{"id":"https://openalex.org/keywords/vivit","display_name":"ViViT","description":"A video vision transformer architecture that uses spatiotemporal attention to analyze video, including for action and sign-language recognition.","display_name_alternatives":["video vision transformer"],"ids":{"openalex":"https://openalex.org/keywords/vivit","wikidata":null},"primary_topic":null,"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.1128,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12620","display_name":"Signaling Pathways in Disease","score":0.0887,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"works_count":320,"cited_by_count":4281,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/vivit","updated_date":"2026-11-22T04:06:09","created_date":"2026-09-30T00:00:00"}
