Matches in SemOpenAlex for { <https://semopenalex.org/work/W3015130333> ?p ?o ?g. }
- W3015130333 endingPage "6124" @default.
- W3015130333 startingPage "6109" @default.
- W3015130333 abstract "The recognition of human actions recorded in a multi-camera environment faces the challenging issue of viewpoint variation. Multi-view methods employ videos from different views to generate a compact view-invariant representation of human actions. This paper proposes a novel multi-view human action recognition approach that uses multiple low-dimensional temporal templates and a reconstruction-based encoding scheme. The proposed approach is based upon the extraction of multiple 2D motion history images (MHIs) of human action videos over non-overlapping temporal windows, constructing multiple batches of motion history images (MB-MHIs). Then, two kinds of descriptions are computed for these MHIs batches based on (1) a deep residual network (ResNet) and (2) histogram of oriented gradients (HOG) to effectively quantify a change in gradient. ResNet descriptions are average pooled at each batch. HOG descriptions are processed independently at each batch to learn a class-based dictionary using a K-spectral value decomposition algorithm. Later, the sparse codes of feature descriptions are obtained using an orthogonal matching pursuit approach. These sparse codes are average pooled to extract encoded feature vectors. Then, encoded feature vectors at each batch are fused to form a final view-invariant feature representation. Finally, a linear support vector machine classifier is trained for action recognition. Experimental results are given on three versions of a multi-view dataset: MuHAVi-8, MuHAVi-14, and MuHAVi-uncut. The proposed approach shows promising results when tested for a novel camera. Results on deep features indicate that action representation by MB-MHIs is more view-invariant than single MHIs." @default.
- W3015130333 created "2020-04-10" @default.
- W3015130333 creator A5000226831 @default.
- W3015130333 creator A5001618284 @default.
- W3015130333 creator A5040966283 @default.
- W3015130333 creator A5059502259 @default.
- W3015130333 date "2020-03-31" @default.
- W3015130333 modified "2023-10-07" @default.
- W3015130333 title "Multiple Batches of Motion History Images (MB-MHIs) for Multi-view Human Action Recognition" @default.
- W3015130333 cites W1534763723 @default.
- W3015130333 cites W1595717062 @default.
- W3015130333 cites W1863225007 @default.
- W3015130333 cites W1871385855 @default.
- W3015130333 cites W1902024696 @default.
- W3015130333 cites W1973066300 @default.
- W3015130333 cites W1977018441 @default.
- W3015130333 cites W1980176153 @default.
- W3015130333 cites W1983705368 @default.
- W3015130333 cites W1998222986 @default.
- W3015130333 cites W2008771257 @default.
- W3015130333 cites W2016053056 @default.
- W3015130333 cites W2019085623 @default.
- W3015130333 cites W2054041160 @default.
- W3015130333 cites W2066132206 @default.
- W3015130333 cites W2068611653 @default.
- W3015130333 cites W2090588508 @default.
- W3015130333 cites W2105101328 @default.
- W3015130333 cites W2142194269 @default.
- W3015130333 cites W2151259137 @default.
- W3015130333 cites W2160547390 @default.
- W3015130333 cites W2165715280 @default.
- W3015130333 cites W2172196609 @default.
- W3015130333 cites W2194775991 @default.
- W3015130333 cites W2207258529 @default.
- W3015130333 cites W2274889442 @default.
- W3015130333 cites W2280031036 @default.
- W3015130333 cites W2291208916 @default.
- W3015130333 cites W2294130536 @default.
- W3015130333 cites W2313747897 @default.
- W3015130333 cites W2323265460 @default.
- W3015130333 cites W2345600632 @default.
- W3015130333 cites W2465488276 @default.
- W3015130333 cites W2536719109 @default.
- W3015130333 cites W2555390784 @default.
- W3015130333 cites W2587332781 @default.
- W3015130333 cites W2593146028 @default.
- W3015130333 cites W2615125230 @default.
- W3015130333 cites W2650426111 @default.
- W3015130333 cites W2748826260 @default.
- W3015130333 cites W2753067135 @default.
- W3015130333 cites W2766893746 @default.
- W3015130333 cites W2767919448 @default.
- W3015130333 cites W2782194610 @default.
- W3015130333 cites W2790490299 @default.
- W3015130333 cites W2792969342 @default.
- W3015130333 cites W2795381502 @default.
- W3015130333 cites W2796426886 @default.
- W3015130333 cites W2799325259 @default.
- W3015130333 cites W2891944521 @default.
- W3015130333 cites W2892028513 @default.
- W3015130333 cites W2898934903 @default.
- W3015130333 cites W2898947732 @default.
- W3015130333 cites W2908324567 @default.
- W3015130333 cites W2938635978 @default.
- W3015130333 cites W2944467232 @default.
- W3015130333 cites W2948260310 @default.
- W3015130333 cites W2962976171 @default.
- W3015130333 cites W2963315828 @default.
- W3015130333 cites W2964260135 @default.
- W3015130333 cites W3025832928 @default.
- W3015130333 cites W914561379 @default.
- W3015130333 doi "https://doi.org/10.1007/s13369-020-04481-y" @default.
- W3015130333 hasPublicationYear "2020" @default.
- W3015130333 type Work @default.
- W3015130333 sameAs 3015130333 @default.
- W3015130333 citedByCount "5" @default.
- W3015130333 countsByYear W30151303332020 @default.
- W3015130333 countsByYear W30151303332021 @default.
- W3015130333 countsByYear W30151303332022 @default.
- W3015130333 countsByYear W30151303332023 @default.
- W3015130333 crossrefType "journal-article" @default.
- W3015130333 hasAuthorship W3015130333A5000226831 @default.
- W3015130333 hasAuthorship W3015130333A5001618284 @default.
- W3015130333 hasAuthorship W3015130333A5040966283 @default.
- W3015130333 hasAuthorship W3015130333A5059502259 @default.
- W3015130333 hasBestOaLocation W30151303332 @default.
- W3015130333 hasConcept C11413529 @default.
- W3015130333 hasConcept C115961682 @default.
- W3015130333 hasConcept C153180895 @default.
- W3015130333 hasConcept C154945302 @default.
- W3015130333 hasConcept C155512373 @default.
- W3015130333 hasConcept C17426736 @default.
- W3015130333 hasConcept C17744445 @default.
- W3015130333 hasConcept C190470478 @default.
- W3015130333 hasConcept C199539241 @default.
- W3015130333 hasConcept C2776359362 @default.
- W3015130333 hasConcept C2777212361 @default.
- W3015130333 hasConcept C2987834672 @default.