Matches in SemOpenAlex for { <https://semopenalex.org/work/W2801296710> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2801296710 abstract "Terror attacks are often targeted towards the civilians gathered in one location (e.g., Boston Marathon bombing). Distinguishing such ’malicious’ scenes from the ’normal’ ones, which are semantically different, is a difficult task as both scenes contain large groups of people with high visual similarity. To overcome the difficulty, previous methods exploited various contextual information, such as language-driven keywords or relevant objects. Although useful, they require additional human effort or dataset. In this paper, we show that using more sophisticated and deeper Convolutional Neural Networks (CNNs) can achieve better classification accuracy even without using any additional information outside the image domain. We have conducted a comparative study where we train and compare seven different CNN architectures (AlexNet, VGG-M, VGG16, GoogLeNet, ResNet- 50, ResNet-101, and ResNet-152). Based on the experimental analyses, we found out that deeper networks typically show better accuracy, and that GoogLeNet is the most favorable among the seven architectures for the task of malicious event classification." @default.
- W2801296710 created "2018-05-17" @default.
- W2801296710 creator A5040282679 @default.
- W2801296710 creator A5077581741 @default.
- W2801296710 creator A5081206531 @default.
- W2801296710 date "2018-04-27" @default.
- W2801296710 modified "2023-10-01" @default.
- W2801296710 title "Going deeper with CNN in malicious crowd event classification" @default.
- W2801296710 doi "https://doi.org/10.1117/12.2306086" @default.
- W2801296710 hasPublicationYear "2018" @default.
- W2801296710 type Work @default.
- W2801296710 sameAs 2801296710 @default.
- W2801296710 citedByCount "3" @default.
- W2801296710 countsByYear W28012967102019 @default.
- W2801296710 countsByYear W28012967102020 @default.
- W2801296710 crossrefType "proceedings-article" @default.
- W2801296710 hasAuthorship W2801296710A5040282679 @default.
- W2801296710 hasAuthorship W2801296710A5077581741 @default.
- W2801296710 hasAuthorship W2801296710A5081206531 @default.
- W2801296710 hasConcept C103278499 @default.
- W2801296710 hasConcept C115961682 @default.
- W2801296710 hasConcept C119857082 @default.
- W2801296710 hasConcept C121332964 @default.
- W2801296710 hasConcept C134306372 @default.
- W2801296710 hasConcept C153180895 @default.
- W2801296710 hasConcept C154945302 @default.
- W2801296710 hasConcept C162324750 @default.
- W2801296710 hasConcept C187736073 @default.
- W2801296710 hasConcept C2779662365 @default.
- W2801296710 hasConcept C2780451532 @default.
- W2801296710 hasConcept C2944601119 @default.
- W2801296710 hasConcept C33923547 @default.
- W2801296710 hasConcept C36503486 @default.
- W2801296710 hasConcept C41008148 @default.
- W2801296710 hasConcept C62520636 @default.
- W2801296710 hasConcept C81363708 @default.
- W2801296710 hasConceptScore W2801296710C103278499 @default.
- W2801296710 hasConceptScore W2801296710C115961682 @default.
- W2801296710 hasConceptScore W2801296710C119857082 @default.
- W2801296710 hasConceptScore W2801296710C121332964 @default.
- W2801296710 hasConceptScore W2801296710C134306372 @default.
- W2801296710 hasConceptScore W2801296710C153180895 @default.
- W2801296710 hasConceptScore W2801296710C154945302 @default.
- W2801296710 hasConceptScore W2801296710C162324750 @default.
- W2801296710 hasConceptScore W2801296710C187736073 @default.
- W2801296710 hasConceptScore W2801296710C2779662365 @default.
- W2801296710 hasConceptScore W2801296710C2780451532 @default.
- W2801296710 hasConceptScore W2801296710C2944601119 @default.
- W2801296710 hasConceptScore W2801296710C33923547 @default.
- W2801296710 hasConceptScore W2801296710C36503486 @default.
- W2801296710 hasConceptScore W2801296710C41008148 @default.
- W2801296710 hasConceptScore W2801296710C62520636 @default.
- W2801296710 hasConceptScore W2801296710C81363708 @default.
- W2801296710 hasLocation W28012967101 @default.
- W2801296710 hasOpenAccess W2801296710 @default.
- W2801296710 hasPrimaryLocation W28012967101 @default.
- W2801296710 hasRelatedWork W2295702360 @default.
- W2801296710 hasRelatedWork W2412479940 @default.
- W2801296710 hasRelatedWork W2741119099 @default.
- W2801296710 hasRelatedWork W2789348963 @default.
- W2801296710 hasRelatedWork W2807436399 @default.
- W2801296710 hasRelatedWork W2807621872 @default.
- W2801296710 hasRelatedWork W2808896182 @default.
- W2801296710 hasRelatedWork W2889031311 @default.
- W2801296710 hasRelatedWork W2900812411 @default.
- W2801296710 hasRelatedWork W2929186373 @default.
- W2801296710 hasRelatedWork W2944624702 @default.
- W2801296710 hasRelatedWork W2949334049 @default.
- W2801296710 hasRelatedWork W2953111739 @default.
- W2801296710 hasRelatedWork W2978680233 @default.
- W2801296710 hasRelatedWork W3084381999 @default.
- W2801296710 hasRelatedWork W3112649497 @default.
- W2801296710 hasRelatedWork W3127819136 @default.
- W2801296710 hasRelatedWork W3157056612 @default.
- W2801296710 hasRelatedWork W3208159610 @default.
- W2801296710 hasRelatedWork W2551176409 @default.
- W2801296710 isParatext "false" @default.
- W2801296710 isRetracted "false" @default.
- W2801296710 magId "2801296710" @default.
- W2801296710 workType "article" @default.