Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308239176> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4308239176 endingPage "22" @default.
- W4308239176 startingPage "1" @default.
- W4308239176 abstract "Mirrors are everywhere in our daily lives. Existing computer vision systems do not consider mirrors, and hence may get confused by the reflected content inside a mirror, resulting in a severe performance degradation. However, separating the real content outside a mirror from the reflected content inside it is non-trivial. The key challenge is that mirrors typically reflect contents similar to their surroundings, making it very difficult to differentiate the two. In this article, we present a novel method to segment mirrors from a single RGB image. To the best of our knowledge, this is the first work to address the mirror segmentation problem with a computational approach. We make the following contributions: First, we propose a novel network, called MirrorNet+, for mirror segmentation, by modeling both contextual contrasts and semantic associations. Second, we construct the first large-scale mirror segmentation dataset, which consists of 4,018 pairs of images containing mirrors and their corresponding manually annotated mirror masks, covering a variety of daily-life scenes. Third, we conduct extensive experiments to evaluate the proposed method and show that it outperforms the related state-of-the-art detection and segmentation methods. Fourth, we further validate the effectiveness and generalization capability of the proposed semantic awareness contextual contrasted feature learning by applying MirrorNet+ to other vision tasks, i.e., salient object detection and shadow detection. Finally, we provide some applications of mirror segmentation and analyze possible future research directions. Project homepage: https://mhaiyang.github.io/TOMM2022-MirrorNet+/index.html ." @default.
- W4308239176 created "2022-11-09" @default.
- W4308239176 creator A5003257736 @default.
- W4308239176 creator A5003642180 @default.
- W4308239176 creator A5006197413 @default.
- W4308239176 creator A5015584516 @default.
- W4308239176 creator A5025567094 @default.
- W4308239176 creator A5032626016 @default.
- W4308239176 creator A5068792201 @default.
- W4308239176 date "2023-02-17" @default.
- W4308239176 modified "2023-10-17" @default.
- W4308239176 title "Mirror Segmentation via Semantic-aware Contextual Contrasted Feature Learning" @default.
- W4308239176 cites W2412782625 @default.
- W4308239176 cites W2914107945 @default.
- W4308239176 cites W2963881378 @default.
- W4308239176 cites W3014304846 @default.
- W4308239176 cites W3048630682 @default.
- W4308239176 cites W3149210910 @default.
- W4308239176 cites W3183652235 @default.
- W4308239176 cites W3185105934 @default.
- W4308239176 cites W3210097264 @default.
- W4308239176 cites W3213100861 @default.
- W4308239176 cites W3214262346 @default.
- W4308239176 cites W3214999242 @default.
- W4308239176 cites W4214931354 @default.
- W4308239176 cites W4226494801 @default.
- W4308239176 cites W4239147634 @default.
- W4308239176 cites W4282922170 @default.
- W4308239176 doi "https://doi.org/10.1145/3566127" @default.
- W4308239176 hasPublicationYear "2023" @default.
- W4308239176 type Work @default.
- W4308239176 citedByCount "1" @default.
- W4308239176 countsByYear W43082391762023 @default.
- W4308239176 crossrefType "journal-article" @default.
- W4308239176 hasAuthorship W4308239176A5003257736 @default.
- W4308239176 hasAuthorship W4308239176A5003642180 @default.
- W4308239176 hasAuthorship W4308239176A5006197413 @default.
- W4308239176 hasAuthorship W4308239176A5015584516 @default.
- W4308239176 hasAuthorship W4308239176A5025567094 @default.
- W4308239176 hasAuthorship W4308239176A5032626016 @default.
- W4308239176 hasAuthorship W4308239176A5068792201 @default.
- W4308239176 hasConcept C117797892 @default.
- W4308239176 hasConcept C134306372 @default.
- W4308239176 hasConcept C138885662 @default.
- W4308239176 hasConcept C153180895 @default.
- W4308239176 hasConcept C154945302 @default.
- W4308239176 hasConcept C15744967 @default.
- W4308239176 hasConcept C177148314 @default.
- W4308239176 hasConcept C199360897 @default.
- W4308239176 hasConcept C2776401178 @default.
- W4308239176 hasConcept C2780719617 @default.
- W4308239176 hasConcept C2780801425 @default.
- W4308239176 hasConcept C31972630 @default.
- W4308239176 hasConcept C33923547 @default.
- W4308239176 hasConcept C41008148 @default.
- W4308239176 hasConcept C41895202 @default.
- W4308239176 hasConcept C542102704 @default.
- W4308239176 hasConcept C89600930 @default.
- W4308239176 hasConceptScore W4308239176C117797892 @default.
- W4308239176 hasConceptScore W4308239176C134306372 @default.
- W4308239176 hasConceptScore W4308239176C138885662 @default.
- W4308239176 hasConceptScore W4308239176C153180895 @default.
- W4308239176 hasConceptScore W4308239176C154945302 @default.
- W4308239176 hasConceptScore W4308239176C15744967 @default.
- W4308239176 hasConceptScore W4308239176C177148314 @default.
- W4308239176 hasConceptScore W4308239176C199360897 @default.
- W4308239176 hasConceptScore W4308239176C2776401178 @default.
- W4308239176 hasConceptScore W4308239176C2780719617 @default.
- W4308239176 hasConceptScore W4308239176C2780801425 @default.
- W4308239176 hasConceptScore W4308239176C31972630 @default.
- W4308239176 hasConceptScore W4308239176C33923547 @default.
- W4308239176 hasConceptScore W4308239176C41008148 @default.
- W4308239176 hasConceptScore W4308239176C41895202 @default.
- W4308239176 hasConceptScore W4308239176C542102704 @default.
- W4308239176 hasConceptScore W4308239176C89600930 @default.
- W4308239176 hasFunder F4320321001 @default.
- W4308239176 hasIssue "2s" @default.
- W4308239176 hasLocation W43082391761 @default.
- W4308239176 hasOpenAccess W4308239176 @default.
- W4308239176 hasPrimaryLocation W43082391761 @default.
- W4308239176 hasRelatedWork W1669643531 @default.
- W4308239176 hasRelatedWork W2005437358 @default.
- W4308239176 hasRelatedWork W2008656436 @default.
- W4308239176 hasRelatedWork W2023558673 @default.
- W4308239176 hasRelatedWork W2041408572 @default.
- W4308239176 hasRelatedWork W2134924024 @default.
- W4308239176 hasRelatedWork W2317337758 @default.
- W4308239176 hasRelatedWork W2517104666 @default.
- W4308239176 hasRelatedWork W3014708372 @default.
- W4308239176 hasRelatedWork W3177406559 @default.
- W4308239176 hasVolume "19" @default.
- W4308239176 isParatext "false" @default.
- W4308239176 isRetracted "false" @default.
- W4308239176 workType "article" @default.