{"work":{"id":"bf38f75f-fbc4-4c6d-ab2a-6e1bcbc38485","openalex_id":null,"doi":null,"arxiv_id":"2407.00634","raw_key":null,"title":"Tarsier: Recipes for training and evaluating large video description models.ArXiv preprint, abs/2407.00634, 2024","authors":null,"authors_text":"Jiawei Wang, Liping Yuan, Yuchen Zhang, and Haomiao Sun","year":2024,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2407.00634","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-06-29T13:23:28.432751+00:00","pith_arxiv_id":null,"created_at":"2026-05-10T23:20:32.953339+00:00","updated_at":"2026-06-29T13:23:28.432751+00:00","title_quality_ok":true,"display_title":"Tarsier: Recipes for training and evaluating large video description models","render_title":"Tarsier: Recipes for training and evaluating large video description models"},"hub":{"state":{"work_id":"bf38f75f-fbc4-4c6d-ab2a-6e1bcbc38485","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":14,"external_cited_by_count":null,"distinct_field_count":1,"first_pith_cited_at":"2024-06-11T17:22:23+00:00","last_pith_cited_at":"2026-05-27T06:27:04+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":"2026-06-30T03:09:31.169775+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3},{"context_role":"dataset","n":1}],"polarity_counts":[{"context_polarity":"background","n":4}],"runs":{},"summary":{},"graph":{},"authors":[]}}