{"work":{"id":"f7355d17-2b25-4606-b51d-e07f909d400f","openalex_id":null,"doi":null,"arxiv_id":"2501.15111","raw_key":null,"title":"arXiv preprint arXiv:2501.15111 , year=","authors":null,"authors_text":"HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding , author=","year":2025,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2501.15111","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-07-04T19:20:06.340081+00:00","pith_arxiv_id":null,"created_at":"2026-05-10T08:53:04.274420+00:00","updated_at":"2026-07-04T19:20:06.340081+00:00","title_quality_ok":false,"display_title":"Humanomni: A large vision-speech language model for human-centric video understanding","render_title":"Humanomni: A large vision-speech language model for human-centric video understanding"},"hub":{"state":{"work_id":"f7355d17-2b25-4606-b51d-e07f909d400f","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":16,"external_cited_by_count":null,"distinct_field_count":4,"first_pith_cited_at":"2025-01-09T08:43:57+00:00","last_pith_cited_at":"2026-06-24T02:43:26+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":"2026-08-22T12:49:36.557267+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":1},{"context_role":"baseline","n":1}],"polarity_counts":[{"context_polarity":"background","n":1},{"context_polarity":"baseline","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}