Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383172033> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4383172033 abstract "In this paper, we present a simple and efficient scheme for segmenting approximately convex 3D object instances in depth images in a few-shot setting via discriminatively modeling the 3D shape of the object using a neural network. Our key idea is to select pairs of 3D points on the depth image between which we compute surface geodesics. As the number of such geodesics is quadratic in the number of image pixels, we can create a large training set of geodesics using only very limited ground truth instance annotations. These annotations are used to create a binary label for each geodesic, which indicates whether or not that geodesic belongs entirely to one instance segment. A neural network is then trained to classify the geodesics using these labels. During inference, we create geodesics from selected seed points in the test depth image, then produce a convex hull of the points that are classified by the neural network as belonging to the same instance, thereby achieving instance segmentation. We present experiments applying our method to segmenting instances of food items in real-world depth images. Our results demonstrate promising performances compared to prior methods in accuracy and computational efficiency." @default.
- W4383172033 created "2023-07-05" @default.
- W4383172033 creator A5001768904 @default.
- W4383172033 creator A5008369672 @default.
- W4383172033 creator A5024613828 @default.
- W4383172033 creator A5062291876 @default.
- W4383172033 date "2023-05-29" @default.
- W4383172033 modified "2023-10-17" @default.
- W4383172033 title "Discriminative 3D Shape Modeling for Few-Shot Instance Segmentation" @default.
- W4383172033 cites W1970531977 @default.
- W4383172033 cites W1999478155 @default.
- W4383172033 cites W2012223818 @default.
- W4383172033 cites W2041642242 @default.
- W4383172033 cites W2061247098 @default.
- W4383172033 cites W2118246710 @default.
- W4383172033 cites W2124260943 @default.
- W4383172033 cites W2128356031 @default.
- W4383172033 cites W2148875485 @default.
- W4383172033 cites W2153504150 @default.
- W4383172033 cites W2557889580 @default.
- W4383172033 cites W2869807091 @default.
- W4383172033 cites W2899271120 @default.
- W4383172033 cites W2963150697 @default.
- W4383172033 cites W2963857746 @default.
- W4383172033 cites W2966885779 @default.
- W4383172033 cites W2974200462 @default.
- W4383172033 cites W3003215308 @default.
- W4383172033 cites W3003477985 @default.
- W4383172033 cites W3008173354 @default.
- W4383172033 cites W3011018694 @default.
- W4383172033 cites W3100901148 @default.
- W4383172033 cites W3103544346 @default.
- W4383172033 cites W3173355903 @default.
- W4383172033 cites W3197450291 @default.
- W4383172033 cites W4210922806 @default.
- W4383172033 cites W4212803998 @default.
- W4383172033 cites W4221166018 @default.
- W4383172033 cites W4312580994 @default.
- W4383172033 doi "https://doi.org/10.1109/icra48891.2023.10160644" @default.
- W4383172033 hasPublicationYear "2023" @default.
- W4383172033 type Work @default.
- W4383172033 citedByCount "0" @default.
- W4383172033 crossrefType "proceedings-article" @default.
- W4383172033 hasAuthorship W4383172033A5001768904 @default.
- W4383172033 hasAuthorship W4383172033A5008369672 @default.
- W4383172033 hasAuthorship W4383172033A5024613828 @default.
- W4383172033 hasAuthorship W4383172033A5062291876 @default.
- W4383172033 hasConcept C112680207 @default.
- W4383172033 hasConcept C124504099 @default.
- W4383172033 hasConcept C134306372 @default.
- W4383172033 hasConcept C153180895 @default.
- W4383172033 hasConcept C154945302 @default.
- W4383172033 hasConcept C165818556 @default.
- W4383172033 hasConcept C206194317 @default.
- W4383172033 hasConcept C2524010 @default.
- W4383172033 hasConcept C2776214188 @default.
- W4383172033 hasConcept C2781238097 @default.
- W4383172033 hasConcept C31972630 @default.
- W4383172033 hasConcept C33923547 @default.
- W4383172033 hasConcept C41008148 @default.
- W4383172033 hasConcept C50644808 @default.
- W4383172033 hasConcept C89600930 @default.
- W4383172033 hasConcept C97931131 @default.
- W4383172033 hasConceptScore W4383172033C112680207 @default.
- W4383172033 hasConceptScore W4383172033C124504099 @default.
- W4383172033 hasConceptScore W4383172033C134306372 @default.
- W4383172033 hasConceptScore W4383172033C153180895 @default.
- W4383172033 hasConceptScore W4383172033C154945302 @default.
- W4383172033 hasConceptScore W4383172033C165818556 @default.
- W4383172033 hasConceptScore W4383172033C206194317 @default.
- W4383172033 hasConceptScore W4383172033C2524010 @default.
- W4383172033 hasConceptScore W4383172033C2776214188 @default.
- W4383172033 hasConceptScore W4383172033C2781238097 @default.
- W4383172033 hasConceptScore W4383172033C31972630 @default.
- W4383172033 hasConceptScore W4383172033C33923547 @default.
- W4383172033 hasConceptScore W4383172033C41008148 @default.
- W4383172033 hasConceptScore W4383172033C50644808 @default.
- W4383172033 hasConceptScore W4383172033C89600930 @default.
- W4383172033 hasConceptScore W4383172033C97931131 @default.
- W4383172033 hasLocation W43831720331 @default.
- W4383172033 hasOpenAccess W4383172033 @default.
- W4383172033 hasPrimaryLocation W43831720331 @default.
- W4383172033 hasRelatedWork W1669643531 @default.
- W4383172033 hasRelatedWork W1963494852 @default.
- W4383172033 hasRelatedWork W2004370856 @default.
- W4383172033 hasRelatedWork W2019566805 @default.
- W4383172033 hasRelatedWork W2026019026 @default.
- W4383172033 hasRelatedWork W2122581818 @default.
- W4383172033 hasRelatedWork W2159066190 @default.
- W4383172033 hasRelatedWork W2383464976 @default.
- W4383172033 hasRelatedWork W2510758617 @default.
- W4383172033 hasRelatedWork W1967061043 @default.
- W4383172033 isParatext "false" @default.
- W4383172033 isRetracted "false" @default.
- W4383172033 workType "article" @default.