FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2808087100> ?p ?o ?g. }

• W2808087100 endingPage "172" @default.
• W2808087100 startingPage "157" @default.
• W2808087100 abstract "This paper is focused on video event recognition based on frame level convolutional neural network (CNN) descriptors. Using transfer learning, the image trained descriptors are applied to the video domain to make event recognition feasible in scenarios with limited computational resources. After fine-tuning of the existing CNN concept score extractors, pretrained on ImageNet, the output descriptors of the different fully connected layers are employed as frame descriptors. The resulting descriptors are hierarchically postprocessed and combined with novel and efficient pooling and normalization methods. As major contributions of this paper to the video event recognition, we present a postprocessing scheme in which the hierarchy and the relative shortest distance of concepts in WordNet concept tree is taken into account to alleviate uncertainty of the resulting concept scores at the output of the CNN. Besides, we propose a concept-wise power law normalization method that outperforms the widely used power law normalization. The integration of these approaches results in a high performance average (max) pooling-based video event recognition. Compared to the average (max) pooling combined with the state-of-the-art normalization methods and fine-tuned support vector machine classification, the proposed processing scheme improves the event recognition accuracy in terms of mean average precision over the Columbia consumer video and unstructured social activity attribute datasets, where achieves a pretty comparable result on UCF101 and ActivityNet datasets." @default.
• W2808087100 created "2018-06-21" @default.
• W2808087100 creator A5042186693 @default.
• W2808087100 creator A5043485825 @default.
• W2808087100 date "2019-01-01" @default.
• W2808087100 modified "2023-09-27" @default.
• W2808087100 title "Hierarchical Concept Score Postprocessing and Concept-Wise Normalization in CNN-Based Video Event Recognition" @default.
• W2808087100 cites W1483393862 @default.
• W2808087100 cites W1599709037 @default.
• W2808087100 cites W1783842908 @default.
• W2808087100 cites W1797109199 @default.
• W2808087100 cites W1900913856 @default.
• W2808087100 cites W1927052826 @default.
• W2808087100 cites W1944615693 @default.
• W2808087100 cites W1945129080 @default.
• W2808087100 cites W1950136256 @default.
• W2808087100 cites W1963882359 @default.
• W2808087100 cites W1965555842 @default.
• W2808087100 cites W1965963232 @default.
• W2808087100 cites W1966465480 @default.
• W2808087100 cites W1967503362 @default.
• W2808087100 cites W1967866783 @default.
• W2808087100 cites W1980921654 @default.
• W2808087100 cites W1983364832 @default.
• W2808087100 cites W1986290085 @default.
• W2808087100 cites W2003686830 @default.
• W2808087100 cites W2003723718 @default.
• W2808087100 cites W2012592962 @default.
• W2808087100 cites W2016053056 @default.
• W2808087100 cites W2020163092 @default.
• W2808087100 cites W2024868105 @default.
• W2808087100 cites W2033740597 @default.
• W2808087100 cites W2035192458 @default.
• W2808087100 cites W2056558786 @default.
• W2808087100 cites W2069682406 @default.
• W2808087100 cites W2077692330 @default.
• W2808087100 cites W2081899160 @default.
• W2808087100 cites W2090042335 @default.
• W2808087100 cites W2093367888 @default.
• W2808087100 cites W2097117768 @default.
• W2808087100 cites W2099396217 @default.
• W2808087100 cites W2102544546 @default.
• W2808087100 cites W2105101328 @default.
• W2808087100 cites W2105174364 @default.
• W2808087100 cites W2105516263 @default.
• W2808087100 cites W2108333036 @default.
• W2808087100 cites W2108598243 @default.
• W2808087100 cites W2108603923 @default.
• W2808087100 cites W2109463015 @default.
• W2808087100 cites W2112796928 @default.
• W2808087100 cites W2117539524 @default.
• W2808087100 cites W2119362355 @default.
• W2808087100 cites W2119967926 @default.
• W2808087100 cites W2120588093 @default.
• W2808087100 cites W2121063440 @default.
• W2808087100 cites W2123446250 @default.
• W2808087100 cites W2131042978 @default.
• W2808087100 cites W2142521298 @default.
• W2808087100 cites W2148661353 @default.
• W2808087100 cites W2153635508 @default.
• W2808087100 cites W2160933224 @default.
• W2808087100 cites W2161969291 @default.
• W2808087100 cites W2162762921 @default.
• W2808087100 cites W2164507085 @default.
• W2808087100 cites W2250539671 @default.
• W2808087100 cites W2277448338 @default.
• W2808087100 cites W2294978630 @default.
• W2808087100 cites W2324076434 @default.
• W2808087100 cites W2342543219 @default.
• W2808087100 cites W2415929499 @default.
• W2808087100 cites W2416798379 @default.
• W2808087100 cites W2465921422 @default.
• W2808087100 cites W2469228190 @default.
• W2808087100 cites W2473032611 @default.
• W2808087100 cites W2517731697 @default.
• W2808087100 cites W2520861906 @default.
• W2808087100 cites W2530143578 @default.
• W2808087100 cites W2618530766 @default.
• W2808087100 cites W2739107216 @default.
• W2808087100 cites W2739179773 @default.
• W2808087100 cites W2751445731 @default.
• W2808087100 cites W2951183276 @default.
• W2808087100 cites W2963274633 @default.
• W2808087100 cites W3099326817 @default.
• W2808087100 cites W3101203783 @default.
• W2808087100 cites W318042436 @default.
• W2808087100 cites W4298212933 @default.
• W2808087100 doi "https://doi.org/10.1109/tmm.2018.2844101" @default.
• W2808087100 hasPublicationYear "2019" @default.
• W2808087100 type Work @default.
• W2808087100 sameAs 2808087100 @default.
• W2808087100 citedByCount "13" @default.
• W2808087100 countsByYear W28080871002019 @default.
• W2808087100 countsByYear W28080871002020 @default.
• W2808087100 countsByYear W28080871002021 @default.
• W2808087100 countsByYear W28080871002022 @default.
• W2808087100 countsByYear W28080871002023 @default.
• W2808087100 crossrefType "journal-article" @default.

• next