4313886688 cites W2963529609 @default.
- W4313886688 cites W2963572583 @default.
- W4313886688 cites W2963604034 @default.
- W4313886688 cites W2963685207 @default.
- W4313886688 cites W2963868681 @default.
- W4313886688 cites W2965985103 @default.
- W4313886688 cites W2979794168 @default.
- W4313886688 cites W2982331121 @default.
- W4313886688 cites W2984615777 @default.
- W4313886688 cites W2997089731 @default.
- W4313886688 cites W2997316506 @default.
- W4313886688 cites W3002301267 @default.
- W4313886688 cites W3004780254 @default.
- W4313886688 cites W3021737479 @default.
- W4313886688 cites W3034320133 @default.
- W4313886688 cites W3035422681 @default.
- W4313886688 cites W3035687312 @default.
- W4313886688 cites W3040304705 @default.
- W4313886688 cites W3093360435 @default.
- W4313886688 cites W3097725659 @default.
- W4313886688 cites W3108608656 @default.
- W4313886688 cites W3108822985 @default.
- W4313886688 cites W3131552587 @default.
- W4313886688 cites W3164098653 @default.
- W4313886688 cites W3164802490 @default.
- W4313886688 cites W3193915232 @default.
- W4313886688 cites W4212906384 @default.
- W4313886688 cites W4239147634 @default.
- W4313886688 doi "https://doi.org/10.1109/tpami.2023.3235415" @default.
- W4313886688 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37276121" @default.
- W4313886688 hasPublicationYear "2023" @default.
- W4313886688 type Work @default.
- W4313886688 citedByCount "2" @default.
- W4313886688 countsByYear W43138866882023 @default.
- W4313886688 crossrefType "journal-article" @default.
- W4313886688 hasAuthorship W4313886688A5002485153 @default.
- W4313886688 hasAuthorship W4313886688A5050309466 @default.
- W4313886688 hasAuthorship W4313886688A5053275663 @default.
- W4313886688 hasAuthorship W4313886688A5057436575 @default.
- W4313886688 hasConcept C115961682 @default.
- W4313886688 hasConcept C13280743 @default.
- W4313886688 hasConcept C147037132 @default.
- W4313886688 hasConcept C153180895 @default.
- W4313886688 hasConcept C154945302 @default.
- W4313886688 hasConcept C17744445 @default.
- W4313886688 hasConcept C185798385 @default.
- W4313886688 hasConcept C199539241 @default.
- W4313886688 hasConcept C202444582 @default.
- W4313886688 hasConcept C205649164 @default.