Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313204589> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4313204589 endingPage "1142" @default.
- W4313204589 startingPage "1127" @default.
- W4313204589 abstract "This paper describes an unsupervised sequential auto-encoding model targeting multi-object scenes. The proposed model uses an attention-based formulation, with reconstruction-driven losses. The main model relies on iteratively writing regions onto a canvas, in a differentiable manner. To enforce attention to objects and/or parts, the model uses a convolutional localization network, a region level bottleneck auto-encoder and a loss term that encourages reconstruction within a limited number of iterations. An extended version of the model incorporates a background modeling component that aims at handling scenes with complex backgrounds. The model is evaluated on two separate datasets: a synthetic dataset that is constructed by composing MNIST digit instances together, and the MS-COCO dataset. The model achieves high reconstruction ability on MNIST based scenes. The extended model shows promising results on the complex and challenging MS-COCO scenes." @default.
- W4313204589 created "2023-01-06" @default.
- W4313204589 creator A5048536471 @default.
- W4313204589 creator A5051499142 @default.
- W4313204589 date "2022-12-30" @default.
- W4313204589 modified "2023-10-18" @default.
- W4313204589 title "Attentive Sequential Auto-Encoding Towards Unsupervised Object-centric Scene Modeling" @default.
- W4313204589 cites W1861492603 @default.
- W4313204589 cites W1999478155 @default.
- W4313204589 cites W2067191022 @default.
- W4313204589 cites W2097323414 @default.
- W4313204589 cites W2116046277 @default.
- W4313204589 cites W2168804568 @default.
- W4313204589 cites W2962770929 @default.
- W4313204589 cites W2990251202 @default.
- W4313204589 cites W2992005611 @default.
- W4313204589 cites W3035231706 @default.
- W4313204589 cites W3035574324 @default.
- W4313204589 cites W3167788848 @default.
- W4313204589 doi "https://doi.org/10.29109/gujsc.1139701" @default.
- W4313204589 hasPublicationYear "2022" @default.
- W4313204589 type Work @default.
- W4313204589 citedByCount "0" @default.
- W4313204589 crossrefType "journal-article" @default.
- W4313204589 hasAuthorship W4313204589A5048536471 @default.
- W4313204589 hasAuthorship W4313204589A5051499142 @default.
- W4313204589 hasBestOaLocation W43132045891 @default.
- W4313204589 hasConcept C108583219 @default.
- W4313204589 hasConcept C111919701 @default.
- W4313204589 hasConcept C11413529 @default.
- W4313204589 hasConcept C118505674 @default.
- W4313204589 hasConcept C119857082 @default.
- W4313204589 hasConcept C121332964 @default.
- W4313204589 hasConcept C125411270 @default.
- W4313204589 hasConcept C134306372 @default.
- W4313204589 hasConcept C149635348 @default.
- W4313204589 hasConcept C153180895 @default.
- W4313204589 hasConcept C154945302 @default.
- W4313204589 hasConcept C168167062 @default.
- W4313204589 hasConcept C190502265 @default.
- W4313204589 hasConcept C202615002 @default.
- W4313204589 hasConcept C2780513914 @default.
- W4313204589 hasConcept C2781238097 @default.
- W4313204589 hasConcept C31972630 @default.
- W4313204589 hasConcept C33923547 @default.
- W4313204589 hasConcept C41008148 @default.
- W4313204589 hasConcept C57273362 @default.
- W4313204589 hasConcept C81363708 @default.
- W4313204589 hasConcept C97355855 @default.
- W4313204589 hasConceptScore W4313204589C108583219 @default.
- W4313204589 hasConceptScore W4313204589C111919701 @default.
- W4313204589 hasConceptScore W4313204589C11413529 @default.
- W4313204589 hasConceptScore W4313204589C118505674 @default.
- W4313204589 hasConceptScore W4313204589C119857082 @default.
- W4313204589 hasConceptScore W4313204589C121332964 @default.
- W4313204589 hasConceptScore W4313204589C125411270 @default.
- W4313204589 hasConceptScore W4313204589C134306372 @default.
- W4313204589 hasConceptScore W4313204589C149635348 @default.
- W4313204589 hasConceptScore W4313204589C153180895 @default.
- W4313204589 hasConceptScore W4313204589C154945302 @default.
- W4313204589 hasConceptScore W4313204589C168167062 @default.
- W4313204589 hasConceptScore W4313204589C190502265 @default.
- W4313204589 hasConceptScore W4313204589C202615002 @default.
- W4313204589 hasConceptScore W4313204589C2780513914 @default.
- W4313204589 hasConceptScore W4313204589C2781238097 @default.
- W4313204589 hasConceptScore W4313204589C31972630 @default.
- W4313204589 hasConceptScore W4313204589C33923547 @default.
- W4313204589 hasConceptScore W4313204589C41008148 @default.
- W4313204589 hasConceptScore W4313204589C57273362 @default.
- W4313204589 hasConceptScore W4313204589C81363708 @default.
- W4313204589 hasConceptScore W4313204589C97355855 @default.
- W4313204589 hasFunder F4320322626 @default.
- W4313204589 hasIssue "4" @default.
- W4313204589 hasLocation W43132045891 @default.
- W4313204589 hasLocation W43132045892 @default.
- W4313204589 hasOpenAccess W4313204589 @default.
- W4313204589 hasPrimaryLocation W43132045891 @default.
- W4313204589 hasRelatedWork W2597787948 @default.
- W4313204589 hasRelatedWork W2731899572 @default.
- W4313204589 hasRelatedWork W2947175736 @default.
- W4313204589 hasRelatedWork W3133861977 @default.
- W4313204589 hasRelatedWork W3156786002 @default.
- W4313204589 hasRelatedWork W3208266890 @default.
- W4313204589 hasRelatedWork W4200173597 @default.
- W4313204589 hasRelatedWork W4309224979 @default.
- W4313204589 hasRelatedWork W4312417841 @default.
- W4313204589 hasRelatedWork W4321369474 @default.
- W4313204589 hasVolume "10" @default.
- W4313204589 isParatext "false" @default.
- W4313204589 isRetracted "false" @default.
- W4313204589 workType "article" @default.