FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3184120406> ?p ?o ?g. }

• W3184120406 endingPage "6699" @default.
• W3184120406 startingPage "6686" @default.
• W3184120406 abstract "The ability to recognize the position and order of the floor-level lines that divide adjacent building floors can benefit many applications, for example, urban augmented reality (AR). This work tackles the problem of locating floor-level lines in street-view images, using a supervised deep learning approach. Unfortunately, very little data is available for training such a network $-$ current street-view datasets contain either semantic annotations that lack geometric attributes, or rectified facades without perspective priors. To address this issue, we first compile a new dataset and develop a new data augmentation scheme to synthesize training samples by harassing (i) the rich semantics of existing rectified facades and (ii) perspective priors of buildings in diverse street views. Next, we design FloorLevel-Net, a multi-task learning network that associates explicit features of building facades and implicit floor-level lines, along with a height-attention mechanism to help enforce a vertical ordering of floor-level lines. The generated segmentations are then passed to a second-stage geometry post-processing to exploit self-constrained geometric priors for plausible and consistent reconstruction of floor-level lines. Quantitative and qualitative evaluations conducted on assorted facades in existing datasets and street views from Google demonstrate the effectiveness of our approach. Also, we present context-aware image overlay results and show the potentials of our approach in enriching AR-related applications." @default.
• W3184120406 created "2021-08-02" @default.
• W3184120406 creator A5029934565 @default.
• W3184120406 creator A5048678503 @default.
• W3184120406 creator A5054382056 @default.
• W3184120406 date "2021-01-01" @default.
• W3184120406 modified "2023-10-16" @default.
• W3184120406 title "FloorLevel-Net: Recognizing Floor-Level Lines With Height-Attention-Guided Multi-Task Learning" @default.
• W3184120406 cites W1482548926 @default.
• W3184120406 cites W1486646730 @default.
• W3184120406 cites W1592011777 @default.
• W3184120406 cites W1899309388 @default.
• W3184120406 cites W1903029394 @default.
• W3184120406 cites W1905829557 @default.
• W3184120406 cites W1978338723 @default.
• W3184120406 cites W1978993048 @default.
• W3184120406 cites W2007261304 @default.
• W3184120406 cites W2021670031 @default.
• W3184120406 cites W2039438219 @default.
• W3184120406 cites W2074154756 @default.
• W3184120406 cites W2115878665 @default.
• W3184120406 cites W2122059483 @default.
• W3184120406 cites W2125310925 @default.
• W3184120406 cites W2127310338 @default.
• W3184120406 cites W2148052781 @default.
• W3184120406 cites W2150066425 @default.
• W3184120406 cites W2156953558 @default.
• W3184120406 cites W2194775991 @default.
• W3184120406 cites W2285214964 @default.
• W3184120406 cites W2340897893 @default.
• W3184120406 cites W2560023338 @default.
• W3184120406 cites W2602359856 @default.
• W3184120406 cites W2741074234 @default.
• W3184120406 cites W2752782242 @default.
• W3184120406 cites W2753409831 @default.
• W3184120406 cites W2768591600 @default.
• W3184120406 cites W2778362064 @default.
• W3184120406 cites W2799166040 @default.
• W3184120406 cites W2799679797 @default.
• W3184120406 cites W2889493913 @default.
• W3184120406 cites W2894541208 @default.
• W3184120406 cites W2895040125 @default.
• W3184120406 cites W2895707844 @default.
• W3184120406 cites W2964309882 @default.
• W3184120406 cites W2981689412 @default.
• W3184120406 cites W3004811588 @default.
• W3184120406 cites W3017034093 @default.
• W3184120406 cites W3054755450 @default.
• W3184120406 cites W3109301572 @default.
• W3184120406 cites W4238070559 @default.
• W3184120406 cites W50236904 @default.
• W3184120406 doi "https://doi.org/10.1109/tip.2021.3096090" @default.
• W3184120406 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34310282" @default.
• W3184120406 hasPublicationYear "2021" @default.
• W3184120406 type Work @default.
• W3184120406 sameAs 3184120406 @default.
• W3184120406 citedByCount "3" @default.
• W3184120406 countsByYear W31841204062022 @default.
• W3184120406 countsByYear W31841204062023 @default.
• W3184120406 crossrefType "journal-article" @default.
• W3184120406 hasAuthorship W3184120406A5029934565 @default.
• W3184120406 hasAuthorship W3184120406A5048678503 @default.
• W3184120406 hasAuthorship W3184120406A5054382056 @default.
• W3184120406 hasBestOaLocation W31841204062 @default.
• W3184120406 hasConcept C107673813 @default.
• W3184120406 hasConcept C119857082 @default.
• W3184120406 hasConcept C12713177 @default.
• W3184120406 hasConcept C127413603 @default.
• W3184120406 hasConcept C151730666 @default.
• W3184120406 hasConcept C154945302 @default.
• W3184120406 hasConcept C165696696 @default.
• W3184120406 hasConcept C177769412 @default.
• W3184120406 hasConcept C201995342 @default.
• W3184120406 hasConcept C2779343474 @default.
• W3184120406 hasConcept C2780451532 @default.
• W3184120406 hasConcept C31972630 @default.
• W3184120406 hasConcept C38652104 @default.
• W3184120406 hasConcept C41008148 @default.
• W3184120406 hasConcept C81363708 @default.
• W3184120406 hasConcept C86803240 @default.
• W3184120406 hasConceptScore W3184120406C107673813 @default.
• W3184120406 hasConceptScore W3184120406C119857082 @default.
• W3184120406 hasConceptScore W3184120406C12713177 @default.
• W3184120406 hasConceptScore W3184120406C127413603 @default.
• W3184120406 hasConceptScore W3184120406C151730666 @default.
• W3184120406 hasConceptScore W3184120406C154945302 @default.
• W3184120406 hasConceptScore W3184120406C165696696 @default.
• W3184120406 hasConceptScore W3184120406C177769412 @default.
• W3184120406 hasConceptScore W3184120406C201995342 @default.
• W3184120406 hasConceptScore W3184120406C2779343474 @default.
• W3184120406 hasConceptScore W3184120406C2780451532 @default.
• W3184120406 hasConceptScore W3184120406C31972630 @default.
• W3184120406 hasConceptScore W3184120406C38652104 @default.
• W3184120406 hasConceptScore W3184120406C41008148 @default.
• W3184120406 hasConceptScore W3184120406C81363708 @default.
• W3184120406 hasConceptScore W3184120406C86803240 @default.
• W3184120406 hasFunder F4320321592 @default.
• W3184120406 hasFunder F4320337111 @default.

• next