FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2904658540> ?p ?o ?g. }

• W2904658540 abstract "Existing methods in video action recognition mostly do not distinguish human body from the environment and easily overfit the scenes and objects. In this work, we present a conceptually simple, general and high-performance framework for action recognition in trimmed videos, aiming at person-centric modeling. The method, called Action Machine, takes as inputs the videos cropped by person bounding boxes. It extends the Inflated 3D ConvNet (I3D) by adding a branch for human pose estimation and a 2D CNN for pose-based action recognition, being fast to train and test. Action Machine can benefit from the multi-task training of action recognition and pose estimation, the fusion of predictions from RGB images and poses. On NTU RGB-D, Action Machine achieves the state-of-the-art performance with top-1 accuracies of 97.2% and 94.3% on cross-view and cross-subject respectively. Action Machine also achieves competitive performance on another three smaller action recognition datasets: Northwestern UCLA Multiview Action3D, MSR Daily Activity3D and UTD-MHAD. Code will be made available." @default.
• W2904658540 created "2018-12-22" @default.
• W2904658540 creator A5001262405 @default.
• W2904658540 creator A5007272888 @default.
• W2904658540 creator A5034524446 @default.
• W2904658540 creator A5036237500 @default.
• W2904658540 creator A5037501616 @default.
• W2904658540 creator A5039762134 @default.
• W2904658540 creator A5044985818 @default.
• W2904658540 creator A5051049837 @default.
• W2904658540 creator A5059915555 @default.
• W2904658540 date "2018-12-13" @default.
• W2904658540 modified "2023-09-23" @default.
• W2904658540 title "Action Machine: Rethinking Action Recognition in Trimmed Videos" @default.
• W2904658540 cites W1950788856 @default.
• W2904658540 cites W1983592444 @default.
• W2904658540 cites W2034014085 @default.
• W2904658540 cites W2048821851 @default.
• W2904658540 cites W2078885226 @default.
• W2904658540 cites W2108598243 @default.
• W2904658540 cites W2126579184 @default.
• W2904658540 cites W2143267104 @default.
• W2904658540 cites W2162033023 @default.
• W2904658540 cites W2186615578 @default.
• W2904658540 cites W2245620145 @default.
• W2904658540 cites W2255781698 @default.
• W2904658540 cites W2296311849 @default.
• W2904658540 cites W2342311830 @default.
• W2904658540 cites W24089286 @default.
• W2904658540 cites W2415469094 @default.
• W2904658540 cites W2507009361 @default.
• W2904658540 cites W2510185399 @default.
• W2904658540 cites W2526041356 @default.
• W2904658540 cites W2554408731 @default.
• W2904658540 cites W2593146028 @default.
• W2904658540 cites W2605111198 @default.
• W2904658540 cites W2613570903 @default.
• W2904658540 cites W2765277449 @default.
• W2904658540 cites W2769331938 @default.
• W2904658540 cites W2769678843 @default.
• W2904658540 cites W2770201307 @default.
• W2904658540 cites W2778523960 @default.
• W2904658540 cites W2784435047 @default.
• W2904658540 cites W2788865504 @default.
• W2904658540 cites W2789011059 @default.
• W2904658540 cites W2799026629 @default.
• W2904658540 cites W2799211965 @default.
• W2904658540 cites W2805042136 @default.
• W2904658540 cites W2886078012 @default.
• W2904658540 cites W2887051120 @default.
• W2904658540 cites W2902905147 @default.
• W2904658540 cites W2949117887 @default.
• W2904658540 cites W2949462896 @default.
• W2904658540 cites W2949650786 @default.
• W2904658540 cites W2950328304 @default.
• W2904658540 cites W2950477723 @default.
• W2904658540 cites W2950762923 @default.
• W2904658540 cites W2951805656 @default.
• W2904658540 cites W2952045486 @default.
• W2904658540 cites W2952186347 @default.
• W2904658540 cites W2952587893 @default.
• W2904658540 cites W2952633803 @default.
• W2904658540 cites W2953106684 @default.
• W2904658540 cites W2953330232 @default.
• W2904658540 cites W2963402313 @default.
• W2904658540 cites W2963524571 @default.
• W2904658540 cites W3098538019 @default.
• W2904658540 cites W3103858256 @default.
• W2904658540 doi "https://doi.org/10.48550/arxiv.1812.05770" @default.
• W2904658540 hasPublicationYear "2018" @default.
• W2904658540 type Work @default.
• W2904658540 sameAs 2904658540 @default.
• W2904658540 citedByCount "6" @default.
• W2904658540 countsByYear W29046585402019 @default.
• W2904658540 countsByYear W29046585402021 @default.
• W2904658540 crossrefType "posted-content" @default.
• W2904658540 hasAuthorship W2904658540A5001262405 @default.
• W2904658540 hasAuthorship W2904658540A5007272888 @default.
• W2904658540 hasAuthorship W2904658540A5034524446 @default.
• W2904658540 hasAuthorship W2904658540A5036237500 @default.
• W2904658540 hasAuthorship W2904658540A5037501616 @default.
• W2904658540 hasAuthorship W2904658540A5039762134 @default.
• W2904658540 hasAuthorship W2904658540A5044985818 @default.
• W2904658540 hasAuthorship W2904658540A5051049837 @default.
• W2904658540 hasAuthorship W2904658540A5059915555 @default.
• W2904658540 hasBestOaLocation W29046585401 @default.
• W2904658540 hasConcept C115961682 @default.
• W2904658540 hasConcept C119857082 @default.
• W2904658540 hasConcept C121332964 @default.
• W2904658540 hasConcept C147037132 @default.
• W2904658540 hasConcept C153180895 @default.
• W2904658540 hasConcept C154945302 @default.
• W2904658540 hasConcept C162324750 @default.
• W2904658540 hasConcept C177264268 @default.
• W2904658540 hasConcept C187736073 @default.
• W2904658540 hasConcept C199360897 @default.
• W2904658540 hasConcept C22019652 @default.
• W2904658540 hasConcept C2776760102 @default.
• W2904658540 hasConcept C2777212361 @default.
• W2904658540 hasConcept C2780451532 @default.

• next