{"work":{"id":"c7602525-8155-4a61-bd4e-abf06c26e6e7","openalex_id":null,"doi":null,"arxiv_id":"2111.12681","raw_key":null,"title":"Violet: End-to-end video-language transformers with masked visual- token modeling,","authors":null,"authors_text":"T","year":2021,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2111.12681","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-07-03T00:57:30.204945+00:00","pith_arxiv_id":null,"created_at":"2026-05-11T05:30:58.154221+00:00","updated_at":"2026-07-03T00:57:30.204945+00:00","title_quality_ok":true,"display_title":"Violet: End-to-end video-language transformers with masked visual-token modeling","render_title":"Violet: End-to-end video-language transformers with masked visual-token modeling"},"hub":{"state":{"work_id":"c7602525-8155-4a61-bd4e-abf06c26e6e7","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":11,"external_cited_by_count":null,"distinct_field_count":2,"first_pith_cited_at":"2022-04-29T16:29:01+00:00","last_pith_cited_at":"2026-04-09T15:10:25+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-28T11:07:15.110809+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3},{"context_role":"baseline","n":1}],"polarity_counts":[{"context_polarity":"background","n":3},{"context_polarity":"baseline","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}