Matches in SemOpenAlex for { <https://semopenalex.org/work/W2437979450> ?p ?o ?g. }
- W2437979450 abstract "In applications involving matching of image sets, the information from multiple images must be effectively exploited to represent each set. State-of-the-art methods use probabilistic distribution or subspace to model a set and use specific distance measure to compare two sets. These methods are slow to compute and not compact to use in a large scale scenario. Learning-based hashing is often used in large scale image retrieval as they provide a compact representation of each sample and the Hamming distance can be used to efficiently compare two samples. However, most hashing methods encode each image separately and discard knowledge that multiple images in the same set represent the same object or person. We investigate the set hashing problem by combining both set representation and hashing in a single deep neural network. An image set is first passed to a CNN module to extract image features, then these features are aggregated using two types of set feature to capture both set specific and database-wide distribution information. The computed set feature is then fed into a multilayer perceptron to learn a compact binary embedding. Triplet loss is used to train the network by forming set similarity relations using class labels. We extensively evaluate our approach on datasets used for image matching and show highly competitive performance compared to state-of-the-art methods." @default.
- W2437979450 created "2016-06-24" @default.
- W2437979450 creator A5017855052 @default.
- W2437979450 creator A5033604465 @default.
- W2437979450 creator A5067090814 @default.
- W2437979450 creator A5075510768 @default.
- W2437979450 date "2016-06-16" @default.
- W2437979450 modified "2023-09-27" @default.
- W2437979450 title "Deep Image Set Hashing" @default.
- W2437979450 cites W1165382972 @default.
- W2437979450 cites W1506778248 @default.
- W2437979450 cites W1509966554 @default.
- W2437979450 cites W1606347560 @default.
- W2437979450 cites W1686810756 @default.
- W2437979450 cites W1820849028 @default.
- W2437979450 cites W1913628733 @default.
- W2437979450 cites W1939575207 @default.
- W2437979450 cites W1959016151 @default.
- W2437979450 cites W1974647172 @default.
- W2437979450 cites W1992371516 @default.
- W2437979450 cites W1996939238 @default.
- W2437979450 cites W2012592962 @default.
- W2437979450 cites W2022398315 @default.
- W2437979450 cites W2068163954 @default.
- W2437979450 cites W2068396114 @default.
- W2437979450 cites W2097117768 @default.
- W2437979450 cites W2110599581 @default.
- W2437979450 cites W2112074816 @default.
- W2437979450 cites W2117539524 @default.
- W2437979450 cites W2122691893 @default.
- W2437979450 cites W2126017757 @default.
- W2437979450 cites W2131846894 @default.
- W2437979450 cites W2134849720 @default.
- W2437979450 cites W2144093206 @default.
- W2437979450 cites W2145607950 @default.
- W2437979450 cites W2147238549 @default.
- W2437979450 cites W2150600350 @default.
- W2437979450 cites W2162813111 @default.
- W2437979450 cites W2164598857 @default.
- W2437979450 cites W2191588813 @default.
- W2437979450 cites W2194775991 @default.
- W2437979450 cites W2293824885 @default.
- W2437979450 cites W2325939864 @default.
- W2437979450 cites W2949235290 @default.
- W2437979450 cites W2950366620 @default.
- W2437979450 cites W2963213486 @default.
- W2437979450 cites W3118608800 @default.
- W2437979450 hasPublicationYear "2016" @default.
- W2437979450 type Work @default.
- W2437979450 sameAs 2437979450 @default.
- W2437979450 citedByCount "0" @default.
- W2437979450 crossrefType "posted-content" @default.
- W2437979450 hasAuthorship W2437979450A5017855052 @default.
- W2437979450 hasAuthorship W2437979450A5033604465 @default.
- W2437979450 hasAuthorship W2437979450A5067090814 @default.
- W2437979450 hasAuthorship W2437979450A5075510768 @default.
- W2437979450 hasConcept C11413529 @default.
- W2437979450 hasConcept C115961682 @default.
- W2437979450 hasConcept C138885662 @default.
- W2437979450 hasConcept C153180895 @default.
- W2437979450 hasConcept C154945302 @default.
- W2437979450 hasConcept C157125643 @default.
- W2437979450 hasConcept C1667742 @default.
- W2437979450 hasConcept C177264268 @default.
- W2437979450 hasConcept C199360897 @default.
- W2437979450 hasConcept C2776401178 @default.
- W2437979450 hasConcept C2779494224 @default.
- W2437979450 hasConcept C38652104 @default.
- W2437979450 hasConcept C41008148 @default.
- W2437979450 hasConcept C41895202 @default.
- W2437979450 hasConcept C57273362 @default.
- W2437979450 hasConcept C73150493 @default.
- W2437979450 hasConcept C81363708 @default.
- W2437979450 hasConcept C99138194 @default.
- W2437979450 hasConceptScore W2437979450C11413529 @default.
- W2437979450 hasConceptScore W2437979450C115961682 @default.
- W2437979450 hasConceptScore W2437979450C138885662 @default.
- W2437979450 hasConceptScore W2437979450C153180895 @default.
- W2437979450 hasConceptScore W2437979450C154945302 @default.
- W2437979450 hasConceptScore W2437979450C157125643 @default.
- W2437979450 hasConceptScore W2437979450C1667742 @default.
- W2437979450 hasConceptScore W2437979450C177264268 @default.
- W2437979450 hasConceptScore W2437979450C199360897 @default.
- W2437979450 hasConceptScore W2437979450C2776401178 @default.
- W2437979450 hasConceptScore W2437979450C2779494224 @default.
- W2437979450 hasConceptScore W2437979450C38652104 @default.
- W2437979450 hasConceptScore W2437979450C41008148 @default.
- W2437979450 hasConceptScore W2437979450C41895202 @default.
- W2437979450 hasConceptScore W2437979450C57273362 @default.
- W2437979450 hasConceptScore W2437979450C73150493 @default.
- W2437979450 hasConceptScore W2437979450C81363708 @default.
- W2437979450 hasConceptScore W2437979450C99138194 @default.
- W2437979450 hasLocation W24379794501 @default.
- W2437979450 hasOpenAccess W2437979450 @default.
- W2437979450 hasPrimaryLocation W24379794501 @default.
- W2437979450 hasRelatedWork W108426146 @default.
- W2437979450 hasRelatedWork W1144411872 @default.
- W2437979450 hasRelatedWork W1167987884 @default.
- W2437979450 hasRelatedWork W1518661375 @default.
- W2437979450 hasRelatedWork W2018457419 @default.