FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2009597984> ?p ?o ?g. }

• W2009597984 abstract "Human action recognition has emerged as an important field in the computer vision community due to its large number of applications such as automatic video surveillance, content based video-search and human robot interaction. In order to cope with the challenges that this large variety of applications present, recent research has focused more on developing classifiers able to detect several actions in more natural and unconstrained video sequences. The invariance discrimination tradeoff in action recognition has been addressed by utilizing a Generalized Hough Transform. As a basis for action representation we transform 3D poses into a robust feature space, referred to as pose descriptors. For each action class a one-dimensional temporal voting space is constructed. Votes are generated from associating pose descriptors with their position in time relative to the end of an action sequence. Training data consists of manually segmented action sequences. In the detection phase valid human 3D poses are assumed as input, e.g. originating from 3D sensors or monocular pose reconstruction methods. The human 3D poses are normalized to gain view-independence and transformed into (i) relative limb-angle space to ensure independence of non-adjacent joints or (ii) geometric features. In (i) an action descriptor consists of the relative angles between limbs and their temporal derivatives. In (ii) the action descriptor consists of different geometric features. In order to circumvent the problem of time-warping we propose to use a codebook of prototypical 3D poses which is generated from sample sequences of 3D motion capture data. This idea is in accordance with the concept of equivalence classes in action space. Results of the codebook method are presented using the Kinect sensor and the CMU Motion Capture Database." @default.
• W2009597984 created "2016-06-24" @default.
• W2009597984 creator A5000041406 @default.
• W2009597984 creator A5005612161 @default.
• W2009597984 creator A5058180931 @default.
• W2009597984 date "2014-10-07" @default.
• W2009597984 modified "2023-09-23" @default.
• W2009597984 title "Generalized Hough transform based time invariant action recognition with 3D pose information" @default.
• W2009597984 cites W1979606776 @default.
• W2009597984 cites W1995444699 @default.
• W2009597984 cites W1997500560 @default.
• W2009597984 cites W2056339039 @default.
• W2009597984 cites W2073605108 @default.
• W2009597984 cites W2083808208 @default.
• W2009597984 cites W2086001523 @default.
• W2009597984 cites W2093655440 @default.
• W2009597984 cites W2098339052 @default.
• W2009597984 cites W2099634219 @default.
• W2009597984 cites W2106255337 @default.
• W2009597984 cites W2106996050 @default.
• W2009597984 cites W2136853139 @default.
• W2009597984 cites W2142194269 @default.
• W2009597984 cites W2155268664 @default.
• W2009597984 cites W2160429843 @default.
• W2009597984 cites W22745672 @default.
• W2009597984 cites W607820920 @default.
• W2009597984 cites W85465870 @default.
• W2009597984 doi "https://doi.org/10.1117/12.2065805" @default.
• W2009597984 hasPublicationYear "2014" @default.
• W2009597984 type Work @default.
• W2009597984 sameAs 2009597984 @default.
• W2009597984 citedByCount "0" @default.
• W2009597984 crossrefType "proceedings-article" @default.
• W2009597984 hasAuthorship W2009597984A5000041406 @default.
• W2009597984 hasAuthorship W2009597984A5005612161 @default.
• W2009597984 hasAuthorship W2009597984A5058180931 @default.
• W2009597984 hasBestOaLocation W20095979842 @default.
• W2009597984 hasConcept C115961682 @default.
• W2009597984 hasConcept C153180895 @default.
• W2009597984 hasConcept C154945302 @default.
• W2009597984 hasConcept C190470478 @default.
• W2009597984 hasConcept C200518788 @default.
• W2009597984 hasConcept C31972630 @default.
• W2009597984 hasConcept C33923547 @default.
• W2009597984 hasConcept C37914503 @default.
• W2009597984 hasConcept C41008148 @default.
• W2009597984 hasConcept C52102323 @default.
• W2009597984 hasConcept C52622490 @default.
• W2009597984 hasConcept C88516994 @default.
• W2009597984 hasConceptScore W2009597984C115961682 @default.
• W2009597984 hasConceptScore W2009597984C153180895 @default.
• W2009597984 hasConceptScore W2009597984C154945302 @default.
• W2009597984 hasConceptScore W2009597984C190470478 @default.
• W2009597984 hasConceptScore W2009597984C200518788 @default.
• W2009597984 hasConceptScore W2009597984C31972630 @default.
• W2009597984 hasConceptScore W2009597984C33923547 @default.
• W2009597984 hasConceptScore W2009597984C37914503 @default.
• W2009597984 hasConceptScore W2009597984C41008148 @default.
• W2009597984 hasConceptScore W2009597984C52102323 @default.
• W2009597984 hasConceptScore W2009597984C52622490 @default.
• W2009597984 hasConceptScore W2009597984C88516994 @default.
• W2009597984 hasLocation W20095979841 @default.
• W2009597984 hasLocation W20095979842 @default.
• W2009597984 hasOpenAccess W2009597984 @default.
• W2009597984 hasPrimaryLocation W20095979841 @default.
• W2009597984 hasRelatedWork W1488959376 @default.
• W2009597984 hasRelatedWork W1561437654 @default.
• W2009597984 hasRelatedWork W1975958833 @default.
• W2009597984 hasRelatedWork W2034295284 @default.
• W2009597984 hasRelatedWork W2076468506 @default.
• W2009597984 hasRelatedWork W2116300362 @default.
• W2009597984 hasRelatedWork W2609035398 @default.
• W2009597984 hasRelatedWork W2744160734 @default.
• W2009597984 hasRelatedWork W2889989850 @default.
• W2009597984 hasRelatedWork W1487047144 @default.
• W2009597984 isParatext "false" @default.
• W2009597984 isRetracted "false" @default.
• W2009597984 magId "2009597984" @default.
• W2009597984 workType "article" @default.