Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288064503> ?p ?o ?g. }
- W4288064503 endingPage "8634" @default.
- W4288064503 startingPage "8623" @default.
- W4288064503 abstract "3D human action recognition has received increasing attention due to its potential application in video surveillance equipment. To guarantee satisfactory performance, previous studies are mainly based on supervised methods, which have to add a large amount of manual annotation costs. In addition, general deep networks for video sequences suffer from heavy computational costs, thus cannot satisfy the basic requirement of embedded systems. In this paper, a novel Motion Guided Attention Learning (MG-AL) framework is proposed, which formulates the action representation learning as a self-supervised motion attention prediction problem. Specifically, MG-AL is a lightweight network. A set of simple motion priors (e.g., intra-joint variance, inter-frame deviation, intra-joint variance, and cross-joint covariance), which minimizes additional parameters and computational overhead, is regarded as a supervisory signal to guide the attention generation. The encoder is trained via predicting multiple self-attention tasks to capture action-specific feature representations. Extensive evaluations are performed on three challenging benchmark datasets (NTU-RGB+D 60, NTU-RGB+D 120 and NW-UCLA). The proposed method achieves superior performance compared to state-of-the-art methods, while having a very low computational cost." @default.
- W4288064503 created "2022-07-28" @default.
- W4288064503 creator A5003022700 @default.
- W4288064503 creator A5009374796 @default.
- W4288064503 creator A5080689913 @default.
- W4288064503 date "2022-12-01" @default.
- W4288064503 modified "2023-09-27" @default.
- W4288064503 title "Motion Guided Attention Learning for Self-Supervised 3D Human Action Recognition" @default.
- W4288064503 cites W1741037957 @default.
- W4288064503 cites W2054041160 @default.
- W4288064503 cites W2056898157 @default.
- W4288064503 cites W2091911422 @default.
- W4288064503 cites W2284126738 @default.
- W4288064503 cites W2507009361 @default.
- W4288064503 cites W2510185399 @default.
- W4288064503 cites W2526041356 @default.
- W4288064503 cites W2550462002 @default.
- W4288064503 cites W2554408731 @default.
- W4288064503 cites W2603861860 @default.
- W4288064503 cites W2606294640 @default.
- W4288064503 cites W2613570903 @default.
- W4288064503 cites W2778523960 @default.
- W4288064503 cites W2787919227 @default.
- W4288064503 cites W2887297641 @default.
- W4288064503 cites W2893511508 @default.
- W4288064503 cites W2902214002 @default.
- W4288064503 cites W2914868535 @default.
- W4288064503 cites W2940457086 @default.
- W4288064503 cites W2942750779 @default.
- W4288064503 cites W2944006115 @default.
- W4288064503 cites W2946714339 @default.
- W4288064503 cites W2948058585 @default.
- W4288064503 cites W2961553857 @default.
- W4288064503 cites W2963076818 @default.
- W4288064503 cites W2963465695 @default.
- W4288064503 cites W2993496908 @default.
- W4288064503 cites W2997085798 @default.
- W4288064503 cites W3034548564 @default.
- W4288064503 cites W3034999503 @default.
- W4288064503 cites W3035225512 @default.
- W4288064503 cites W3035524453 @default.
- W4288064503 cites W3081111248 @default.
- W4288064503 cites W3092754310 @default.
- W4288064503 cites W3100993552 @default.
- W4288064503 cites W3105195350 @default.
- W4288064503 cites W3114632476 @default.
- W4288064503 cites W3156509901 @default.
- W4288064503 cites W3158576998 @default.
- W4288064503 cites W3173151551 @default.
- W4288064503 cites W3185273257 @default.
- W4288064503 cites W3186755040 @default.
- W4288064503 cites W3193482352 @default.
- W4288064503 cites W3205106480 @default.
- W4288064503 cites W3212618454 @default.
- W4288064503 cites W4200634815 @default.
- W4288064503 cites W4205432963 @default.
- W4288064503 doi "https://doi.org/10.1109/tcsvt.2022.3194350" @default.
- W4288064503 hasPublicationYear "2022" @default.
- W4288064503 type Work @default.
- W4288064503 citedByCount "6" @default.
- W4288064503 countsByYear W42880645032023 @default.
- W4288064503 crossrefType "journal-article" @default.
- W4288064503 hasAuthorship W4288064503A5003022700 @default.
- W4288064503 hasAuthorship W4288064503A5009374796 @default.
- W4288064503 hasAuthorship W4288064503A5080689913 @default.
- W4288064503 hasConcept C104114177 @default.
- W4288064503 hasConcept C111919701 @default.
- W4288064503 hasConcept C118505674 @default.
- W4288064503 hasConcept C119857082 @default.
- W4288064503 hasConcept C13280743 @default.
- W4288064503 hasConcept C136389625 @default.
- W4288064503 hasConcept C153180895 @default.
- W4288064503 hasConcept C154945302 @default.
- W4288064503 hasConcept C185798385 @default.
- W4288064503 hasConcept C205649164 @default.
- W4288064503 hasConcept C2779960059 @default.
- W4288064503 hasConcept C41008148 @default.
- W4288064503 hasConcept C50644808 @default.
- W4288064503 hasConcept C59404180 @default.
- W4288064503 hasConcept C82990744 @default.
- W4288064503 hasConcept C97541855 @default.
- W4288064503 hasConceptScore W4288064503C104114177 @default.
- W4288064503 hasConceptScore W4288064503C111919701 @default.
- W4288064503 hasConceptScore W4288064503C118505674 @default.
- W4288064503 hasConceptScore W4288064503C119857082 @default.
- W4288064503 hasConceptScore W4288064503C13280743 @default.
- W4288064503 hasConceptScore W4288064503C136389625 @default.
- W4288064503 hasConceptScore W4288064503C153180895 @default.
- W4288064503 hasConceptScore W4288064503C154945302 @default.
- W4288064503 hasConceptScore W4288064503C185798385 @default.
- W4288064503 hasConceptScore W4288064503C205649164 @default.
- W4288064503 hasConceptScore W4288064503C2779960059 @default.
- W4288064503 hasConceptScore W4288064503C41008148 @default.
- W4288064503 hasConceptScore W4288064503C50644808 @default.
- W4288064503 hasConceptScore W4288064503C59404180 @default.
- W4288064503 hasConceptScore W4288064503C82990744 @default.
- W4288064503 hasConceptScore W4288064503C97541855 @default.
- W4288064503 hasFunder F4320335777 @default.