Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310971794> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4310971794 abstract "Recognizing new action categories from a few reference samples is an encouraging research field because the cost of labeling data is expensive. This work presents a method for few-shot (or one-shot) skeleton-based action recognition by fusing temporal and spatial features of actions. Trajectory primitives are proposed to characterize the temporal features, which can be obtained by segmenting and clustering the trajectories of joints. After that, we modify the original dynamic time warping (DTW) algorithm and use it to measure the similarity between trajectory primitive sequences. Besides, we compute the joint angles as spatial feature vectors. Support vector machines (SVM) are used to classify the joint angle vectors. In this way, the temporal distance matrix can be calculated by modified DTW, and the spatial distance matrix can be obtained by trained SVM. Finally, we fuse temporal and spatial distance matrices by adjusting a parameter to improve recognition accuracy. Furthermore, extensive experiments are conducted on three small-scale datasets to verify the effectiveness of our proposed method." @default.
- W4310971794 created "2022-12-21" @default.
- W4310971794 creator A5020870852 @default.
- W4310971794 creator A5030809912 @default.
- W4310971794 creator A5030863883 @default.
- W4310971794 creator A5042936784 @default.
- W4310971794 creator A5044534184 @default.
- W4310971794 date "2022-10-17" @default.
- W4310971794 modified "2023-10-18" @default.
- W4310971794 title "Temporal-spatial Feature Fusion for Few-shot Skeleton-based Action Recognition" @default.
- W4310971794 cites W1981934656 @default.
- W4310971794 cites W2075338093 @default.
- W4310971794 cites W2155195832 @default.
- W4310971794 cites W2156503960 @default.
- W4310971794 cites W2291892784 @default.
- W4310971794 cites W2296311849 @default.
- W4310971794 cites W2573897806 @default.
- W4310971794 cites W2941651142 @default.
- W4310971794 cites W2944006115 @default.
- W4310971794 cites W2963282966 @default.
- W4310971794 cites W3023385002 @default.
- W4310971794 cites W3035374961 @default.
- W4310971794 cites W3038959479 @default.
- W4310971794 cites W3040289276 @default.
- W4310971794 cites W3082666011 @default.
- W4310971794 cites W3158215955 @default.
- W4310971794 cites W3179667740 @default.
- W4310971794 cites W3186213478 @default.
- W4310971794 doi "https://doi.org/10.1109/iecon49645.2022.9968781" @default.
- W4310971794 hasPublicationYear "2022" @default.
- W4310971794 type Work @default.
- W4310971794 citedByCount "0" @default.
- W4310971794 crossrefType "proceedings-article" @default.
- W4310971794 hasAuthorship W4310971794A5020870852 @default.
- W4310971794 hasAuthorship W4310971794A5030809912 @default.
- W4310971794 hasAuthorship W4310971794A5030863883 @default.
- W4310971794 hasAuthorship W4310971794A5042936784 @default.
- W4310971794 hasAuthorship W4310971794A5044534184 @default.
- W4310971794 hasConcept C138885662 @default.
- W4310971794 hasConcept C153180895 @default.
- W4310971794 hasConcept C154945302 @default.
- W4310971794 hasConcept C158525013 @default.
- W4310971794 hasConcept C178790620 @default.
- W4310971794 hasConcept C185592680 @default.
- W4310971794 hasConcept C18969341 @default.
- W4310971794 hasConcept C199360897 @default.
- W4310971794 hasConcept C2776401178 @default.
- W4310971794 hasConcept C2777212361 @default.
- W4310971794 hasConcept C2778344882 @default.
- W4310971794 hasConcept C2987834672 @default.
- W4310971794 hasConcept C31972630 @default.
- W4310971794 hasConcept C41008148 @default.
- W4310971794 hasConcept C41895202 @default.
- W4310971794 hasConcept C52622490 @default.
- W4310971794 hasConceptScore W4310971794C138885662 @default.
- W4310971794 hasConceptScore W4310971794C153180895 @default.
- W4310971794 hasConceptScore W4310971794C154945302 @default.
- W4310971794 hasConceptScore W4310971794C158525013 @default.
- W4310971794 hasConceptScore W4310971794C178790620 @default.
- W4310971794 hasConceptScore W4310971794C185592680 @default.
- W4310971794 hasConceptScore W4310971794C18969341 @default.
- W4310971794 hasConceptScore W4310971794C199360897 @default.
- W4310971794 hasConceptScore W4310971794C2776401178 @default.
- W4310971794 hasConceptScore W4310971794C2777212361 @default.
- W4310971794 hasConceptScore W4310971794C2778344882 @default.
- W4310971794 hasConceptScore W4310971794C2987834672 @default.
- W4310971794 hasConceptScore W4310971794C31972630 @default.
- W4310971794 hasConceptScore W4310971794C41008148 @default.
- W4310971794 hasConceptScore W4310971794C41895202 @default.
- W4310971794 hasConceptScore W4310971794C52622490 @default.
- W4310971794 hasFunder F4320321001 @default.
- W4310971794 hasLocation W43109717941 @default.
- W4310971794 hasOpenAccess W4310971794 @default.
- W4310971794 hasPrimaryLocation W43109717941 @default.
- W4310971794 hasRelatedWork W1504288058 @default.
- W4310971794 hasRelatedWork W2016461833 @default.
- W4310971794 hasRelatedWork W2042470658 @default.
- W4310971794 hasRelatedWork W2144724818 @default.
- W4310971794 hasRelatedWork W2331674254 @default.
- W4310971794 hasRelatedWork W2363843671 @default.
- W4310971794 hasRelatedWork W2534909612 @default.
- W4310971794 hasRelatedWork W2546942002 @default.
- W4310971794 hasRelatedWork W2811390910 @default.
- W4310971794 hasRelatedWork W3131297908 @default.
- W4310971794 isParatext "false" @default.
- W4310971794 isRetracted "false" @default.
- W4310971794 workType "article" @default.