FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2000946514> ?p ?o ?g. }

• W2000946514 abstract "Depth information has been shown to affect identification of visually salient regions in images. In this paper, we investigate the role of depth in saliency detection in the presence of (i) competing saliencies due to appearance, (ii) depth-induced blur and (iii) centre-bias. Having established through experiments that depth continues to be a significant contributor to saliency in the presence of these cues, we propose a 3D-saliency formulation that takes into account structural features of objects in an indoor setting to identify regions at salient depth levels. Computed 3D-saliency is used in conjunction with 2D-saliency models through non-linear regression using SVM to improve saliency maps. Experiments on benchmark datasets containing depth information show that the proposed fusion of 3D-saliency with 2D-saliency models results in an average improvement in ROC scores of about 9% over state-of-the-art 2D saliency models. The main contributions of this paper are: (i) The development of a 3D-saliency model that integrates depth and geometric features of object surfaces in indoor scenes. (ii) Fusion of appearance (RGB) saliency with depth saliency through non-linear regression using SVM. (iii) Experiments to support the hypothesis that depth improves saliency detection in the presence of blur and centre-bias. The effectiveness of the 3D-saliency model and its fusion with RGB-saliency is illustrated through experiments on two benchmark datasets that contain depth information. Current stateof-the-art saliency detection algorithms perform poorly on these datasets that depict indoor scenes due to the presence of competing saliencies in the form of color contrast. For example in Fig. 1, saliency maps of [1] is shown for different scenes, along with its human eye fixations and our proposed saliency map after fusion. It is seen from the first scene of Fig. 1, that illumination plays spoiler role in RGB-saliency map. In second scene of Fig. 1, the RGB-saliency is focused on the cap though multiple salient objects are present in the scene. Last scene at the bottom of Fig. 1, shows the limitation of the RGB-saliency when the object is similar in appearance with the background. Effect of depth on Saliency: In [4], it is shown that depth is an important cue for saliency. In this paper we go further and verify if the depth alone influences the saliency. Different scenes were captured for experimentation using Kinect sensor. Observations resulted out of these experiments are (i) Humans fixate on the objects at closer depth, in the presence of visually competing salient objects in the background, (ii) Early attention happens on the objects at closer depth, (iii) Effective fixations are high at the low contrast foreground compared to the high contrast objects in the background which are blurred, (iv) Low contrast object placed at the center of the field of view, gets more attention compared to other locations. As a result of all these observations, we develop a 3D-saliency that captures the depth information of the regions in the scene. 3D-Saliency: We adapt the region based contrast method from Cheng et al. [1] in computing contrast strengths for the segmented 3D surfaces or regions. Each segmented region is assigned a contrast score using surface normals as the feature. Structure of the surface can be described based on the distribution of normals in the region. We compute a histogram of angular distances formed by every pair of normals in the region. Every region Rk is associated with a histogram Hk. Contrast score Ck of a region Rk is computed as the sum of the dot products of its histogram with histograms of other regions in the scene. Since the depth of the region is influencing the visual attention, the contrast score is scaled by a value Zk, which is the depth of the region Rk from the sensor. In order to define the saliency, sizes of the regions i.e. the number of the points in the region, have to be considered. We find the ratio of the region dimension to the half of the scene dimension. Considering nk as the number of 3D points in the region Rk, the constrast score becomes Figure 1: Four different scenes and their saliency maps; For each scene from top left (i) Original Image, (ii) RGB-Saliency map using RC [1], (iii) Human fixations from eye-tracker and (iv) Fused RGBD-saliency map" @default.
• W2000946514 created "2016-06-24" @default.
• W2000946514 creator A5009372982 @default.
• W2000946514 creator A5015413484 @default.
• W2000946514 creator A5052038649 @default.
• W2000946514 creator A5053387862 @default.
• W2000946514 date "2013-01-01" @default.
• W2000946514 modified "2023-10-13" @default.
• W2000946514 title "Depth really Matters: Improving Visual Salient Region Detection with Depth" @default.
• W2000946514 cites W1497443722 @default.
• W2000946514 cites W1993713494 @default.
• W2000946514 cites W2018762251 @default.
• W2000946514 cites W2037954058 @default.
• W2000946514 cites W2051647827 @default.
• W2000946514 cites W2074044156 @default.
• W2000946514 cites W2093334045 @default.
• W2000946514 cites W2097295641 @default.
• W2000946514 cites W2098883970 @default.
• W2000946514 cites W2100470808 @default.
• W2000946514 cites W2124321291 @default.
• W2000946514 cites W2132734311 @default.
• W2000946514 cites W2146103513 @default.
• W2000946514 cites W2147339212 @default.
