Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892933850> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2892933850 startingPage "287" @default.
- W2892933850 abstract "The bag-of-visual-words (BoW) generation is a widely used unsupervised feature extraction method for the variety of computer vision applications. However, space and computational complexity of bag-of-visual-words generation increase with an increase in the size of the dataset because of computational complexities involved in underlying algorithms. In this paper, we present Fast-BoW, a scalable method for BoW generation for both hard and soft vector-quantization with time complexities O(|h| log2 k) and O(|h|k), respectively1. We replace the process of finding the closest cluster center with a softmax classifier which improves the cluster boundaries over k-means and also can be used for both hard and soft BoW encoding. To make the model compact and faster, we quantize the real weights into integer weights which can be represented using few bits (2−8) only. Also, on the quantized weights, we apply the hashing to reduce the number of multiplications which makes the process further faster. We evaluated the proposed approach on several public benchmark datasets. The experimental results outperform the existing hierarchical clustering tree-based approach by ≈ 12 times." @default.
- W2892933850 created "2018-10-05" @default.
- W2892933850 creator A5012566120 @default.
- W2892933850 creator A5048439740 @default.
- W2892933850 creator A5068460573 @default.
- W2892933850 creator A5077717460 @default.
- W2892933850 date "2018-01-01" @default.
- W2892933850 modified "2023-09-22" @default.
- W2892933850 title "Fast-BoW: Scaling Bag-of-Visual-Words Generation" @default.
- W2892933850 hasPublicationYear "2018" @default.
- W2892933850 type Work @default.
- W2892933850 sameAs 2892933850 @default.
- W2892933850 citedByCount "0" @default.
- W2892933850 crossrefType "proceedings-article" @default.
- W2892933850 hasAuthorship W2892933850A5012566120 @default.
- W2892933850 hasAuthorship W2892933850A5048439740 @default.
- W2892933850 hasAuthorship W2892933850A5068460573 @default.
- W2892933850 hasAuthorship W2892933850A5077717460 @default.
- W2892933850 hasConcept C101738243 @default.
- W2892933850 hasConcept C108583219 @default.
- W2892933850 hasConcept C11413529 @default.
- W2892933850 hasConcept C115961682 @default.
- W2892933850 hasConcept C127759330 @default.
- W2892933850 hasConcept C13672336 @default.
- W2892933850 hasConcept C153180895 @default.
- W2892933850 hasConcept C154945302 @default.
- W2892933850 hasConcept C1667742 @default.
- W2892933850 hasConcept C167611913 @default.
- W2892933850 hasConcept C179799912 @default.
- W2892933850 hasConcept C188441871 @default.
- W2892933850 hasConcept C189391414 @default.
- W2892933850 hasConcept C199833920 @default.
- W2892933850 hasConcept C38652104 @default.
- W2892933850 hasConcept C41008148 @default.
- W2892933850 hasConcept C48044578 @default.
- W2892933850 hasConcept C52622490 @default.
- W2892933850 hasConcept C73555534 @default.
- W2892933850 hasConcept C77088390 @default.
- W2892933850 hasConcept C83665646 @default.
- W2892933850 hasConcept C99138194 @default.
- W2892933850 hasConceptScore W2892933850C101738243 @default.
- W2892933850 hasConceptScore W2892933850C108583219 @default.
- W2892933850 hasConceptScore W2892933850C11413529 @default.
- W2892933850 hasConceptScore W2892933850C115961682 @default.
- W2892933850 hasConceptScore W2892933850C127759330 @default.
- W2892933850 hasConceptScore W2892933850C13672336 @default.
- W2892933850 hasConceptScore W2892933850C153180895 @default.
- W2892933850 hasConceptScore W2892933850C154945302 @default.
- W2892933850 hasConceptScore W2892933850C1667742 @default.
- W2892933850 hasConceptScore W2892933850C167611913 @default.
- W2892933850 hasConceptScore W2892933850C179799912 @default.
- W2892933850 hasConceptScore W2892933850C188441871 @default.
- W2892933850 hasConceptScore W2892933850C189391414 @default.
- W2892933850 hasConceptScore W2892933850C199833920 @default.
- W2892933850 hasConceptScore W2892933850C38652104 @default.
- W2892933850 hasConceptScore W2892933850C41008148 @default.
- W2892933850 hasConceptScore W2892933850C48044578 @default.
- W2892933850 hasConceptScore W2892933850C52622490 @default.
- W2892933850 hasConceptScore W2892933850C73555534 @default.
- W2892933850 hasConceptScore W2892933850C77088390 @default.
- W2892933850 hasConceptScore W2892933850C83665646 @default.
- W2892933850 hasConceptScore W2892933850C99138194 @default.
- W2892933850 hasLocation W28929338501 @default.
- W2892933850 hasOpenAccess W2892933850 @default.
- W2892933850 hasPrimaryLocation W28929338501 @default.
- W2892933850 hasRelatedWork W122956856 @default.
- W2892933850 hasRelatedWork W135741203 @default.
- W2892933850 hasRelatedWork W1484703468 @default.
- W2892933850 hasRelatedWork W159470477 @default.
- W2892933850 hasRelatedWork W161426234 @default.
- W2892933850 hasRelatedWork W1987040325 @default.
- W2892933850 hasRelatedWork W2029785729 @default.
- W2892933850 hasRelatedWork W2065791510 @default.
- W2892933850 hasRelatedWork W2211964529 @default.
- W2892933850 hasRelatedWork W2215369824 @default.
- W2892933850 hasRelatedWork W2216462535 @default.
- W2892933850 hasRelatedWork W2472431043 @default.
- W2892933850 hasRelatedWork W2550698348 @default.
- W2892933850 hasRelatedWork W2789935499 @default.
- W2892933850 hasRelatedWork W2807884750 @default.
- W2892933850 hasRelatedWork W2949159428 @default.
- W2892933850 hasRelatedWork W3169788532 @default.
- W2892933850 hasRelatedWork W3183436810 @default.
- W2892933850 hasRelatedWork W3196069353 @default.
- W2892933850 hasRelatedWork W3205509771 @default.
- W2892933850 isParatext "false" @default.
- W2892933850 isRetracted "false" @default.
- W2892933850 magId "2892933850" @default.
- W2892933850 workType "article" @default.