Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896904464> ?p ?o ?g. }
- W2896904464 endingPage "281" @default.
- W2896904464 startingPage "264" @default.
- W2896904464 abstract "Dense, discrete Graphical Models with pairwise potentials are a powerful class of models which are employed in state-of-the-art computer vision and bio-imaging applications. This work introduces a new MAP-solver, based on the popular Dual Block-Coordinate Ascent principle. Surprisingly, by making a small change to a low-performing solver, the Max Product Linear Programming (MPLP) algorithm [7], we derive the new solver MPLP++ that significantly outperforms all existing solvers by a large margin, including the state-of-the-art solver Tree-Reweighted Sequential (TRW-S) message-passing algorithm [17]. Additionally, our solver is highly parallel, in contrast to TRW-S, which gives a further boost in performance with the proposed GPU and multi-thread CPU implementations. We verify the superiority of our algorithm on dense problems from publicly available benchmarks as well as a new benchmark for 6D Object Pose estimation. We also provide an ablation study with respect to graph density." @default.
- W2896904464 created "2018-10-26" @default.
- W2896904464 creator A5022781127 @default.
- W2896904464 creator A5034290170 @default.
- W2896904464 creator A5068080640 @default.
- W2896904464 creator A5071268662 @default.
- W2896904464 date "2018-01-01" @default.
- W2896904464 modified "2023-09-27" @default.
- W2896904464 title "MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Models" @default.
- W2896904464 cites W120040546 @default.
- W2896904464 cites W1507297895 @default.
- W2896904464 cites W1671067710 @default.
- W2896904464 cites W1965865731 @default.
- W2896904464 cites W1971861370 @default.
- W2896904464 cites W1975605063 @default.
- W2896904464 cites W1985554679 @default.
- W2896904464 cites W2015447696 @default.
- W2896904464 cites W2034200749 @default.
- W2896904464 cites W2055257826 @default.
- W2896904464 cites W2082413021 @default.
- W2896904464 cites W2082935303 @default.
- W2896904464 cites W2084041193 @default.
- W2896904464 cites W2092811510 @default.
- W2896904464 cites W2107884096 @default.
- W2896904464 cites W2114741181 @default.
- W2896904464 cites W2135414191 @default.
- W2896904464 cites W2138514146 @default.
- W2896904464 cites W2140714440 @default.
- W2896904464 cites W2142406598 @default.
- W2896904464 cites W2161274594 @default.
- W2896904464 cites W2164918853 @default.
- W2896904464 cites W2229674747 @default.
- W2896904464 cites W2342178758 @default.
- W2896904464 cites W2466841391 @default.
- W2896904464 cites W2485390272 @default.
- W2896904464 cites W2520070334 @default.
- W2896904464 cites W2546630226 @default.
- W2896904464 cites W2560535692 @default.
- W2896904464 cites W2739228395 @default.
- W2896904464 cites W2950298732 @default.
- W2896904464 cites W2964346077 @default.
- W2896904464 cites W49572150 @default.
- W2896904464 doi "https://doi.org/10.1007/978-3-030-01225-0_16" @default.
- W2896904464 hasPublicationYear "2018" @default.
- W2896904464 type Work @default.
- W2896904464 sameAs 2896904464 @default.
- W2896904464 citedByCount "13" @default.
- W2896904464 countsByYear W28969044642019 @default.
- W2896904464 countsByYear W28969044642020 @default.
- W2896904464 countsByYear W28969044642021 @default.
- W2896904464 countsByYear W28969044642022 @default.
- W2896904464 countsByYear W28969044642023 @default.
- W2896904464 crossrefType "book-chapter" @default.
- W2896904464 hasAuthorship W2896904464A5022781127 @default.
- W2896904464 hasAuthorship W2896904464A5034290170 @default.
- W2896904464 hasAuthorship W2896904464A5068080640 @default.
- W2896904464 hasAuthorship W2896904464A5071268662 @default.
- W2896904464 hasBestOaLocation W28969044642 @default.
- W2896904464 hasConcept C11413529 @default.
- W2896904464 hasConcept C13280743 @default.
- W2896904464 hasConcept C173608175 @default.
- W2896904464 hasConcept C185798385 @default.
- W2896904464 hasConcept C199360897 @default.
- W2896904464 hasConcept C205649164 @default.
- W2896904464 hasConcept C2524010 @default.
- W2896904464 hasConcept C2777210771 @default.
- W2896904464 hasConcept C2778770139 @default.
- W2896904464 hasConcept C33923547 @default.
- W2896904464 hasConcept C41008148 @default.
- W2896904464 hasConcept C80444323 @default.
- W2896904464 hasConceptScore W2896904464C11413529 @default.
- W2896904464 hasConceptScore W2896904464C13280743 @default.
- W2896904464 hasConceptScore W2896904464C173608175 @default.
- W2896904464 hasConceptScore W2896904464C185798385 @default.
- W2896904464 hasConceptScore W2896904464C199360897 @default.
- W2896904464 hasConceptScore W2896904464C205649164 @default.
- W2896904464 hasConceptScore W2896904464C2524010 @default.
- W2896904464 hasConceptScore W2896904464C2777210771 @default.
- W2896904464 hasConceptScore W2896904464C2778770139 @default.
- W2896904464 hasConceptScore W2896904464C33923547 @default.
- W2896904464 hasConceptScore W2896904464C41008148 @default.
- W2896904464 hasConceptScore W2896904464C80444323 @default.
- W2896904464 hasLocation W28969044641 @default.
- W2896904464 hasLocation W28969044642 @default.
- W2896904464 hasOpenAccess W2896904464 @default.
- W2896904464 hasPrimaryLocation W28969044641 @default.
- W2896904464 hasRelatedWork W1485630101 @default.
- W2896904464 hasRelatedWork W197769707 @default.
- W2896904464 hasRelatedWork W2016422608 @default.
- W2896904464 hasRelatedWork W2029210135 @default.
- W2896904464 hasRelatedWork W2080076943 @default.
- W2896904464 hasRelatedWork W2498017833 @default.
- W2896904464 hasRelatedWork W2890907854 @default.
- W2896904464 hasRelatedWork W3011697905 @default.
- W2896904464 hasRelatedWork W3148014268 @default.
- W2896904464 hasRelatedWork W4312469216 @default.
- W2896904464 isParatext "false" @default.
- W2896904464 isRetracted "false" @default.