FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2559917662> ?p ?o ?g. }

• W2559917662 abstract "Deep learning for human action recognition in videos is making significant progress, but is slowed down by its dependency on expensive manual labeling of large video collections. In this work, we investigate the generation of synthetic training data for action recognition, as it has recently shown promising results for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation and other computer graphics techniques of modern game engines. We generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for Procedural Human Action Videos. It contains a total of 39,982 videos, with more than 1,000 examples for each action of 35 categories. Our approach is not limited to existing motion capture sequences, and we procedurally define 14 synthetic actions. We introduce a deep multi-task representation learning architecture to mix synthetic and real videos, even if the action categories differ. Our experiments on the UCF101 and HMDB51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance, significantly outperforming fine-tuning state-of-the-art unsupervised generative models of videos." @default.
• W2559917662 created "2016-12-16" @default.
• W2559917662 creator A5022076552 @default.
• W2559917662 creator A5070076119 @default.
• W2559917662 creator A5071037008 @default.
• W2559917662 creator A5075018873 @default.
• W2559917662 date "2016-12-02" @default.
• W2559917662 modified "2023-09-27" @default.
• W2559917662 title "Procedural Generation of Videos to Train Deep Action Recognition Networks" @default.
• W2559917662 cites W141900914 @default.
• W2559917662 cites W1529834497 @default.
• W2559917662 cites W1578215370 @default.
• W2559917662 cites W1578985305 @default.
• W2559917662 cites W158943247 @default.
• W2559917662 cites W1592744379 @default.
• W2559917662 cites W1757796397 @default.
• W2559917662 cites W1861492603 @default.
• W2559917662 cites W1926645898 @default.
• W2559917662 cites W1964201035 @default.
• W2559917662 cites W1975533357 @default.
• W2559917662 cites W1987716715 @default.
• W2559917662 cites W2010625607 @default.
• W2559917662 cites W2033547469 @default.
• W2559917662 cites W2036242214 @default.
• W2559917662 cites W2041280778 @default.
• W2559917662 cites W2052583664 @default.
• W2559917662 cites W2059319345 @default.
• W2559917662 cites W2060280062 @default.
• W2559917662 cites W2068611653 @default.
• W2559917662 cites W2079624250 @default.
• W2559917662 cites W2083544878 @default.
• W2559917662 cites W2084341401 @default.
• W2559917662 cites W2095705004 @default.
• W2559917662 cites W2105101328 @default.
• W2559917662 cites W2108004794 @default.
• W2559917662 cites W2108598243 @default.
• W2559917662 cites W2126579184 @default.
• W2559917662 cites W2129091674 @default.
• W2559917662 cites W2132254707 @default.
• W2559917662 cites W2152377484 @default.
• W2559917662 cites W2153062878 @default.
• W2559917662 cites W2165741220 @default.
• W2559917662 cites W2182005629 @default.
• W2559917662 cites W2185084818 @default.
• W2559917662 cites W2190165033 @default.
• W2559917662 cites W2196779496 @default.
• W2559917662 cites W2211115409 @default.
• W2559917662 cites W2264238051 @default.
• W2559917662 cites W2308045930 @default.
• W2559917662 cites W2341569833 @default.
• W2559917662 cites W24089286 @default.
• W2559917662 cites W2414825695 @default.
• W2559917662 cites W2431874326 @default.
• W2559917662 cites W2475287302 @default.
• W2559917662 cites W2492904644 @default.
• W2559917662 cites W2511475724 @default.
• W2559917662 cites W2522340145 @default.
• W2559917662 cites W2553497478 @default.
• W2559917662 cites W2571761409 @default.
• W2559917662 cites W2949099979 @default.
• W2559917662 cites W2949117887 @default.
• W2559917662 cites W2949366274 @default.
• W2559917662 cites W2950025457 @default.
• W2559917662 cites W2950179405 @default.
• W2559917662 cites W2950971447 @default.
• W2559917662 cites W2951384764 @default.
• W2559917662 cites W2951747365 @default.
• W2559917662 cites W2951893483 @default.
• W2559917662 cites W2952186347 @default.
• W2559917662 cites W2952633803 @default.
• W2559917662 cites W2952787450 @default.
• W2559917662 cites W2953084276 @default.
• W2559917662 cites W2953100850 @default.
• W2559917662 cites W2953139137 @default.
• W2559917662 cites W2953248129 @default.
• W2559917662 cites W3037730906 @default.
• W2559917662 cites W3141021069 @default.
• W2559917662 cites W914561379 @default.
• W2559917662 cites W2056732426 @default.
• W2559917662 cites W2623306799 @default.
• W2559917662 hasPublicationYear "2016" @default.
• W2559917662 type Work @default.
• W2559917662 sameAs 2559917662 @default.
• W2559917662 citedByCount "5" @default.
• W2559917662 countsByYear W25599176622017 @default.
• W2559917662 countsByYear W25599176622018 @default.
• W2559917662 countsByYear W25599176622019 @default.
• W2559917662 countsByYear W25599176622020 @default.
• W2559917662 crossrefType "posted-content" @default.
• W2559917662 hasAuthorship W2559917662A5022076552 @default.
• W2559917662 hasAuthorship W2559917662A5070076119 @default.
• W2559917662 hasAuthorship W2559917662A5071037008 @default.
• W2559917662 hasAuthorship W2559917662A5075018873 @default.
• W2559917662 hasConcept C104114177 @default.
• W2559917662 hasConcept C105795698 @default.
• W2559917662 hasConcept C108583219 @default.
• W2559917662 hasConcept C117251300 @default.
• W2559917662 hasConcept C119857082 @default.
• W2559917662 hasConcept C121332964 @default.
• W2559917662 hasConcept C121684516 @default.

• next