FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4361247902> ?p ?o ?g. }

• W4361247902 endingPage "186" @default.
• W4361247902 startingPage "164" @default.
• W4361247902 abstract "Skeleton-based action recognition has rapidly become one of the most popular and essential research topics in computer vision. The task is to analyze the characteristics of human joints and accurately classify their behaviors through deep learning technology. Skeleton provides numerous unique advantages over other data modalities, such as robustness, compactness, noise immunity, etc. In particular, the skeleton modality is extremely lightweight, which is especially beneficial for deep learning research in low-resource environments. Due to the non-European nature of skeleton data, Graph Convolution Network (GCN) has become mainstream in the past few years, leveraging the benefits of processing topological information. However, with the explosive development of transformer methods in natural language processing and computer vision, many works have applied transformer into the field of skeleton action recognition, breaking the accuracy monopoly of GCN. Therefore, we conduct a survey using transformer method for skeleton-based action recognition, forming of a taxonomy on existing works. This paper gives a comprehensive overview of the recent transformer techniques for skeleton action recognition, proposes a taxonomy of transformer-style techniques for action recognition, conducts a detailed study on benchmark datasets, compares the algorithm accuracy of standard methods, and finally discusses the future research directions and trends. To the best of our knowledge, this study is the first to describe skeleton-based action recognition techniques in the style of transformers and to suggest novel recognition taxonomies in a review. We are confident that Transformer-based action recognition technology will become mainstream in the near future, so this survey aims to help researchers systematically learn core tasks, select appropriate datasets, understand current challenges, and select promising future directions." @default.
• W4361247902 created "2023-03-31" @default.
• W4361247902 creator A5008659449 @default.
• W4361247902 creator A5019315893 @default.
• W4361247902 creator A5051643079 @default.
• W4361247902 creator A5052676364 @default.
• W4361247902 creator A5059866451 @default.
• W4361247902 creator A5080566166 @default.
• W4361247902 date "2023-06-01" @default.
• W4361247902 modified "2023-10-12" @default.
• W4361247902 title "Transformer for Skeleton-based action recognition: A review of recent advances" @default.
• W4361247902 cites W1874503286 @default.
• W4361247902 cites W2054041160 @default.
• W4361247902 cites W2058256495 @default.
• W4361247902 cites W2079447555 @default.
• W4361247902 cites W2086663212 @default.
• W4361247902 cites W2184544926 @default.
• W4361247902 cites W2235034809 @default.
• W4361247902 cites W2344034899 @default.
• W4361247902 cites W2537988662 @default.
• W4361247902 cites W2558630670 @default.
• W4361247902 cites W2559085405 @default.
• W4361247902 cites W2606294640 @default.
• W4361247902 cites W2755876276 @default.
• W4361247902 cites W2765433083 @default.
• W4361247902 cites W2788388592 @default.
• W4361247902 cites W2810685774 @default.
• W4361247902 cites W2892614179 @default.
• W4361247902 cites W2908279665 @default.
• W4361247902 cites W2916798096 @default.
• W4361247902 cites W2935497007 @default.
• W4361247902 cites W2943389014 @default.
• W4361247902 cites W2944006115 @default.
• W4361247902 cites W2948058585 @default.
• W4361247902 cites W2963076818 @default.
• W4361247902 cites W2963563276 @default.
• W4361247902 cites W2964087927 @default.
• W4361247902 cites W2964094092 @default.
• W4361247902 cites W2964134613 @default.
• W4361247902 cites W2964192819 @default.
• W4361247902 cites W2971680695 @default.
• W4361247902 cites W2981578854 @default.
• W4361247902 cites W2990503944 @default.
• W4361247902 cites W2991376513 @default.
• W4361247902 cites W2998549866 @default.
• W4361247902 cites W3000347952 @default.
• W4361247902 cites W3006198072 @default.
• W4361247902 cites W3014731553 @default.
• W4361247902 cites W3028433894 @default.
• W4361247902 cites W3029267566 @default.
• W4361247902 cites W3034548564 @default.
• W4361247902 cites W3034999503 @default.
• W4361247902 cites W3035050855 @default.
• W4361247902 cites W3035225512 @default.
• W4361247902 cites W3080358492 @default.
• W4361247902 cites W3084215704 @default.
• W4361247902 cites W3086544482 @default.
• W4361247902 cites W3088102655 @default.
• W4361247902 cites W3092336341 @default.
• W4361247902 cites W3092382593 @default.
• W4361247902 cites W3092799791 @default.
• W4361247902 cites W3093411241 @default.
• W4361247902 cites W3094795122 @default.
• W4361247902 cites W3119427296 @default.
• W4361247902 cites W3121874414 @default.
• W4361247902 cites W3127089628 @default.
• W4361247902 cites W3129366157 @default.
• W4361247902 cites W3130191949 @default.
• W4361247902 cites W3135191333 @default.
• W4361247902 cites W3137592945 @default.
• W4361247902 cites W3138674438 @default.
• W4361247902 cites W3138697035 @default.
• W4361247902 cites W3145450063 @default.
• W4361247902 cites W3146918276 @default.
• W4361247902 cites W3156509901 @default.
• W4361247902 cites W3157441214 @default.
• W4361247902 cites W3159212182 @default.
• W4361247902 cites W3160967194 @default.
• W4361247902 cites W3169413442 @default.
• W4361247902 cites W3170480636 @default.
• W4361247902 cites W3174053790 @default.
• W4361247902 cites W3174415351 @default.
• W4361247902 cites W3174836262 @default.
• W4361247902 cites W3175080943 @default.
• W4361247902 cites W3177319367 @default.
• W4361247902 cites W3178066030 @default.
• W4361247902 cites W3179667740 @default.
• W4361247902 cites W3183399135 @default.
• W4361247902 cites W3189271170 @default.
• W4361247902 cites W3194397797 @default.
• W4361247902 cites W3194512065 @default.
• W4361247902 cites W3195639294 @default.
• W4361247902 cites W3201247567 @default.
• W4361247902 cites W3202944637 @default.
• W4361247902 cites W3203514840 @default.
• W4361247902 cites W3203634062 @default.
• W4361247902 cites W3204239658 @default.
• W4361247902 cites W3205032456 @default.

• next