Matches in SemOpenAlex for { <https://semopenalex.org/work/W2899804785> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2899804785 abstract "Action classification from video streams is a challenging problem, especially when there is a limited number of training data for different actions. Recent developments in deep learning based methods enabled high classification accuracies for many problems in different domains, yet they still perform poorly when the dataset is small. In this work, we examined the performances of Hidden Markov Models (HMM) and long short-term memory (LSTM) based recurrent neural network models using the same sequence classification framework with the well known KTH action dataset. KTH contains limited examples for training, hence challenges the deep learning based techniques even when transfer learning is applied in feature extraction. Our experiments depict that using a pre-trained convolutional network, i.e. SqueezeNet, and fine-tuning for feature extraction; HMM performs better in sequence modeling than an LSTM based model. Using the same feature extraction approach, i.e. fine-tuned SqueezeNet, we obtained 99.30% accuracy with an HMM, which is the best classification accuracy that is reported so far with this dataset; yet 81.92% accuracy with the best performing LSTM configuration." @default.
- W2899804785 created "2018-11-16" @default.
- W2899804785 creator A5028781916 @default.
- W2899804785 creator A5071978946 @default.
- W2899804785 date "2018-11-09" @default.
- W2899804785 modified "2023-09-25" @default.
- W2899804785 title "A Comparative Study of HMMs and LSTMs on Action Classification with Limited Training Data" @default.
- W2899804785 cites W1849277567 @default.
- W2899804785 cites W1983364832 @default.
- W2899804785 cites W1999192586 @default.
- W2899804785 cites W2016053056 @default.
- W2899804785 cites W2064675550 @default.
- W2899804785 cites W2097117768 @default.
- W2899804785 cites W2103822353 @default.
- W2899804785 cites W2108598243 @default.
- W2899804785 cites W2126579184 @default.
- W2899804785 cites W2135658380 @default.
- W2899804785 cites W2146634731 @default.
- W2899804785 cites W2158593205 @default.
- W2899804785 cites W2165715280 @default.
- W2899804785 cites W2473461688 @default.
- W2899804785 cites W2508429489 @default.
- W2899804785 cites W255708204 @default.
- W2899804785 cites W2579984156 @default.
- W2899804785 cites W2749270783 @default.
- W2899804785 cites W2963173190 @default.
- W2899804785 cites W4249279051 @default.
- W2899804785 doi "https://doi.org/10.1007/978-3-030-01054-6_76" @default.
- W2899804785 hasPublicationYear "2018" @default.
- W2899804785 type Work @default.
- W2899804785 sameAs 2899804785 @default.
- W2899804785 citedByCount "0" @default.
- W2899804785 crossrefType "book-chapter" @default.
- W2899804785 hasAuthorship W2899804785A5028781916 @default.
- W2899804785 hasAuthorship W2899804785A5071978946 @default.
- W2899804785 hasConcept C108583219 @default.
- W2899804785 hasConcept C119857082 @default.
- W2899804785 hasConcept C138885662 @default.
- W2899804785 hasConcept C147168706 @default.
- W2899804785 hasConcept C150899416 @default.
- W2899804785 hasConcept C153180895 @default.
- W2899804785 hasConcept C154945302 @default.
- W2899804785 hasConcept C162324750 @default.
- W2899804785 hasConcept C187736073 @default.
- W2899804785 hasConcept C23224414 @default.
- W2899804785 hasConcept C2776401178 @default.
- W2899804785 hasConcept C2778112365 @default.
- W2899804785 hasConcept C2780451532 @default.
- W2899804785 hasConcept C35639132 @default.
- W2899804785 hasConcept C41008148 @default.
- W2899804785 hasConcept C41895202 @default.
- W2899804785 hasConcept C50644808 @default.
- W2899804785 hasConcept C52622490 @default.
- W2899804785 hasConcept C54355233 @default.
- W2899804785 hasConcept C81363708 @default.
- W2899804785 hasConcept C86803240 @default.
- W2899804785 hasConceptScore W2899804785C108583219 @default.
- W2899804785 hasConceptScore W2899804785C119857082 @default.
- W2899804785 hasConceptScore W2899804785C138885662 @default.
- W2899804785 hasConceptScore W2899804785C147168706 @default.
- W2899804785 hasConceptScore W2899804785C150899416 @default.
- W2899804785 hasConceptScore W2899804785C153180895 @default.
- W2899804785 hasConceptScore W2899804785C154945302 @default.
- W2899804785 hasConceptScore W2899804785C162324750 @default.
- W2899804785 hasConceptScore W2899804785C187736073 @default.
- W2899804785 hasConceptScore W2899804785C23224414 @default.
- W2899804785 hasConceptScore W2899804785C2776401178 @default.
- W2899804785 hasConceptScore W2899804785C2778112365 @default.
- W2899804785 hasConceptScore W2899804785C2780451532 @default.
- W2899804785 hasConceptScore W2899804785C35639132 @default.
- W2899804785 hasConceptScore W2899804785C41008148 @default.
- W2899804785 hasConceptScore W2899804785C41895202 @default.
- W2899804785 hasConceptScore W2899804785C50644808 @default.
- W2899804785 hasConceptScore W2899804785C52622490 @default.
- W2899804785 hasConceptScore W2899804785C54355233 @default.
- W2899804785 hasConceptScore W2899804785C81363708 @default.
- W2899804785 hasConceptScore W2899804785C86803240 @default.
- W2899804785 hasLocation W28998047851 @default.
- W2899804785 hasOpenAccess W2899804785 @default.
- W2899804785 hasPrimaryLocation W28998047851 @default.
- W2899804785 hasRelatedWork W2760944304 @default.
- W2899804785 hasRelatedWork W2773120646 @default.
- W2899804785 hasRelatedWork W2800691917 @default.
- W2899804785 hasRelatedWork W2807839383 @default.
- W2899804785 hasRelatedWork W2940859255 @default.
- W2899804785 hasRelatedWork W3021430260 @default.
- W2899804785 hasRelatedWork W3196211586 @default.
- W2899804785 hasRelatedWork W3211334395 @default.
- W2899804785 hasRelatedWork W4200183533 @default.
- W2899804785 hasRelatedWork W4285815702 @default.
- W2899804785 isParatext "false" @default.
- W2899804785 isRetracted "false" @default.
- W2899804785 magId "2899804785" @default.
- W2899804785 workType "book-chapter" @default.