Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381610130> ?p ?o ?g. }
- W4381610130 abstract "Abstract Recently proposed state-of-the-art saliency detection models rely heavily on labeled datasets and rarely focus on perfect RGBD feature fusion, which lowers their generalization ability. In this paper, we propose a depth-based interaction and refinement network (DIR-Net) to fully leverage the depth information provided with RGB images to generate and refine the corresponding saliency segmentation maps. In total, three modules are included in our framework. A depth-based refinement module (DRM) and an RGB module work in parallel while coordinating via interactive spatial guidance modules (ISGMs), which utilize spatial and channel attention computed from both depth features and RGB features. In each layer, the features in both modules are refined and guided by the spatial information obtained from the other module through ISGMs. In the RGB module, before sending the depth-guided feature map to the decoder, a convolutional gated recurrent unit (ConvGRU)-based block is introduced to handle temporal information. Thinking about the clear movement information in RGB features, the block also guides temporal information in DRM. By merging the results from both the DRM and RGB modules, a segmentation map with distinct boundaries is generated. Considering the lack of depth images in popular public datasets, we utilize a depth estimation network that incorporates manual postprocessing-based correction to generate depth images on the DAVIS and UVSD datasets. The state-of-the-art performance achieved on both the original and new datasets illustrates the advantage of our RGBD feature fusion strategy, with a real-time speed of 19 fps on a single GPU." @default.
- W4381610130 created "2023-06-23" @default.
- W4381610130 creator A5016855891 @default.
- W4381610130 creator A5028972131 @default.
- W4381610130 creator A5050336733 @default.
- W4381610130 creator A5055151897 @default.
- W4381610130 date "2023-05-06" @default.
- W4381610130 modified "2023-09-25" @default.
- W4381610130 title "Salient object detection for RGBD video via spatial interaction and depth-based boundary refinement" @default.
- W4381610130 cites W1498386302 @default.
- W4381610130 cites W1536680647 @default.
- W4381610130 cites W1605517717 @default.
- W4381610130 cites W1894057436 @default.
- W4381610130 cites W1901129140 @default.
- W4381610130 cites W1903029394 @default.
- W4381610130 cites W1920234547 @default.
- W4381610130 cites W1942214758 @default.
- W4381610130 cites W1986670485 @default.
- W4381610130 cites W1996326832 @default.
- W4381610130 cites W1999776728 @default.
- W4381610130 cites W2007817642 @default.
- W4381610130 cites W2052635379 @default.
- W4381610130 cites W2055180303 @default.
- W4381610130 cites W2063093722 @default.
- W4381610130 cites W2080142539 @default.
- W4381610130 cites W2110019070 @default.
- W4381610130 cites W2118985252 @default.
- W4381610130 cites W2128272608 @default.
- W4381610130 cites W2146103513 @default.
- W4381610130 cites W2158535435 @default.
- W4381610130 cites W2166650627 @default.
- W4381610130 cites W2170632605 @default.
- W4381610130 cites W2293332611 @default.
- W4381610130 cites W2338972621 @default.
- W4381610130 cites W2470139095 @default.
- W4381610130 cites W2501148868 @default.
- W4381610130 cites W2547489168 @default.
- W4381610130 cites W2585592883 @default.
- W4381610130 cites W2757028014 @default.
- W4381610130 cites W2765103010 @default.
- W4381610130 cites W2770201307 @default.
- W4381610130 cites W2797761794 @default.
- W4381610130 cites W2884585870 @default.
- W4381610130 cites W2895340898 @default.
- W4381610130 cites W2948300571 @default.
- W4381610130 cites W2962965915 @default.
- W4381610130 cites W2963868681 @default.
- W4381610130 cites W2964121744 @default.
- W4381610130 cites W2965638232 @default.
- W4381610130 cites W2980454593 @default.
- W4381610130 cites W2984144959 @default.
- W4381610130 cites W2985775862 @default.
- W4381610130 cites W2986131415 @default.
- W4381610130 cites W3035357085 @default.
- W4381610130 cites W3035687312 @default.
- W4381610130 cites W3099871687 @default.
- W4381610130 cites W3108812909 @default.
- W4381610130 cites W3125055566 @default.
- W4381610130 cites W3173882198 @default.
- W4381610130 cites W4213438864 @default.
- W4381610130 cites W639708223 @default.
- W4381610130 doi "https://doi.org/10.1007/s40747-023-01072-w" @default.
- W4381610130 hasPublicationYear "2023" @default.
- W4381610130 type Work @default.
- W4381610130 citedByCount "0" @default.
- W4381610130 crossrefType "journal-article" @default.
- W4381610130 hasAuthorship W4381610130A5016855891 @default.
- W4381610130 hasAuthorship W4381610130A5028972131 @default.
- W4381610130 hasAuthorship W4381610130A5050336733 @default.
- W4381610130 hasAuthorship W4381610130A5055151897 @default.
- W4381610130 hasBestOaLocation W43816101301 @default.
- W4381610130 hasConcept C115961682 @default.
- W4381610130 hasConcept C120665830 @default.
- W4381610130 hasConcept C121332964 @default.
- W4381610130 hasConcept C138885662 @default.
- W4381610130 hasConcept C141268832 @default.
- W4381610130 hasConcept C153083717 @default.
- W4381610130 hasConcept C153180895 @default.
- W4381610130 hasConcept C154945302 @default.
- W4381610130 hasConcept C192209626 @default.
- W4381610130 hasConcept C2524010 @default.
- W4381610130 hasConcept C2776401178 @default.
- W4381610130 hasConcept C2777210771 @default.
- W4381610130 hasConcept C31972630 @default.
- W4381610130 hasConcept C33923547 @default.
- W4381610130 hasConcept C41008148 @default.
- W4381610130 hasConcept C41895202 @default.
- W4381610130 hasConcept C81363708 @default.
- W4381610130 hasConcept C82990744 @default.
- W4381610130 hasConcept C89600930 @default.
- W4381610130 hasConceptScore W4381610130C115961682 @default.
- W4381610130 hasConceptScore W4381610130C120665830 @default.
- W4381610130 hasConceptScore W4381610130C121332964 @default.
- W4381610130 hasConceptScore W4381610130C138885662 @default.
- W4381610130 hasConceptScore W4381610130C141268832 @default.
- W4381610130 hasConceptScore W4381610130C153083717 @default.
- W4381610130 hasConceptScore W4381610130C153180895 @default.
- W4381610130 hasConceptScore W4381610130C154945302 @default.
- W4381610130 hasConceptScore W4381610130C192209626 @default.
- W4381610130 hasConceptScore W4381610130C2524010 @default.