{"id":"https://openalex.org/keywords/videomae","display_name":"VideoMAE","description":"A self-supervised video representation learning method that pretrains a vision transformer by masking and reconstructing video content.","display_name_alternatives":["Video Masked Autoencoders","video masked autoencoder"],"ids":{"openalex":"https://openalex.org/keywords/videomae","wikidata":null},"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.32,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.32,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.1078,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"works_count":177,"cited_by_count":2240,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/videomae","updated_date":"2026-11-22T04:06:09","created_date":"2026-09-30T00:00:00"}
