Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313886487> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4313886487 abstract "Human action recognition has been a hot research for decades, and mainstream supervised frameworks include a feature extraction backbone and a softmax classifier to predict daily human actions. When the number of classes applied to the dataset changes, we must retrain the classifier on the well-trained backbone. This pipeline restricts the generalization and transfer ability of the model due to an extra training period. Moreover, replacing action labels with simple number labels discards useful semantic information and can only receive a meaningless classifier at last. In this work, we present a model SkeletonCLIP for skeleton-based human action recognition. We add an alternative text encoder to extract semantic information from labels while keeping the original sequence encoder. We use dot production to measure the similarities of sequence-text pairs in place of traditional classifier head and cross-entropy loss. Experiments from three human action datasets show that our framework can reach a higher recognition accuracy with the help of semantic information when training the network from scratch. The code has been shown at eunseo-v/SkeletonCLIP." @default.
- W4313886487 created "2023-01-10" @default.
- W4313886487 creator A5009178889 @default.
- W4313886487 creator A5030863883 @default.
- W4313886487 creator A5042936784 @default.
- W4313886487 creator A5067911307 @default.
- W4313886487 creator A5074990944 @default.
- W4313886487 date "2022-12-10" @default.
- W4313886487 modified "2023-09-26" @default.
- W4313886487 title "SkeletonCLIP: Recognizing Skeleton-based Human Actions with Text Prompts" @default.
- W4313886487 cites W1522734439 @default.
- W4313886487 cites W2056898157 @default.
- W4313886487 cites W2126579184 @default.
- W4313886487 cites W2194775991 @default.
- W4313886487 cites W2765433083 @default.
- W4313886487 cites W2792140610 @default.
- W4313886487 cites W2916798096 @default.
- W4313886487 cites W2944006115 @default.
- W4313886487 cites W2948058585 @default.
- W4313886487 cites W2963524571 @default.
- W4313886487 cites W2964134613 @default.
- W4313886487 cites W2990503944 @default.
- W4313886487 cites W3035225512 @default.
- W4313886487 cites W3035524453 @default.
- W4313886487 cites W3113067059 @default.
- W4313886487 cites W3123784868 @default.
- W4313886487 cites W4206004984 @default.
- W4313886487 cites W4281249524 @default.
- W4313886487 cites W4285606530 @default.
- W4313886487 cites W4312245820 @default.
- W4313886487 cites W4312614039 @default.
- W4313886487 cites W4312956471 @default.
- W4313886487 cites W4312980231 @default.
- W4313886487 doi "https://doi.org/10.1109/icsai57119.2022.10005459" @default.
- W4313886487 hasPublicationYear "2022" @default.
- W4313886487 type Work @default.
- W4313886487 citedByCount "0" @default.
- W4313886487 crossrefType "proceedings-article" @default.
- W4313886487 hasAuthorship W4313886487A5009178889 @default.
- W4313886487 hasAuthorship W4313886487A5030863883 @default.
- W4313886487 hasAuthorship W4313886487A5042936784 @default.
- W4313886487 hasAuthorship W4313886487A5067911307 @default.
- W4313886487 hasAuthorship W4313886487A5074990944 @default.
- W4313886487 hasConcept C108583219 @default.
- W4313886487 hasConcept C111919701 @default.
- W4313886487 hasConcept C118505674 @default.
- W4313886487 hasConcept C119857082 @default.
- W4313886487 hasConcept C153180895 @default.
- W4313886487 hasConcept C154945302 @default.
- W4313886487 hasConcept C188441871 @default.
- W4313886487 hasConcept C204321447 @default.
- W4313886487 hasConcept C2777212361 @default.
- W4313886487 hasConcept C2987834672 @default.
- W4313886487 hasConcept C41008148 @default.
- W4313886487 hasConcept C52622490 @default.
- W4313886487 hasConcept C95623464 @default.
- W4313886487 hasConceptScore W4313886487C108583219 @default.
- W4313886487 hasConceptScore W4313886487C111919701 @default.
- W4313886487 hasConceptScore W4313886487C118505674 @default.
- W4313886487 hasConceptScore W4313886487C119857082 @default.
- W4313886487 hasConceptScore W4313886487C153180895 @default.
- W4313886487 hasConceptScore W4313886487C154945302 @default.
- W4313886487 hasConceptScore W4313886487C188441871 @default.
- W4313886487 hasConceptScore W4313886487C204321447 @default.
- W4313886487 hasConceptScore W4313886487C2777212361 @default.
- W4313886487 hasConceptScore W4313886487C2987834672 @default.
- W4313886487 hasConceptScore W4313886487C41008148 @default.
- W4313886487 hasConceptScore W4313886487C52622490 @default.
- W4313886487 hasConceptScore W4313886487C95623464 @default.
- W4313886487 hasFunder F4320321001 @default.
- W4313886487 hasLocation W43138864871 @default.
- W4313886487 hasOpenAccess W4313886487 @default.
- W4313886487 hasPrimaryLocation W43138864871 @default.
- W4313886487 hasRelatedWork W2022996092 @default.
- W4313886487 hasRelatedWork W2188464267 @default.
- W4313886487 hasRelatedWork W2743258233 @default.
- W4313886487 hasRelatedWork W2784352036 @default.
- W4313886487 hasRelatedWork W2807311372 @default.
- W4313886487 hasRelatedWork W2888789309 @default.
- W4313886487 hasRelatedWork W2905846897 @default.
- W4313886487 hasRelatedWork W2977314777 @default.
- W4313886487 hasRelatedWork W4281716632 @default.
- W4313886487 hasRelatedWork W4367598285 @default.
- W4313886487 isParatext "false" @default.
- W4313886487 isRetracted "false" @default.
- W4313886487 workType "article" @default.