{"id":{"repo_id":"missouri","oai_identifier":"oai:mospace.umsystem.edu:10355/14908"},"canonical_url":"https://search.dev.ndltd.org/etd/missouri/oai:mospace.umsystem.edu:10355/14908","repository":{"repo_id":"missouri","name":"University of Missouri","base_url":"https://mospace.umsystem.edu/oai/request"},"display":{"title":"Action recognition via sequence embedding","abstract":"[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI-COLUMBIA AT AUTHOR'S REQUEST.] A comb structural exemplar embedding based approach is introduced for action recognition. We propose a new framework to represent an action as a weak classifier pool. During training, firstly, construct a set of static comb structural exemplars from training data; then convolve each exemplar on the training action video; later on, construct a weak classifier pool from minimum distances between the templates and the action sequence. In order to capture both shape and motion features, we employ three different kinds of image representation method, such as edge detection, Histogram of Oriented Gradients (HOG) and Histogram of Optical Flow (HOF). After capturing shape and motion features, salient weak classifiers are picked up by AdaBoost algorithm. Our approach enables robust action recognition in very challenging situations and the framework is validated based on four public standard datasets: the Weizmann dataset, the KTH dataset, IXMAS multi-view dataset and Rochester. Our extensive experimental results from those four datasets are state-of-the-art in terms of performance, tolerance to noise and viewpoints, and robustness across different subjects and datasets.","abstract_html":"[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI-COLUMBIA AT AUTHOR'S REQUEST.] A comb structural exemplar embedding based approach is introduced for action recognition. We propose a new framework to represent an action as a weak classifier pool. During training, firstly, construct a set of static comb structural exemplars from training data; then convolve each exemplar on the training action video; later on, construct a weak classifier pool from minimum distances between the templates and the action sequence. In order to capture both shape and motion features, we employ three different kinds of image representation method, such as edge detection, Histogram of Oriented Gradients (HOG) and Histogram of Optical Flow (HOF). After capturing shape and motion features, salient weak classifiers are picked up by AdaBoost algorithm. Our approach enables robust action recognition in very challenging situations and the framework is validated based on four public standard datasets: the Weizmann dataset, the KTH dataset, IXMAS multi-view dataset and Rochester. Our extensive experimental results from those four datasets are state-of-the-art in terms of performance, tolerance to noise and viewpoints, and robustness across different subjects and datasets.","abstract_has_math":false,"creators":["Gong, Wei"],"institution":"University of Missouri--Columbia","degree_name":"M.S.","degree_level":"Masters","degree_discipline":"Computer engineering (MU)","degree_department":null,"school":null,"contributors":[],"advisors":["Han, Xu (Tony Xu)"],"committee_chairs":[],"committee_members":[],"year":2011,"date_issued":"2011","date_published":"2011","updated_at":"2026-07-24T03:09:39Z","subjects":["computer vision","action recognition","machine learning"],"languages":["eng","English"],"rights":["Access to files is limited to the University of Missouri--Columbia with SSO login."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/10355/14908","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Han, Xu (Tony Xu)"]},{"key":"dc:creator","label":"Author","values":["Gong, Wei"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2012-08-23T15:18:33Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2012-08-23T15:18:33Z"]},{"key":"dc:date.issued","label":"Date","values":["2011"]},{"key":"dc:publisher","label":"Institution","values":["University of Missouri--Columbia"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer engineering (MU)"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Missouri--Columbia"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["computer vision","action recognition","machine learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]},{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Access to files is limited to the University of Missouri--Columbia with SSO login."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/10355/14908"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Title from PDF of title page (University of Missouri--Columbia, viewed on August 23, 2012).","The entire thesis text is included in the research.pdf file; the official abstract appears in the short.pdf file; a non-technical public abstract appears in the public.pdf file.","Thesis advisor: Dr. Tony Han","Includes bibliographical references.","M.S. University of Missouri--Columbia 2011.","\"May 2011\""]},{"key":"dc:description.abstract","label":"Abstract","values":["[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI-COLUMBIA AT AUTHOR'S REQUEST.] A comb structural exemplar embedding based approach is introduced for action recognition. We propose a new framework to represent an action as a weak classifier pool. During training, firstly, construct a set of static comb structural exemplars from training data; then convolve each exemplar on the training action video; later on, construct a weak classifier pool from minimum distances between the templates and the action sequence. In order to capture both shape and motion features, we employ three different kinds of image representation method, such as edge detection, Histogram of Oriented Gradients (HOG) and Histogram of Optical Flow (HOF). After capturing shape and motion features, salient weak classifiers are picked up by AdaBoost algorithm. Our approach enables robust action recognition in very challenging situations and the framework is validated based on four public standard datasets: the Weizmann dataset, the KTH dataset, IXMAS multi-view dataset and Rochester. Our extensive experimental results from those four datasets are state-of-the-art in terms of performance, tolerance to noise and viewpoints, and robustness across different subjects and datasets."]},{"key":"dc:title","label":"Title","values":["Action recognition via sequence embedding"]}]}],"canonical_facts":{"dc:contributor.advisor":["Han, Xu (Tony Xu)"],"dc:creator":["Gong, Wei"],"dc:date.accessioned":["2012-08-23T15:18:33Z"],"dc:date.available":["2012-08-23T15:18:33Z"],"dc:date.issued":["2011"],"dc:description":["Title from PDF of title page (University of Missouri--Columbia, viewed on August 23, 2012).","The entire thesis text is included in the research.pdf file; the official abstract appears in the short.pdf file; a non-technical public abstract appears in the public.pdf file.","Thesis advisor: Dr. Tony Han","Includes bibliographical references.","M.S. University of Missouri--Columbia 2011.","\"May 2011\""],"dc:description.abstract":["[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI-COLUMBIA AT AUTHOR'S REQUEST.] A comb structural exemplar embedding based approach is introduced for action recognition. We propose a new framework to represent an action as a weak classifier pool. During training, firstly, construct a set of static comb structural exemplars from training data; then convolve each exemplar on the training action video; later on, construct a weak classifier pool from minimum distances between the templates and the action sequence. In order to capture both shape and motion features, we employ three different kinds of image representation method, such as edge detection, Histogram of Oriented Gradients (HOG) and Histogram of Optical Flow (HOF). After capturing shape and motion features, salient weak classifiers are picked up by AdaBoost algorithm. Our approach enables robust action recognition in very challenging situations and the framework is validated based on four public standard datasets: the Weizmann dataset, the KTH dataset, IXMAS multi-view dataset and Rochester. Our extensive experimental results from those four datasets are state-of-the-art in terms of performance, tolerance to noise and viewpoints, and robustness across different subjects and datasets."],"dc:identifier.uri":["http://hdl.handle.net/10355/14908"],"dc:language":["English"],"dc:language.iso":["eng"],"dc:publisher":["University of Missouri--Columbia"],"dc:rights":["Access to files is limited to the University of Missouri--Columbia with SSO login."],"dc:subject":["computer vision","action recognition","machine learning"],"dc:title":["Action recognition via sequence embedding"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer engineering (MU)"],"thesis:degree_level":["Masters"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Missouri--Columbia"]},"updated_at":"2026-07-24T03:09:39Z"}