Matches in SemOpenAlex for { <https://semopenalex.org/work/W2948796875> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W2948796875 abstract "Local spatio-temporal features with a Bag-of-visual words model is a popular approach used in human action recognition. Bag-of-features methods suffer from several challenges such as extracting appropriate appearance and motion features from videos, converting extracted features appropriate for classification and designing a suitable classification framework. In this paper we address the problem of efficiently representing the extracted features for classification to improve the overall performance. We introduce two generative supervised topic models, maximum entropy discrimination LDA (MedLDA) and class- specific simplex LDA (css-LDA), to encode the raw features suitable for discriminative SVM based classification. Unsupervised LDA models disconnect topic discovery from the classification task, hence yield poor results compared to the baseline Bag-of-words framework. On the other hand supervised LDA techniques learn the topic structure by considering the class labels and improve the recognition accuracy significantly. MedLDA maximizes likelihood and within class margins using max-margin techniques and yields a sparse highly discriminative topic structure; while in css-LDA separate class specific topics are learned instead of common set of topics across the entire dataset. In our representation first topics are learned and then each video is represented as a topic proportion vector, i.e. it can be comparable to a histogram of topics. Finally SVM classification is done on the learned topic proportion vector. We demonstrate the efficiency of the above two representation techniques through the experiments carried out in two popular datasets. Experimental results demonstrate significantly improved performance compared to the baseline Bag-of-features framework which uses kmeans to construct histogram of words from the feature vectors." @default.
- W2948796875 created "2019-06-14" @default.
- W2948796875 creator A5034095159 @default.
- W2948796875 creator A5055128383 @default.
- W2948796875 creator A5062844207 @default.
- W2948796875 creator A5083626840 @default.
- W2948796875 date "2014-01-01" @default.
- W2948796875 modified "2023-09-22" @default.
- W2948796875 title "Supervised latent dirichlet allocation models for efficient activity representation" @default.
- W2948796875 hasPublicationYear "2014" @default.
- W2948796875 type Work @default.
- W2948796875 sameAs 2948796875 @default.
- W2948796875 citedByCount "0" @default.
- W2948796875 crossrefType "journal-article" @default.
- W2948796875 hasAuthorship W2948796875A5034095159 @default.
- W2948796875 hasAuthorship W2948796875A5055128383 @default.
- W2948796875 hasAuthorship W2948796875A5062844207 @default.
- W2948796875 hasAuthorship W2948796875A5083626840 @default.
- W2948796875 hasConcept C115961682 @default.
- W2948796875 hasConcept C119857082 @default.
- W2948796875 hasConcept C12267149 @default.
- W2948796875 hasConcept C13672336 @default.
- W2948796875 hasConcept C153180895 @default.
- W2948796875 hasConcept C154945302 @default.
- W2948796875 hasConcept C171686336 @default.
- W2948796875 hasConcept C41008148 @default.
- W2948796875 hasConcept C500882744 @default.
- W2948796875 hasConcept C53533937 @default.
- W2948796875 hasConcept C774472 @default.
- W2948796875 hasConcept C97931131 @default.
- W2948796875 hasConceptScore W2948796875C115961682 @default.
- W2948796875 hasConceptScore W2948796875C119857082 @default.
- W2948796875 hasConceptScore W2948796875C12267149 @default.
- W2948796875 hasConceptScore W2948796875C13672336 @default.
- W2948796875 hasConceptScore W2948796875C153180895 @default.
- W2948796875 hasConceptScore W2948796875C154945302 @default.
- W2948796875 hasConceptScore W2948796875C171686336 @default.
- W2948796875 hasConceptScore W2948796875C41008148 @default.
- W2948796875 hasConceptScore W2948796875C500882744 @default.
- W2948796875 hasConceptScore W2948796875C53533937 @default.
- W2948796875 hasConceptScore W2948796875C774472 @default.
- W2948796875 hasConceptScore W2948796875C97931131 @default.
- W2948796875 hasLocation W29487968751 @default.
- W2948796875 hasOpenAccess W2948796875 @default.
- W2948796875 hasPrimaryLocation W29487968751 @default.
- W2948796875 hasRelatedWork W1966135063 @default.
- W2948796875 hasRelatedWork W1971845424 @default.
- W2948796875 hasRelatedWork W1981789749 @default.
- W2948796875 hasRelatedWork W1992030210 @default.
- W2948796875 hasRelatedWork W2020903464 @default.
- W2948796875 hasRelatedWork W2025679133 @default.
- W2948796875 hasRelatedWork W2030668353 @default.
- W2948796875 hasRelatedWork W2043147077 @default.
- W2948796875 hasRelatedWork W2058057007 @default.
- W2948796875 hasRelatedWork W2067130063 @default.
- W2948796875 hasRelatedWork W2077193964 @default.
- W2948796875 hasRelatedWork W2123317149 @default.
- W2948796875 hasRelatedWork W2131912381 @default.
- W2948796875 hasRelatedWork W2259243964 @default.
- W2948796875 hasRelatedWork W2284110181 @default.
- W2948796875 hasRelatedWork W2377468574 @default.
- W2948796875 hasRelatedWork W3037585159 @default.
- W2948796875 hasRelatedWork W3193176099 @default.
- W2948796875 hasRelatedWork W2915659333 @default.
- W2948796875 hasRelatedWork W3135489455 @default.
- W2948796875 isParatext "false" @default.
- W2948796875 isRetracted "false" @default.
- W2948796875 magId "2948796875" @default.
- W2948796875 workType "article" @default.