{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M7YNJDSNRTK2VDB6XVM5MCPRPF","short_pith_number":"pith:M7YNJDSN","schema_version":"1.0","canonical_sha256":"67f0d48e4d8cd5aa8c3ebd59d609f179468b2d4fb6199a27bc05476d515a92b0","source":{"kind":"arxiv","id":"2403.12035","version":1},"attestation_state":"computed","paper":{"title":"CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Liang, Bojia Zi, Jianan Wang, Kam-Fai Wong, Lei Zhang, Qianyu Chen, Shihao Zhao, Xianbiao Qi, Yukai Shi","submitted_at":"2024-03-18T17:59:27Z","abstract_excerpt":"Recent advancements in video generation have been remarkable, yet many existing methods struggle with issues of consistency and poor text-video alignment. Moreover, the field lacks effective techniques for text-guided video inpainting, a stark contrast to the well-explored domain of text-guided image inpainting. To this end, this paper proposes a novel text-guided video inpainting model that achieves better consistency, controllability and compatibility. Specifically, we introduce a simple but efficient motion capture module to preserve motion consistency, and design an instance-aware region s"},"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":"2403.12035","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T17:59:27Z","cross_cats_sorted":[],"title_canon_sha256":"b43c84f7a248340bf7bacd410495e08339b8e9c3e3dab16cd1845dc6f5c730b2","abstract_canon_sha256":"0b4c321055231bacbfe0e14b93f974b7e092f31be2f56e867fe7180272bbf27c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:35.443619Z","signature_b64":"/kexZ9lmsMLCfKZHQZk4OCvB9m9Qkn+eDgfK6pA+kMVWXZrs9dywf+BHFdNkqutraZpw2DgeG3YfpvrIHU7FCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67f0d48e4d8cd5aa8c3ebd59d609f179468b2d4fb6199a27bc05476d515a92b0","last_reissued_at":"2026-07-05T07:57:35.443099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:35.443099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Liang, Bojia Zi, Jianan Wang, Kam-Fai Wong, Lei Zhang, Qianyu Chen, Shihao Zhao, Xianbiao Qi, Yukai Shi","submitted_at":"2024-03-18T17:59:27Z","abstract_excerpt":"Recent advancements in video generation have been remarkable, yet many existing methods struggle with issues of consistency and poor text-video alignment. Moreover, the field lacks effective techniques for text-guided video inpainting, a stark contrast to the well-explored domain of text-guided image inpainting. To this end, this paper proposes a novel text-guided video inpainting model that achieves better consistency, controllability and compatibility. Specifically, we introduce a simple but efficient motion capture module to preserve motion consistency, and design an instance-aware region s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12035","kind":"arxiv","version":1},"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/2403.12035/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":"2403.12035","created_at":"2026-07-05T07:57:35.443164+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12035v1","created_at":"2026-07-05T07:57:35.443164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12035","created_at":"2026-07-05T07:57:35.443164+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7YNJDSNRTK2","created_at":"2026-07-05T07:57:35.443164+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7YNJDSNRTK2VDB6","created_at":"2026-07-05T07:57:35.443164+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7YNJDSN","created_at":"2026-07-05T07:57:35.443164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.18601","citing_title":"BulletGen: Improving 4D Reconstruction with Bullet-Time Generation","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14556","citing_title":"Controllable Video Object Insertion via Multiview Priors","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M7YNJDSNRTK2VDB6XVM5MCPRPF","json":"https://pith.science/pith/M7YNJDSNRTK2VDB6XVM5MCPRPF.json","graph_json":"https://pith.science/api/pith-number/M7YNJDSNRTK2VDB6XVM5MCPRPF/graph.json","events_json":"https://pith.science/api/pith-number/M7YNJDSNRTK2VDB6XVM5MCPRPF/events.json","paper":"https://pith.science/paper/M7YNJDSN"},"agent_actions":{"view_html":"https://pith.science/pith/M7YNJDSNRTK2VDB6XVM5MCPRPF","download_json":"https://pith.science/pith/M7YNJDSNRTK2VDB6XVM5MCPRPF.json","view_paper":"https://pith.science/paper/M7YNJDSN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12035&json=true","fetch_graph":"https://pith.science/api/pith-number/M7YNJDSNRTK2VDB6XVM5MCPRPF/graph.json","fetch_events":"https://pith.science/api/pith-number/M7YNJDSNRTK2VDB6XVM5MCPRPF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7YNJDSNRTK2VDB6XVM5MCPRPF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7YNJDSNRTK2VDB6XVM5MCPRPF/action/storage_attestation","attest_author":"https://pith.science/pith/M7YNJDSNRTK2VDB6XVM5MCPRPF/action/author_attestation","sign_citation":"https://pith.science/pith/M7YNJDSNRTK2VDB6XVM5MCPRPF/action/citation_signature","submit_replication":"https://pith.science/pith/M7YNJDSNRTK2VDB6XVM5MCPRPF/action/replication_record"}},"created_at":"2026-07-05T07:57:35.443164+00:00","updated_at":"2026-07-05T07:57:35.443164+00:00"}