FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2807884750> ?p ?o ?g. }

• W2807884750 endingPage "32131" @default.
• W2807884750 startingPage "32107" @default.
• W2807884750 abstract "The convolutional neural network (CNN) features can give good description of image content, which usually represent an image with a single feature vector. Although CNN features are more compact than local descriptors, they still cannot efficiently deal with large-scale retrieval due to the linearly incremental cost of computation and storage. To address this issue, we build a simple but effective indexing framework on inverted table, which significantly decreases both search time and memory usage. First, several strategies are fully investigated to adapt inverted table to CNN features for compensating for quantization error. We use multiple assignment for the query and database images to increase the probability that relevant images are assigned to the same visual word obtained via clustering. Embedding codes are also introduced to improve retrieval accuracy by removing false matches. Second, a novel indexing framework that combines inverted table and hashing codes is proposed. This framework is faster than the reformed inverted tables with the introduced strategies. Experiment on several benchmark datasets demonstrates that our method yields faster retrieval speed compared to brute-force search. We also provide fair comparison between popular CNN features." @default.
• W2807884750 created "2018-06-21" @default.
• W2807884750 creator A5005421447 @default.
• W2807884750 creator A5006854141 @default.
• W2807884750 creator A5041070092 @default.
• W2807884750 creator A5057149288 @default.
• W2807884750 date "2018-06-15" @default.
• W2807884750 modified "2023-10-18" @default.
• W2807884750 title "Indexing of the CNN features for the large scale image search" @default.
• W2807884750 cites W1524680991 @default.
• W2807884750 cites W1536680647 @default.
• W2807884750 cites W1556531089 @default.
• W2807884750 cites W1677409904 @default.
• W2807884750 cites W1835419070 @default.
• W2807884750 cites W1913628733 @default.
• W2807884750 cites W1925596459 @default.
• W2807884750 cites W1939575207 @default.
• W2807884750 cites W1966811077 @default.
• W2807884750 cites W1988445395 @default.
• W2807884750 cites W2007972815 @default.
• W2807884750 cites W2012592962 @default.
• W2807884750 cites W2019863495 @default.
• W2807884750 cites W2021283827 @default.
• W2807884750 cites W204268067 @default.
• W2807884750 cites W2046589280 @default.
• W2807884750 cites W2056935845 @default.
• W2807884750 cites W2071901160 @default.
• W2807884750 cites W2074668987 @default.
• W2807884750 cites W2077815765 @default.
• W2807884750 cites W2088866137 @default.
• W2807884750 cites W2089632823 @default.
• W2807884750 cites W2097117768 @default.
• W2807884750 cites W2102605133 @default.
• W2807884750 cites W2108598243 @default.
• W2807884750 cites W2109255472 @default.
• W2807884750 cites W2124509324 @default.
• W2807884750 cites W2128017662 @default.
• W2807884750 cites W2131846894 @default.
• W2807884750 cites W2133995768 @default.
• W2807884750 cites W2141362318 @default.
• W2807884750 cites W2147238549 @default.
• W2807884750 cites W2149991777 @default.
• W2807884750 cites W2151103935 @default.
• W2807884750 cites W2159498975 @default.
• W2807884750 cites W2161969291 @default.
• W2807884750 cites W2162006472 @default.
• W2807884750 cites W2171896402 @default.
• W2807884750 cites W2177274842 @default.
• W2807884750 cites W2194775991 @default.
• W2807884750 cites W2293824885 @default.
• W2807884750 cites W2295537791 @default.
• W2807884750 cites W2336803177 @default.
• W2807884750 cites W2340690086 @default.
• W2807884750 cites W2461086877 @default.
• W2807884750 cites W2464915613 @default.
• W2807884750 cites W2499468060 @default.
• W2807884750 cites W2544587078 @default.
• W2807884750 cites W2600067905 @default.
• W2807884750 cites W2782994636 @default.
• W2807884750 cites W2962817490 @default.
• W2807884750 cites W2963037989 @default.
• W2807884750 cites W2963589668 @default.
• W2807884750 cites W2964076257 @default.
• W2807884750 cites W2964280870 @default.
• W2807884750 cites W3098711604 @default.
• W2807884750 cites W4242599275 @default.
• W2807884750 doi "https://doi.org/10.1007/s11042-018-6210-3" @default.
• W2807884750 hasPublicationYear "2018" @default.
• W2807884750 type Work @default.
• W2807884750 sameAs 2807884750 @default.
• W2807884750 citedByCount "17" @default.
• W2807884750 countsByYear W28078847502018 @default.
• W2807884750 countsByYear W28078847502020 @default.
• W2807884750 countsByYear W28078847502021 @default.
• W2807884750 countsByYear W28078847502022 @default.
• W2807884750 countsByYear W28078847502023 @default.
• W2807884750 crossrefType "journal-article" @default.
• W2807884750 hasAuthorship W2807884750A5005421447 @default.
• W2807884750 hasAuthorship W2807884750A5006854141 @default.
• W2807884750 hasAuthorship W2807884750A5041070092 @default.
• W2807884750 hasAuthorship W2807884750A5057149288 @default.
• W2807884750 hasBestOaLocation W28078847502 @default.
• W2807884750 hasConcept C115961682 @default.
• W2807884750 hasConcept C130590232 @default.
• W2807884750 hasConcept C13280743 @default.
• W2807884750 hasConcept C138885662 @default.
• W2807884750 hasConcept C153180895 @default.
• W2807884750 hasConcept C154945302 @default.
• W2807884750 hasConcept C1667742 @default.
• W2807884750 hasConcept C185798385 @default.
• W2807884750 hasConcept C205649164 @default.
• W2807884750 hasConcept C2776401178 @default.
• W2807884750 hasConcept C38652104 @default.
• W2807884750 hasConcept C41008148 @default.
• W2807884750 hasConcept C41895202 @default.
• W2807884750 hasConcept C67388219 @default.
• W2807884750 hasConcept C75165309 @default.
• W2807884750 hasConcept C81363708 @default.

• next