Matches in SemOpenAlex for { <https://semopenalex.org/work/W2321314925> ?p ?o ?g. }
- W2321314925 abstract "There is an increasing interest in exploiting multiple images for scene understanding, with great progress in areas such as cosegmentation and video segmentation. Jointly analyzing the images in a large set offers the opportunity to exploit a greater source of information than when considering a single image on its own. However, this also yields challenges since, to effectively exploit all the available information, the resulting methods need to consider not just local connections, but efficiently analyze similarity between all pairs of pixels within and across all the images. In this paper, we propose to model an image set as a fully connected pairwise Conditional Random Field (CRF) defined over the image pixels, or superpixels, with Gaussian edge potentials. We show that this lets us co-label the images of a large set efficiently, thus yielding increased accuracy at no additional computational cost compared to sequential labeling of the images. Furthermore, we extend our framework to incorporate temporal dependence, thus effectively encompassing video segmentation as a special case of our approach, as well as to modeling label dependence over larger image regions. Our experimental evaluation demonstrates that our framework lets us handle over 10 000 images in a matter of seconds." @default.
- W2321314925 created "2016-06-24" @default.
- W2321314925 creator A5020898778 @default.
- W2321314925 creator A5049300388 @default.
- W2321314925 creator A5072837153 @default.
- W2321314925 date "2016-09-01" @default.
- W2321314925 modified "2023-10-18" @default.
- W2321314925 title "Exploiting Large Image Sets for Road Scene Parsing" @default.
- W2321314925 cites W122025198 @default.
- W2321314925 cites W148361626 @default.
- W2321314925 cites W150235323 @default.
- W2321314925 cites W1536434015 @default.
- W2321314925 cites W159595522 @default.
- W2321314925 cites W1610707153 @default.
- W2321314925 cites W1913356549 @default.
- W2321314925 cites W1955404912 @default.
- W2321314925 cites W1963920598 @default.
- W2321314925 cites W1964772475 @default.
- W2321314925 cites W1964884769 @default.
- W2321314925 cites W1968731684 @default.
- W2321314925 cites W1970899458 @default.
- W2321314925 cites W1981283549 @default.
- W2321314925 cites W1989348325 @default.
- W2321314925 cites W1999478155 @default.
- W2321314925 cites W2003217181 @default.
- W2321314925 cites W2026778943 @default.
- W2321314925 cites W2030346542 @default.
- W2321314925 cites W2039747299 @default.
- W2321314925 cites W204334820 @default.
- W2321314925 cites W2050159143 @default.
- W2321314925 cites W2054279472 @default.
- W2321314925 cites W2068994826 @default.
- W2321314925 cites W2097333614 @default.
- W2321314925 cites W2100588357 @default.
- W2321314925 cites W2103846358 @default.
- W2321314925 cites W2116442155 @default.
- W2321314925 cites W2118246710 @default.
- W2321314925 cites W2125310925 @default.
- W2321314925 cites W2127893047 @default.
- W2321314925 cites W2128700566 @default.
- W2321314925 cites W2129112648 @default.
- W2321314925 cites W2129822853 @default.
- W2321314925 cites W2137881638 @default.
- W2321314925 cites W2149698896 @default.
- W2321314925 cites W2153423793 @default.
- W2321314925 cites W2157244733 @default.
- W2321314925 cites W2160461961 @default.
- W2321314925 cites W2161236525 @default.
- W2321314925 cites W2163747463 @default.
- W2321314925 cites W2171943915 @default.
- W2321314925 cites W2295160225 @default.
- W2321314925 cites W2536208356 @default.
- W2321314925 cites W33116912 @default.
- W2321314925 doi "https://doi.org/10.1109/tits.2016.2522506" @default.
- W2321314925 hasPublicationYear "2016" @default.
- W2321314925 type Work @default.
- W2321314925 sameAs 2321314925 @default.
- W2321314925 citedByCount "4" @default.
- W2321314925 countsByYear W23213149252018 @default.
- W2321314925 countsByYear W23213149252022 @default.
- W2321314925 crossrefType "journal-article" @default.
- W2321314925 hasAuthorship W2321314925A5020898778 @default.
- W2321314925 hasAuthorship W2321314925A5049300388 @default.
- W2321314925 hasAuthorship W2321314925A5072837153 @default.
- W2321314925 hasConcept C103278499 @default.
- W2321314925 hasConcept C115961682 @default.
- W2321314925 hasConcept C121332964 @default.
- W2321314925 hasConcept C124504099 @default.
- W2321314925 hasConcept C152565575 @default.
- W2321314925 hasConcept C153180895 @default.
- W2321314925 hasConcept C154945302 @default.
- W2321314925 hasConcept C160633673 @default.
- W2321314925 hasConcept C163716315 @default.
- W2321314925 hasConcept C165696696 @default.
- W2321314925 hasConcept C177264268 @default.
- W2321314925 hasConcept C184898388 @default.
- W2321314925 hasConcept C186644900 @default.
- W2321314925 hasConcept C199360897 @default.
- W2321314925 hasConcept C31972630 @default.
- W2321314925 hasConcept C38652104 @default.
- W2321314925 hasConcept C41008148 @default.
- W2321314925 hasConcept C62520636 @default.
- W2321314925 hasConcept C89600930 @default.
- W2321314925 hasConceptScore W2321314925C103278499 @default.
- W2321314925 hasConceptScore W2321314925C115961682 @default.
- W2321314925 hasConceptScore W2321314925C121332964 @default.
- W2321314925 hasConceptScore W2321314925C124504099 @default.
- W2321314925 hasConceptScore W2321314925C152565575 @default.
- W2321314925 hasConceptScore W2321314925C153180895 @default.
- W2321314925 hasConceptScore W2321314925C154945302 @default.
- W2321314925 hasConceptScore W2321314925C160633673 @default.
- W2321314925 hasConceptScore W2321314925C163716315 @default.
- W2321314925 hasConceptScore W2321314925C165696696 @default.
- W2321314925 hasConceptScore W2321314925C177264268 @default.
- W2321314925 hasConceptScore W2321314925C184898388 @default.
- W2321314925 hasConceptScore W2321314925C186644900 @default.
- W2321314925 hasConceptScore W2321314925C199360897 @default.
- W2321314925 hasConceptScore W2321314925C31972630 @default.
- W2321314925 hasConceptScore W2321314925C38652104 @default.
- W2321314925 hasConceptScore W2321314925C41008148 @default.