FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2991531736> ?p ?o ?g. }

• W2991531736 abstract "Object co-segmentation is to segment the shared objects in multiple relevant images, which has numerous applications in computer vision. This paper presents a spatial and semantic modulated deep network framework for object co-segmentation. A backbone network is adopted to extract multi-resolution image features. With the multi-resolution features of the relevant images as input, we design a spatial modulator to learn a mask for each image. The spatial modulator captures the correlations of image feature descriptors via unsupervised learning. The learned mask can roughly localize the shared foreground object while suppressing the background. For the semantic modulator, we model it as a supervised image classification task. We propose a hierarchical second-order pooling module to transform the image features for classification use. The outputs of the two modulators manipulate the multi-resolution features by a shift-and-scale operation so that the features focus on segmenting co-object regions. The proposed model is trained end-to-end without any intricate post-processing. Extensive experiments on four image co-segmentation benchmark datasets demonstrate the superior accuracy of the proposed method compared to state-of-the-art methods." @default.
• W2991531736 created "2019-12-05" @default.
• W2991531736 creator A5054433231 @default.
• W2991531736 creator A5057353444 @default.
• W2991531736 creator A5075412755 @default.
• W2991531736 creator A5088669096 @default.
• W2991531736 date "2019-11-28" @default.
• W2991531736 modified "2023-10-17" @default.
• W2991531736 title "Deep Object Co-segmentation via Spatial-Semantic Network Modulation" @default.
• W2991531736 cites W1522301498 @default.
• W2991531736 cites W1686810756 @default.
• W2991531736 cites W1808966389 @default.
• W2991531736 cites W1923115158 @default.
• W2991531736 cites W1963920598 @default.
• W2991531736 cites W1984034752 @default.
• W2991531736 cites W1986555171 @default.
• W2991531736 cites W1996140089 @default.
• W2991531736 cites W2002754212 @default.
• W2991531736 cites W2003343330 @default.
• W2991531736 cites W2031489346 @default.
• W2991531736 cites W2099242680 @default.
• W2991531736 cites W2108598243 @default.
• W2991531736 cites W2109255472 @default.
• W2991531736 cites W2110370288 @default.
• W2991531736 cites W2118557299 @default.
• W2991531736 cites W2160812203 @default.
• W2991531736 cites W2295160225 @default.
• W2991531736 cites W2304841027 @default.
• W2991531736 cites W2415053570 @default.
• W2991531736 cites W2468480815 @default.
• W2991531736 cites W2550553598 @default.
• W2991531736 cites W2565639579 @default.
• W2991531736 cites W2604413995 @default.
• W2991531736 cites W2616689446 @default.
• W2991531736 cites W2740660291 @default.
• W2991531736 cites W2747199123 @default.
• W2991531736 cites W2750988638 @default.
• W2991531736 cites W2773771410 @default.
• W2991531736 cites W2792010009 @default.
• W2991531736 cites W2807912089 @default.
• W2991531736 cites W2885254978 @default.
• W2991531736 cites W2887361581 @default.
• W2991531736 cites W2891177538 @default.
• W2991531736 cites W2896011443 @default.
• W2991531736 cites W2904945062 @default.
• W2991531736 cites W2916798096 @default.
• W2991531736 cites W2950877941 @default.
• W2991531736 cites W2954380329 @default.
• W2991531736 cites W2962825871 @default.
• W2991531736 cites W2963150697 @default.
• W2991531736 cites W2963245493 @default.
• W2991531736 cites W2963834057 @default.
• W2991531736 cites W2963921132 @default.
• W2991531736 cites W2964028976 @default.
• W2991531736 cites W2964283970 @default.
• W2991531736 cites W2972640707 @default.
• W2991531736 cites W4554164 @default.
• W2991531736 cites W566255863 @default.
• W2991531736 cites W2519388566 @default.
• W2991531736 doi "https://doi.org/10.48550/arxiv.1911.12950" @default.
• W2991531736 hasPublicationYear "2019" @default.
• W2991531736 type Work @default.
• W2991531736 sameAs 2991531736 @default.
• W2991531736 citedByCount "0" @default.
• W2991531736 crossrefType "posted-content" @default.
• W2991531736 hasAuthorship W2991531736A5054433231 @default.
• W2991531736 hasAuthorship W2991531736A5057353444 @default.
• W2991531736 hasAuthorship W2991531736A5075412755 @default.
• W2991531736 hasAuthorship W2991531736A5088669096 @default.
• W2991531736 hasBestOaLocation W29915317361 @default.
• W2991531736 hasConcept C120665830 @default.
• W2991531736 hasConcept C121332964 @default.
• W2991531736 hasConcept C124504099 @default.
• W2991531736 hasConcept C13280743 @default.
• W2991531736 hasConcept C138885662 @default.
• W2991531736 hasConcept C153180895 @default.
• W2991531736 hasConcept C154945302 @default.
• W2991531736 hasConcept C185798385 @default.
• W2991531736 hasConcept C192209626 @default.
• W2991531736 hasConcept C205649164 @default.
• W2991531736 hasConcept C2776401178 @default.
• W2991531736 hasConcept C2781238097 @default.
• W2991531736 hasConcept C31972630 @default.
• W2991531736 hasConcept C41008148 @default.
• W2991531736 hasConcept C41895202 @default.
• W2991531736 hasConcept C70437156 @default.
• W2991531736 hasConcept C89600930 @default.
• W2991531736 hasConceptScore W2991531736C120665830 @default.
• W2991531736 hasConceptScore W2991531736C121332964 @default.
• W2991531736 hasConceptScore W2991531736C124504099 @default.
• W2991531736 hasConceptScore W2991531736C13280743 @default.
• W2991531736 hasConceptScore W2991531736C138885662 @default.
• W2991531736 hasConceptScore W2991531736C153180895 @default.
• W2991531736 hasConceptScore W2991531736C154945302 @default.
• W2991531736 hasConceptScore W2991531736C185798385 @default.
• W2991531736 hasConceptScore W2991531736C192209626 @default.
• W2991531736 hasConceptScore W2991531736C205649164 @default.
• W2991531736 hasConceptScore W2991531736C2776401178 @default.
• W2991531736 hasConceptScore W2991531736C2781238097 @default.
• W2991531736 hasConceptScore W2991531736C31972630 @default.

• next