{"id":{"repo_id":"usf","oai_identifier":"oai:digitalcommons.usf.edu:etd-7846"},"canonical_url":"https://search.ndltd.org/etd/usf/oai:digitalcommons.usf.edu:etd-7846","repository":{"repo_id":"usf","name":"University of South Florida","base_url":"https://digitalcommons.usf.edu/do/oai/"},"display":{"title":"Semantic Description of Activities in Videos","abstract":"Description of human activities in videos results not only in detection of actions and objects but also in identification of their active semantic relationships in the scene. Towards this broader goal, we present a combinatorial approach that assumes availability of algorithms for detecting and labeling objects and actions, albeit with some errors. Given these uncertain labels and detected objects, we link them into interpretative structures using domain knowledge encoded with concepts of Grenander’s general pattern theory. Here a semantic video description is built using basic units, termed generators, that represent labels of objects or actions. These generators have multiple out-bonds, each associated with either a type of domain semantics, spatial constraints, temporal constraints or image/video evidence. Generators combine between each other, according to a set of pre-defined combination rules that capture domain semantics, to form larger structures known as configurations, which here will be used to represent video descriptions. Such connected structures of generators are called configurations. This framework offers a powerful representational scheme for its flexibility in spanning a space of interpretative structures (configurations) of varying sizes and structural complexity. We impose a probability distribution on the configuration space, with inferences generated using a Markov Chain Monte Carlo-based simulated annealing algorithm. The primary advantage of the approach is that it handles known computer vision challenges – appearance variability, errors in object label annotation, object clutter, simultaneous events, temporal dependency encoding, etc. – without the need for a exponentially- large (labeled) training data set.","abstract_html":"Description of human activities in videos results not only in detection of actions and objects but also in identification of their active semantic relationships in the scene. Towards this broader goal, we present a combinatorial approach that assumes availability of algorithms for detecting and labeling objects and actions, albeit with some errors. Given these uncertain labels and detected objects, we link them into interpretative structures using domain knowledge encoded with concepts of Grenander’s general pattern theory. Here a semantic video description is built using basic units, termed generators, that represent labels of objects or actions. These generators have multiple out-bonds, each associated with either a type of domain semantics, spatial constraints, temporal constraints or image/video evidence. Generators combine between each other, according to a set of pre-defined combination rules that capture domain semantics, to form larger structures known as configurations, which here will be used to represent video descriptions. Such connected structures of generators are called configurations. This framework offers a powerful representational scheme for its flexibility in spanning a space of interpretative structures (configurations) of varying sizes and structural complexity. We impose a probability distribution on the configuration space, with inferences generated using a Markov Chain Monte Carlo-based simulated annealing algorithm. The primary advantage of the approach is that it handles known computer vision challenges – appearance variability, errors in object label annotation, object clutter, simultaneous events, temporal dependency encoding, etc. – without the need for a exponentially- large (labeled) training data set.","abstract_has_math":false,"creators":["Dias Moreira De Souza, Fillipe"],"institution":"University of South Florida","degree_name":"Doctor of Philosophy (Ph.D.)","degree_level":"Dissertation","degree_discipline":"Computer Science and Engineering","degree_department":null,"school":null,"contributors":["Sudeep Sarkar, Ph.D.","Anuj Srivastava, Ph.D.","Dmitry Goldgof, Ph.D.","Rangachar Kasturi, Ph.D.","Rajiv Dubey, Ph.D.","Andrew Raij, Ph.D."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2017,"date_issued":"2017-04-07T07:00:00Z","date_published":"2017-04-07T07:00:00Z","updated_at":"2026-11-19T08:43:00Z","subjects":["Pattern Theory","Video Analysis","Activity Recognition","Graphical Models","Compositional Approach","Applied Mathematics","Artificial Intelligence and Robotics","Computer Sciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usf.edu/etd/6649","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usf.edu/etd/6649","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.usf.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.usf.edu%3Aetd-7846","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Sudeep Sarkar, Ph.D.","Anuj Srivastava, Ph.D.","Dmitry Goldgof, Ph.D.","Rangachar Kasturi, Ph.D.","Rajiv Dubey, Ph.D.","Andrew Raij, Ph.D."]