{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MBMALURUCJ2XTXHZCRB6OMMAJM","short_pith_number":"pith:MBMALURU","schema_version":"1.0","canonical_sha256":"605805d234127579dcf91443e731804b1b89080f58352e3be1083ad65006cfb5","source":{"kind":"arxiv","id":"2504.12157","version":3},"attestation_state":"computed","paper":{"title":"FocusedAD: Character-centric Movie Audio Description","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun Wang, Jiajun Bu, Liangcheng Li, Sheng Zhou, Xiaojun Ye, Yiren Song","submitted_at":"2025-04-16T15:04:14Z","abstract_excerpt":"Movie Audio Description (AD) aims to narrate visual content during dialogue-free segments, particularly benefiting blind and visually impaired (BVI) audiences. Compared with general video captioning, AD demands plot-relevant narration with explicit character name references, posing unique challenges in movie understanding.To identify active main characters and focus on storyline-relevant regions, we propose FocusedAD, a novel framework that delivers character-centric movie audio descriptions. It includes: (i) a Character Perception Module(CPM) for tracking character regions and linking them to"},"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":"2504.12157","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-16T15:04:14Z","cross_cats_sorted":[],"title_canon_sha256":"cdb0df78df02c5b87976ad3c26c2f96fa2b348025e50b59569393535c9e81425","abstract_canon_sha256":"63f5556928491f0ebc0eb3f49f40ccdbfca2837bae4855829eb7904e36603ce0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:04.228462Z","signature_b64":"KJCgMWb9Z3Fv+WIDHLXAKpCEHWCCSjRwNo6UYLcy3/eVPipLY1kiEw3CMHar4TKJwNtaVegsoLxL2BYojv56Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"605805d234127579dcf91443e731804b1b89080f58352e3be1083ad65006cfb5","last_reissued_at":"2026-07-05T11:01:04.227951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:04.227951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FocusedAD: Character-centric Movie Audio Description","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun Wang, Jiajun Bu, Liangcheng Li, Sheng Zhou, Xiaojun Ye, Yiren Song","submitted_at":"2025-04-16T15:04:14Z","abstract_excerpt":"Movie Audio Description (AD) aims to narrate visual content during dialogue-free segments, particularly benefiting blind and visually impaired (BVI) audiences. Compared with general video captioning, AD demands plot-relevant narration with explicit character name references, posing unique challenges in movie understanding.To identify active main characters and focus on storyline-relevant regions, we propose FocusedAD, a novel framework that delivers character-centric movie audio descriptions. It includes: (i) a Character Perception Module(CPM) for tracking character regions and linking them to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12157","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/2504.12157/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":"2504.12157","created_at":"2026-07-05T11:01:04.228011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.12157v3","created_at":"2026-07-05T11:01:04.228011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12157","created_at":"2026-07-05T11:01:04.228011+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBMALURUCJ2X","created_at":"2026-07-05T11:01:04.228011+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBMALURUCJ2XTXHZ","created_at":"2026-07-05T11:01:04.228011+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBMALURU","created_at":"2026-07-05T11:01:04.228011+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22766","citing_title":"READ More than What You See: Reinforcement Learning for Accurate and Coherent Audio Description Generations","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MBMALURUCJ2XTXHZCRB6OMMAJM","json":"https://pith.science/pith/MBMALURUCJ2XTXHZCRB6OMMAJM.json","graph_json":"https://pith.science/api/pith-number/MBMALURUCJ2XTXHZCRB6OMMAJM/graph.json","events_json":"https://pith.science/api/pith-number/MBMALURUCJ2XTXHZCRB6OMMAJM/events.json","paper":"https://pith.science/paper/MBMALURU"},"agent_actions":{"view_html":"https://pith.science/pith/MBMALURUCJ2XTXHZCRB6OMMAJM","download_json":"https://pith.science/pith/MBMALURUCJ2XTXHZCRB6OMMAJM.json","view_paper":"https://pith.science/paper/MBMALURU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.12157&json=true","fetch_graph":"https://pith.science/api/pith-number/MBMALURUCJ2XTXHZCRB6OMMAJM/graph.json","fetch_events":"https://pith.science/api/pith-number/MBMALURUCJ2XTXHZCRB6OMMAJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBMALURUCJ2XTXHZCRB6OMMAJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBMALURUCJ2XTXHZCRB6OMMAJM/action/storage_attestation","attest_author":"https://pith.science/pith/MBMALURUCJ2XTXHZCRB6OMMAJM/action/author_attestation","sign_citation":"https://pith.science/pith/MBMALURUCJ2XTXHZCRB6OMMAJM/action/citation_signature","submit_replication":"https://pith.science/pith/MBMALURUCJ2XTXHZCRB6OMMAJM/action/replication_record"}},"created_at":"2026-07-05T11:01:04.228011+00:00","updated_at":"2026-07-05T11:01:04.228011+00:00"}