{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DQH4FNN2DN6H4KTCZARN3ILOH2","short_pith_number":"pith:DQH4FNN2","schema_version":"1.0","canonical_sha256":"1c0fc2b5ba1b7c7e2a62c822dda16e3e85c5fa7fb8c7103a3efc86ef971339e1","source":{"kind":"arxiv","id":"2411.07076","version":3},"attestation_state":"computed","paper":{"title":"StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hanchong Zhang, Jianchao Wu, Ruicheng Le, Yichen He, Yuan Lin, Yuchen Zhang","submitted_at":"2024-11-11T15:51:48Z","abstract_excerpt":"Existing large vision-language models (LVLMs) are largely limited to processing short, seconds-long videos and struggle with generating coherent descriptions for extended video spanning minutes or more. Long video description introduces new challenges, such as consistent character identification and plot-level descriptions incorporating both visual and audio information. To address these, we figure out audio-visual character identification, matching character names to each dialogue, as a key factor. We propose StoryTeller, a system for generating dense descriptions of long videos, incorporatin"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.07076","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-11T15:51:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e155c3f6fad7b0e8bd7504a2ac32b37d4f78557f3fda0114435c718005d48fab","abstract_canon_sha256":"f54024f51fcc527acaf49a7d41c4a5c9a42f92edb9ec22412a8327a55ce4a107"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:29.669526Z","signature_b64":"cSeWF796VzkGFavVfFfgKbYbB7wMNP0gCyGVT24ENcUp6WCTSigw6HdSp3mQxwGDJJdtNaJZBmG5EnPavCI0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c0fc2b5ba1b7c7e2a62c822dda16e3e85c5fa7fb8c7103a3efc86ef971339e1","last_reissued_at":"2026-07-05T11:45:29.668990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:29.668990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hanchong Zhang, Jianchao Wu, Ruicheng Le, Yichen He, Yuan Lin, Yuchen Zhang","submitted_at":"2024-11-11T15:51:48Z","abstract_excerpt":"Existing large vision-language models (LVLMs) are largely limited to processing short, seconds-long videos and struggle with generating coherent descriptions for extended video spanning minutes or more. Long video description introduces new challenges, such as consistent character identification and plot-level descriptions incorporating both visual and audio information. To address these, we figure out audio-visual character identification, matching character names to each dialogue, as a key factor. We propose StoryTeller, a system for generating dense descriptions of long videos, incorporatin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07076","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.07076/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.07076","created_at":"2026-07-05T11:45:29.669055+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.07076v3","created_at":"2026-07-05T11:45:29.669055+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07076","created_at":"2026-07-05T11:45:29.669055+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQH4FNN2DN6H","created_at":"2026-07-05T11:45:29.669055+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQH4FNN2DN6H4KTC","created_at":"2026-07-05T11:45:29.669055+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQH4FNN2","created_at":"2026-07-05T11:45:29.669055+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31075","citing_title":"Task-Focused Memorization for Multimodal Agents","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31069","citing_title":"Towards Effective Long-Video Event Prediction via Multi-Level Event Semantics Mining","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DQH4FNN2DN6H4KTCZARN3ILOH2","json":"https://pith.science/pith/DQH4FNN2DN6H4KTCZARN3ILOH2.json","graph_json":"https://pith.science/api/pith-number/DQH4FNN2DN6H4KTCZARN3ILOH2/graph.json","events_json":"https://pith.science/api/pith-number/DQH4FNN2DN6H4KTCZARN3ILOH2/events.json","paper":"https://pith.science/paper/DQH4FNN2"},"agent_actions":{"view_html":"https://pith.science/pith/DQH4FNN2DN6H4KTCZARN3ILOH2","download_json":"https://pith.science/pith/DQH4FNN2DN6H4KTCZARN3ILOH2.json","view_paper":"https://pith.science/paper/DQH4FNN2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.07076&json=true","fetch_graph":"https://pith.science/api/pith-number/DQH4FNN2DN6H4KTCZARN3ILOH2/graph.json","fetch_events":"https://pith.science/api/pith-number/DQH4FNN2DN6H4KTCZARN3ILOH2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQH4FNN2DN6H4KTCZARN3ILOH2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQH4FNN2DN6H4KTCZARN3ILOH2/action/storage_attestation","attest_author":"https://pith.science/pith/DQH4FNN2DN6H4KTCZARN3ILOH2/action/author_attestation","sign_citation":"https://pith.science/pith/DQH4FNN2DN6H4KTCZARN3ILOH2/action/citation_signature","submit_replication":"https://pith.science/pith/DQH4FNN2DN6H4KTCZARN3ILOH2/action/replication_record"}},"created_at":"2026-07-05T11:45:29.669055+00:00","updated_at":"2026-07-05T11:45:29.669055+00:00"}