{"id":"https://openalex.org/keywords/vision-language-transformers","display_name":"vision-language transformers","description":"Vision-language transformers are neural network models that use transformer architectures to process and relate visual and textual information in multimodal tasks.","display_name_alternatives":["vision-language transformer","visual-language transformers","visual-linguistic transformers","transformers for vision and language"],"ids":{"openalex":"https://openalex.org/keywords/vision-language-transformers","wikidata":null},"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5547,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5547,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0796,"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"}}],"works_count":168,"cited_by_count":3590,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/vision-language-transformers","updated_date":"2026-11-20T04:06:44","created_date":"2026-09-30T00:00:00"}
