Matches in SemOpenAlex for { <https://semopenalex.org/work/W2778867171> ?p ?o ?g. }
- W2778867171 endingPage "716" @default.
- W2778867171 startingPage "704" @default.
- W2778867171 abstract "We present a novel framework for finding complex activities matching user-described queries in cluttered surveillance videos. The wide diversity of queries coupled with unavailability of annotated activity data limits our ability to train activity models. To bridge the semantic gap we propose to let users describe an activity as a semantic graph with object attributes and inter-object relationships associated with nodes and edges, respectively. We learn node/edge-level visual predictors during training and, at test-time, propose to retrieve activity by identifying likely locations that match the semantic graph. We formulate a novel CRF based probabilistic activity localization objective that accounts for mis-detections, mis-classifications and track-losses, and outputs a likelihood score for a candidate grounded location of the query in the video. We seek groundings that maximize overall precision and recall. To handle the combinatorial search over all high-probability groundings, we propose a highest precision subgraph matching algorithm. Our method outperforms existing retrieval methods on benchmarked datasets." @default.
- W2778867171 created "2018-01-05" @default.
- W2778867171 creator A5014997567 @default.
- W2778867171 creator A5033934219 @default.
- W2778867171 creator A5038232885 @default.
- W2778867171 creator A5048704387 @default.
- W2778867171 creator A5067363128 @default.
- W2778867171 date "2019-03-01" @default.
- W2778867171 modified "2023-09-23" @default.
- W2778867171 title "Probabilistic Semantic Retrieval for Surveillance Videos With Activity Graphs" @default.
- W2778867171 cites W1544176085 @default.
- W2778867171 cites W1930223417 @default.
- W2778867171 cites W1950136256 @default.
- W2778867171 cites W1971695614 @default.
- W2778867171 cites W1972696612 @default.
- W2778867171 cites W1974318954 @default.
- W2778867171 cites W1982185844 @default.
- W2778867171 cites W2016053056 @default.
- W2778867171 cites W2018668305 @default.
- W2778867171 cites W2021899621 @default.
- W2778867171 cites W2043220995 @default.
- W2778867171 cites W2044330629 @default.
- W2778867171 cites W2075760279 @default.
- W2778867171 cites W2077069816 @default.
- W2778867171 cites W2081899160 @default.
- W2778867171 cites W2086842362 @default.
- W2778867171 cites W2095242101 @default.
- W2778867171 cites W2096422609 @default.
- W2778867171 cites W2100771357 @default.
- W2778867171 cites W2104828970 @default.
- W2778867171 cites W2109463015 @default.
- W2778867171 cites W2142258645 @default.
- W2778867171 cites W2142996775 @default.
- W2778867171 cites W2150979491 @default.
- W2778867171 cites W2165369085 @default.
- W2778867171 cites W2194775991 @default.
- W2778867171 cites W2252355370 @default.
- W2778867171 cites W2256680489 @default.
- W2778867171 cites W2258844511 @default.
- W2778867171 cites W2277448338 @default.
- W2778867171 cites W2293561010 @default.
- W2778867171 cites W2341212498 @default.
- W2778867171 cites W2405223529 @default.
- W2778867171 cites W2563615176 @default.
- W2778867171 cites W2586899202 @default.
- W2778867171 cites W2603203130 @default.
- W2778867171 cites W2623912370 @default.
- W2778867171 cites W2735673432 @default.
- W2778867171 cites W2742256643 @default.
- W2778867171 cites W2746923101 @default.
- W2778867171 cites W2751445731 @default.
- W2778867171 cites W2764138706 @default.
- W2778867171 cites W2766862947 @default.
- W2778867171 cites W2964086552 @default.
- W2778867171 cites W2964275819 @default.
- W2778867171 cites W3101203783 @default.
- W2778867171 cites W3104069527 @default.
- W2778867171 cites W3143107425 @default.
- W2778867171 cites W639708223 @default.
- W2778867171 doi "https://doi.org/10.1109/tmm.2018.2865860" @default.
- W2778867171 hasPublicationYear "2019" @default.
- W2778867171 type Work @default.
- W2778867171 sameAs 2778867171 @default.
- W2778867171 citedByCount "8" @default.
- W2778867171 countsByYear W27788671712019 @default.
- W2778867171 countsByYear W27788671712020 @default.
- W2778867171 countsByYear W27788671712021 @default.
- W2778867171 crossrefType "journal-article" @default.
- W2778867171 hasAuthorship W2778867171A5014997567 @default.
- W2778867171 hasAuthorship W2778867171A5033934219 @default.
- W2778867171 hasAuthorship W2778867171A5038232885 @default.
- W2778867171 hasAuthorship W2778867171A5048704387 @default.
- W2778867171 hasAuthorship W2778867171A5067363128 @default.
- W2778867171 hasBestOaLocation W27788671712 @default.
- W2778867171 hasConcept C105795698 @default.
- W2778867171 hasConcept C119857082 @default.
- W2778867171 hasConcept C124101348 @default.
- W2778867171 hasConcept C127413603 @default.
- W2778867171 hasConcept C132525143 @default.
- W2778867171 hasConcept C154945302 @default.
- W2778867171 hasConcept C165064840 @default.
- W2778867171 hasConcept C200601418 @default.
- W2778867171 hasConcept C23123220 @default.
- W2778867171 hasConcept C2780505938 @default.
- W2778867171 hasConcept C33923547 @default.
- W2778867171 hasConcept C41008148 @default.
- W2778867171 hasConcept C49937458 @default.
- W2778867171 hasConcept C80444323 @default.
- W2778867171 hasConcept C81669768 @default.
- W2778867171 hasConceptScore W2778867171C105795698 @default.
- W2778867171 hasConceptScore W2778867171C119857082 @default.
- W2778867171 hasConceptScore W2778867171C124101348 @default.
- W2778867171 hasConceptScore W2778867171C127413603 @default.
- W2778867171 hasConceptScore W2778867171C132525143 @default.
- W2778867171 hasConceptScore W2778867171C154945302 @default.
- W2778867171 hasConceptScore W2778867171C165064840 @default.
- W2778867171 hasConceptScore W2778867171C200601418 @default.
- W2778867171 hasConceptScore W2778867171C23123220 @default.