Matches in SemOpenAlex for { <https://semopenalex.org/work/W2582553469> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2582553469 endingPage "1568" @default.
- W2582553469 startingPage "1558" @default.
- W2582553469 abstract "Complex event detection has been progressively researched in recent years for the broad interest of video indexing and retrieval. To fulfill the purpose of event detection, one needs to train a classifier using both positive and negative examples. Current classifier training treats the negative videos as equally negative. However, we notice that many negative videos resemble the positive videos in different degrees. Intuitively, we may capture more informative cues from the negative videos if we assign them fine-grained labels, thus benefiting the classifier learning. Aiming for this, we use a statistical method on both the positive and negative examples to get the decisive attributes of a specific event. Based on these decisive attributes, we assign the fine-grained labels to negative examples to treat them differently for more effective exploitation. The resulting fine-grained labels may be not optimal to capture the discriminative cues from the negative videos. Hence, we propose to jointly optimize the fine-grained labels with the classifier learning, which brings mutual reciprocality. Meanwhile, the labels of positive examples are supposed to remain unchanged. We thus additionally introduce a constraint for this purpose. On the other hand, the state-of-the-art deep convolutional neural network features are leveraged in our approach for event detection to further boost the performance. Extensive experiments on the challenging TRECVID MED 2014 dataset have validated the efficacy of our proposed approach." @default.
- W2582553469 created "2017-02-03" @default.
- W2582553469 creator A5005421447 @default.
- W2582553469 creator A5027063174 @default.
- W2582553469 creator A5027171279 @default.
- W2582553469 creator A5034967388 @default.
- W2582553469 creator A5062546146 @default.
- W2582553469 date "2017-07-01" @default.
- W2582553469 modified "2023-10-18" @default.
- W2582553469 title "The Many Shades of Negativity" @default.
- W2582553469 cites W1950136256 @default.
- W2582553469 cites W1971695614 @default.
- W2582553469 cites W1986397799 @default.
- W2582553469 cites W2007510844 @default.
- W2582553469 cites W2014208121 @default.
- W2582553469 cites W2016053056 @default.
- W2582553469 cites W2018668305 @default.
- W2582553469 cites W2035607533 @default.
- W2582553469 cites W2063438554 @default.
- W2582553469 cites W2083319857 @default.
- W2582553469 cites W2104311745 @default.
- W2582553469 cites W2105101328 @default.
- W2582553469 cites W2130567847 @default.
- W2582553469 cites W2139395976 @default.
- W2582553469 cites W2140095548 @default.
- W2582553469 cites W2140406904 @default.
- W2582553469 cites W2147502347 @default.
- W2582553469 cites W2148809503 @default.
- W2582553469 cites W2164261375 @default.
- W2582553469 cites W2169992457 @default.
- W2582553469 cites W2472345018 @default.
- W2582553469 cites W2520861906 @default.
- W2582553469 cites W2618530766 @default.
- W2582553469 doi "https://doi.org/10.1109/tmm.2017.2659221" @default.
- W2582553469 hasPublicationYear "2017" @default.
- W2582553469 type Work @default.
- W2582553469 sameAs 2582553469 @default.
- W2582553469 citedByCount "63" @default.
- W2582553469 countsByYear W25825534692017 @default.
- W2582553469 countsByYear W25825534692018 @default.
- W2582553469 countsByYear W25825534692019 @default.
- W2582553469 countsByYear W25825534692020 @default.
- W2582553469 countsByYear W25825534692021 @default.
- W2582553469 countsByYear W25825534692022 @default.
- W2582553469 crossrefType "journal-article" @default.
- W2582553469 hasAuthorship W2582553469A5005421447 @default.
- W2582553469 hasAuthorship W2582553469A5027063174 @default.
- W2582553469 hasAuthorship W2582553469A5027171279 @default.
- W2582553469 hasAuthorship W2582553469A5034967388 @default.
- W2582553469 hasAuthorship W2582553469A5062546146 @default.
- W2582553469 hasConcept C119857082 @default.
- W2582553469 hasConcept C153180895 @default.
- W2582553469 hasConcept C154945302 @default.
- W2582553469 hasConcept C41008148 @default.
- W2582553469 hasConcept C75165309 @default.
- W2582553469 hasConcept C81363708 @default.
- W2582553469 hasConcept C95623464 @default.
- W2582553469 hasConcept C97931131 @default.
- W2582553469 hasConceptScore W2582553469C119857082 @default.
- W2582553469 hasConceptScore W2582553469C153180895 @default.
- W2582553469 hasConceptScore W2582553469C154945302 @default.
- W2582553469 hasConceptScore W2582553469C41008148 @default.
- W2582553469 hasConceptScore W2582553469C75165309 @default.
- W2582553469 hasConceptScore W2582553469C81363708 @default.
- W2582553469 hasConceptScore W2582553469C95623464 @default.
- W2582553469 hasConceptScore W2582553469C97931131 @default.
- W2582553469 hasFunder F4320306076 @default.
- W2582553469 hasIssue "7" @default.
- W2582553469 hasLocation W25825534691 @default.
- W2582553469 hasOpenAccess W2582553469 @default.
- W2582553469 hasPrimaryLocation W25825534691 @default.
- W2582553469 hasRelatedWork W1652783584 @default.
- W2582553469 hasRelatedWork W2112343299 @default.
- W2582553469 hasRelatedWork W2404514746 @default.
- W2582553469 hasRelatedWork W2406522397 @default.
- W2582553469 hasRelatedWork W2518599539 @default.
- W2582553469 hasRelatedWork W2905846897 @default.
- W2582553469 hasRelatedWork W2995914718 @default.
- W2582553469 hasRelatedWork W3031552518 @default.
- W2582553469 hasRelatedWork W4319994054 @default.
- W2582553469 hasRelatedWork W564581980 @default.
- W2582553469 hasVolume "19" @default.
- W2582553469 isParatext "false" @default.
- W2582553469 isRetracted "false" @default.
- W2582553469 magId "2582553469" @default.
- W2582553469 workType "article" @default.