FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1897029691> ?p ?o ?g. }

• W1897029691 endingPage "5915" @default.
• W1897029691 startingPage "5904" @default.
• W1897029691 abstract "Slow feature analysis (SFA) extracts slowly varying signals from input data and has been used to model complex cells in the primary visual cortex (V1). It transmits information to both ventral and dorsal pathways to process appearance and motion information, respectively. However, SFA only uses slowly varying features for local feature extraction, because they represent appearance information more effectively than motion information. To better utilize temporal information, we propose temporal variance analysis (TVA) as a generalization of SFA. TVA learns a linear transformation matrix that projects multidimensional temporal data to temporal components with temporal variance. Inspired by the function of V1, we learn receptive fields by TVA and apply convolution and pooling to extract local features. Embedded in the improved dense trajectory framework, TVA for action recognition is proposed to: 1) extract appearance and motion features from gray using slow and fast filters, respectively; 2) extract additional motion features using slow filters from horizontal and vertical optical flows; and 3) separately encode extracted local features with different temporal variances and concatenate all the encoded features as final features. We evaluate the proposed TVA features on several challenging data sets and show that both slow and fast features are useful in the low-level feature extraction. Experimental results show that the proposed TVA features outperform the conventional histogram-based features, and excellent results can be achieved by combining all TVA features." @default.
• W1897029691 created "2016-06-24" @default.
• W1897029691 creator A5000885779 @default.
• W1897029691 creator A5007354180 @default.
• W1897029691 creator A5053820185 @default.
• W1897029691 creator A5074103823 @default.
• W1897029691 creator A5077884274 @default.
• W1897029691 date "2015-12-01" @default.
• W1897029691 modified "2023-10-16" @default.
• W1897029691 title "Temporal Variance Analysis for Action Recognition" @default.
• W1897029691 cites W1972053684 @default.
• W1897029691 cites W1977814411 @default.
• W1897029691 cites W1980527289 @default.
• W1897029691 cites W1981781955 @default.
• W1897029691 cites W1985469025 @default.
• W1897029691 cites W1991598519 @default.
• W1897029691 cites W1993229407 @default.
• W1897029691 cites W1996904744 @default.
• W1897029691 cites W2018870022 @default.
• W1897029691 cites W2019377328 @default.
• W1897029691 cites W2019725986 @default.
• W1897029691 cites W2024868105 @default.
• W1897029691 cites W2035299679 @default.
• W1897029691 cites W2042041679 @default.
• W1897029691 cites W2047666344 @default.
• W1897029691 cites W2051822550 @default.
• W1897029691 cites W2055306175 @default.
• W1897029691 cites W2064776690 @default.
• W1897029691 cites W2068611653 @default.
• W1897029691 cites W2080107612 @default.
• W1897029691 cites W2080353936 @default.
• W1897029691 cites W2084793887 @default.
• W1897029691 cites W2092903210 @default.
• W1897029691 cites W2095802353 @default.
• W1897029691 cites W2096691069 @default.
• W1897029691 cites W2105101328 @default.
• W1897029691 cites W2108333036 @default.
• W1897029691 cites W2115762103 @default.
• W1897029691 cites W2119799051 @default.
• W1897029691 cites W2126574503 @default.
• W1897029691 cites W2130913433 @default.
• W1897029691 cites W2131042978 @default.
• W1897029691 cites W2142194269 @default.
• W1897029691 cites W2146444479 @default.
• W1897029691 cites W2148553367 @default.
• W1897029691 cites W2149194912 @default.
• W1897029691 cites W2158969428 @default.
• W1897029691 cites W2161969291 @default.
• W1897029691 cites W4237044863 @default.
• W1897029691 doi "https://doi.org/10.1109/tip.2015.2490551" @default.
• W1897029691 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/26469203" @default.
• W1897029691 hasPublicationYear "2015" @default.
• W1897029691 type Work @default.
• W1897029691 sameAs 1897029691 @default.
• W1897029691 citedByCount "14" @default.
• W1897029691 countsByYear W18970296912015 @default.
• W1897029691 countsByYear W18970296912016 @default.
• W1897029691 countsByYear W18970296912017 @default.
• W1897029691 countsByYear W18970296912018 @default.
• W1897029691 countsByYear W18970296912019 @default.
• W1897029691 countsByYear W18970296912020 @default.
• W1897029691 countsByYear W18970296912021 @default.
• W1897029691 crossrefType "journal-article" @default.
• W1897029691 hasAuthorship W1897029691A5000885779 @default.
• W1897029691 hasAuthorship W1897029691A5007354180 @default.
• W1897029691 hasAuthorship W1897029691A5053820185 @default.
• W1897029691 hasAuthorship W1897029691A5074103823 @default.
• W1897029691 hasAuthorship W1897029691A5077884274 @default.
• W1897029691 hasConcept C10161872 @default.
• W1897029691 hasConcept C104317684 @default.
• W1897029691 hasConcept C115961682 @default.
• W1897029691 hasConcept C153180895 @default.
• W1897029691 hasConcept C154945302 @default.
• W1897029691 hasConcept C17426736 @default.
• W1897029691 hasConcept C185592680 @default.
• W1897029691 hasConcept C31972630 @default.
• W1897029691 hasConcept C41008148 @default.
• W1897029691 hasConcept C52622490 @default.
• W1897029691 hasConcept C53533937 @default.
• W1897029691 hasConcept C55493867 @default.
• W1897029691 hasConcept C66746571 @default.
• W1897029691 hasConcept C70437156 @default.
• W1897029691 hasConceptScore W1897029691C10161872 @default.
• W1897029691 hasConceptScore W1897029691C104317684 @default.
• W1897029691 hasConceptScore W1897029691C115961682 @default.
• W1897029691 hasConceptScore W1897029691C153180895 @default.
• W1897029691 hasConceptScore W1897029691C154945302 @default.
• W1897029691 hasConceptScore W1897029691C17426736 @default.
• W1897029691 hasConceptScore W1897029691C185592680 @default.
• W1897029691 hasConceptScore W1897029691C31972630 @default.
• W1897029691 hasConceptScore W1897029691C41008148 @default.
• W1897029691 hasConceptScore W1897029691C52622490 @default.
• W1897029691 hasConceptScore W1897029691C53533937 @default.
• W1897029691 hasConceptScore W1897029691C55493867 @default.
• W1897029691 hasConceptScore W1897029691C66746571 @default.
• W1897029691 hasConceptScore W1897029691C70437156 @default.
• W1897029691 hasIssue "12" @default.
• W1897029691 hasLocation W18970296911 @default.

• next