• W2000946514 cites W2152233525 @default.
• W2000946514 cites W2152864241 @default.
• W2000946514 cites W2153635508 @default.
• W2000946514 cites W2156222070 @default.
• W2000946514 cites W2164084182 @default.
• W2000946514 cites W2213271652 @default.
• W2000946514 cites W2750339080 @default.
• W2000946514 cites W3210232381 @default.
• W2000946514 cites W79820356 @default.
• W2000946514 doi "https://doi.org/10.5244/c.27.98" @default.
• W2000946514 hasPublicationYear "2013" @default.
• W2000946514 type Work @default.
• W2000946514 sameAs 2000946514 @default.
• W2000946514 citedByCount "124" @default.
• W2000946514 countsByYear W20009465142014 @default.
• W2000946514 countsByYear W20009465142015 @default.
• W2000946514 countsByYear W20009465142016 @default.
• W2000946514 countsByYear W20009465142017 @default.
• W2000946514 countsByYear W20009465142018 @default.
• W2000946514 countsByYear W20009465142019 @default.
• W2000946514 countsByYear W20009465142020 @default.
• W2000946514 countsByYear W20009465142021 @default.
• W2000946514 countsByYear W20009465142022 @default.
• W2000946514 countsByYear W20009465142023 @default.
• W2000946514 crossrefType "proceedings-article" @default.
• W2000946514 hasAuthorship W2000946514A5009372982 @default.
• W2000946514 hasAuthorship W2000946514A5015413484 @default.
• W2000946514 hasAuthorship W2000946514A5052038649 @default.
• W2000946514 hasAuthorship W2000946514A5053387862 @default.
• W2000946514 hasBestOaLocation W20009465141 @default.
• W2000946514 hasConcept C115961682 @default.
• W2000946514 hasConcept C12267149 @default.
• W2000946514 hasConcept C127313418 @default.
• W2000946514 hasConcept C13280743 @default.
• W2000946514 hasConcept C138885662 @default.
• W2000946514 hasConcept C141268832 @default.
• W2000946514 hasConcept C153180895 @default.
• W2000946514 hasConcept C154945302 @default.
• W2000946514 hasConcept C158525013 @default.
• W2000946514 hasConcept C185798385 @default.
• W2000946514 hasConcept C202227193 @default.
• W2000946514 hasConcept C2776151529 @default.
• W2000946514 hasConcept C2779679900 @default.
• W2000946514 hasConcept C2780719617 @default.
• W2000946514 hasConcept C31972630 @default.
• W2000946514 hasConcept C41008148 @default.
• W2000946514 hasConcept C41895202 @default.
• W2000946514 hasConcept C82990744 @default.
• W2000946514 hasConceptScore W2000946514C115961682 @default.
• W2000946514 hasConceptScore W2000946514C12267149 @default.
• W2000946514 hasConceptScore W2000946514C127313418 @default.
• W2000946514 hasConceptScore W2000946514C13280743 @default.
• W2000946514 hasConceptScore W2000946514C138885662 @default.
• W2000946514 hasConceptScore W2000946514C141268832 @default.
• W2000946514 hasConceptScore W2000946514C153180895 @default.
• W2000946514 hasConceptScore W2000946514C154945302 @default.
• W2000946514 hasConceptScore W2000946514C158525013 @default.
• W2000946514 hasConceptScore W2000946514C185798385 @default.
• W2000946514 hasConceptScore W2000946514C202227193 @default.
• W2000946514 hasConceptScore W2000946514C2776151529 @default.
• W2000946514 hasConceptScore W2000946514C2779679900 @default.
• W2000946514 hasConceptScore W2000946514C2780719617 @default.
• W2000946514 hasConceptScore W2000946514C31972630 @default.
• W2000946514 hasConceptScore W2000946514C41008148 @default.
• W2000946514 hasConceptScore W2000946514C41895202 @default.
• W2000946514 hasConceptScore W2000946514C82990744 @default.
• W2000946514 hasLocation W20009465141 @default.
• W2000946514 hasOpenAccess W2000946514 @default.
• W2000946514 hasPrimaryLocation W20009465141 @default.
• W2000946514 hasRelatedWork W187484614 @default.
• W2000946514 hasRelatedWork W2041073875 @default.
• W2000946514 hasRelatedWork W2053675109 @default.
• W2000946514 hasRelatedWork W2095710116 @default.
• W2000946514 hasRelatedWork W2328068029 @default.
• W2000946514 hasRelatedWork W2538748790 @default.
• W2000946514 hasRelatedWork W2580345890 @default.
• W2000946514 hasRelatedWork W2607572884 @default.

• next