},{"key":"dc:creator","label":"Author","values":["Dias Moreira De Souza, Fillipe"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2017-04-07T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science and Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation","Ph.D."]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy (Ph.D.)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of South Florida"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Pattern Theory","Video Analysis","Activity Recognition","Graphical Models","Compositional Approach","Applied Mathematics","Artificial Intelligence and Robotics","Computer Sciences"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights.license","label":"Dc Rights License","values":["default"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usf.edu/etd/6649"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Description of human activities in videos results not only in detection of actions and objects but also in identification of their active semantic relationships in the scene. Towards this broader goal, we present a combinatorial approach that assumes availability of algorithms for detecting and labeling objects and actions, albeit with some errors. Given these uncertain labels and detected objects, we link them into interpretative structures using domain knowledge encoded with concepts of Grenander’s general pattern theory. Here a semantic video description is built using basic units, termed generators, that represent labels of objects or actions. These generators have multiple out-bonds, each associated with either a type of domain semantics, spatial constraints, temporal constraints or image/video evidence. Generators combine between each other, according to a set of pre-defined combination rules that capture domain semantics, to form larger structures known as configurations, which here will be used to represent video descriptions. Such connected structures of generators are called configurations. This framework offers a powerful representational scheme for its flexibility in spanning a space of interpretative structures (configurations) of varying sizes and structural complexity. We impose a probability distribution on the configuration space, with inferences generated using a Markov Chain Monte Carlo-based simulated annealing algorithm. The primary advantage of the approach is that it handles known computer vision challenges – appearance variability, errors in object label annotation, object clutter, simultaneous events, temporal dependency encoding, etc. – without the need for a exponentially- large (labeled) training data set."]},{"key":"dc:title","label":"Title","values":["Semantic Description of Activities in Videos"]}]}],"canonical_facts":{"dc:contributor":["Sudeep Sarkar, Ph.D.","Anuj Srivastava, Ph.D.","Dmitry Goldgof, Ph.D.","Rangachar Kasturi, Ph.D.","Rajiv Dubey, Ph.D.","Andrew Raij, Ph.D."],"dc:creator":["Dias Moreira De Souza, Fillipe"],"dc:date":["2017-04-07T07:00:00Z"],"dc:description":["Description of human activities in videos results not only in detection of actions and objects but also in identification of their active semantic relationships in the scene. Towards this broader goal, we present a combinatorial approach that assumes availability of algorithms for detecting and labeling objects and actions, albeit with some errors. Given these uncertain labels and detected objects, we link them into interpretative structures using domain knowledge encoded with concepts of Grenander’s general pattern theory. Here a semantic video description is built using basic units, termed generators, that represent labels of objects or actions. These generators have multiple out-bonds, each associated with either a type of domain semantics, spatial constraints, temporal constraints or image/video evidence. Generators combine between each other, according to a set of pre-defined combination rules that capture domain semantics, to form larger structures known as configurations, which here will be used to represent video descriptions. Such connected structures of generators are called configurations. This framework offers a powerful representational scheme for its flexibility in spanning a space of interpretative structures (configurations) of varying sizes and structural complexity. We impose a probability distribution on the configuration space, with inferences generated using a Markov Chain Monte Carlo-based simulated annealing algorithm. The primary advantage of the approach is that it handles known computer vision challenges – appearance variability, errors in object label annotation, object clutter, simultaneous events, temporal dependency encoding, etc. – without the need for a exponentially- large (labeled) training data set."],"dc:identifier":["https://digitalcommons.usf.edu/etd/6649"],"dc:rights.license":["default"],"dc:subject":["Pattern Theory","Video Analysis","Activity Recognition","Graphical Models","Compositional Approach","Applied Mathematics","Artificial Intelligence and Robotics","Computer Sciences"],"dc:title":["Semantic Description of Activities in Videos"],"thesis:degree_discipline":["Computer Science and Engineering"],"thesis:degree_level":["Dissertation","Ph.D."],"thesis:degree_name":["Doctor of Philosophy (Ph.D.)"],"thesis:institution_name":["University of South Florida"]},"updated_at":"2026-11-19T08:43:00Z"}