{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L3ZLRP3MZCCSHAZNXUX6ARF5D3","short_pith_number":"pith:L3ZLRP3M","schema_version":"1.0","canonical_sha256":"5ef2b8bf6cc88523832dbd2fe044bd1ee0400900ec29b72cdd0abece1faf38e2","source":{"kind":"arxiv","id":"2503.10678","version":1},"attestation_state":"computed","paper":{"title":"VRMDiff: Text-Guided Video Referring Matting Generation of Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daiqing Qi, Jincen Song, Lehan Yang, Sheng Li, Tianlong Wang, Weili Shi, Yuheng Liu","submitted_at":"2025-03-11T06:12:35Z","abstract_excerpt":"We propose a new task, video referring matting, which obtains the alpha matte of a specified instance by inputting a referring caption. We treat the dense prediction task of matting as video generation, leveraging the text-to-video alignment prior of video diffusion models to generate alpha mattes that are temporally coherent and closely related to the corresponding semantic instances. Moreover, we propose a new Latent-Constructive loss to further distinguish different instances, enabling more controllable interactive matting. Additionally, we introduce a large-scale video referring matting da"},"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":"2503.10678","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T06:12:35Z","cross_cats_sorted":[],"title_canon_sha256":"de31924ac6b918d3eed15fb721c57f34643b2b67c335f4a3d0c576297a549f76","abstract_canon_sha256":"cdd50f6ccffb3cdcbf0405e183cd770af09d78389cbd55fe0439c6c864f759ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:03.512527Z","signature_b64":"0bpEykv4gH1KkbpAIHyK6QweJ0sQLAG/hZ/m3YeF9xPmb0+mu3RWIwV4CMHbZBzCTjboViOefDX+LlV2SBQBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ef2b8bf6cc88523832dbd2fe044bd1ee0400900ec29b72cdd0abece1faf38e2","last_reissued_at":"2026-07-05T10:31:03.512032Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:03.512032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VRMDiff: Text-Guided Video Referring Matting Generation of Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daiqing Qi, Jincen Song, Lehan Yang, Sheng Li, Tianlong Wang, Weili Shi, Yuheng Liu","submitted_at":"2025-03-11T06:12:35Z","abstract_excerpt":"We propose a new task, video referring matting, which obtains the alpha matte of a specified instance by inputting a referring caption. We treat the dense prediction task of matting as video generation, leveraging the text-to-video alignment prior of video diffusion models to generate alpha mattes that are temporally coherent and closely related to the corresponding semantic instances. Moreover, we propose a new Latent-Constructive loss to further distinguish different instances, enabling more controllable interactive matting. Additionally, we introduce a large-scale video referring matting da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10678","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/2503.10678/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":"2503.10678","created_at":"2026-07-05T10:31:03.512090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10678v1","created_at":"2026-07-05T10:31:03.512090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10678","created_at":"2026-07-05T10:31:03.512090+00:00"},{"alias_kind":"pith_short_12","alias_value":"L3ZLRP3MZCCS","created_at":"2026-07-05T10:31:03.512090+00:00"},{"alias_kind":"pith_short_16","alias_value":"L3ZLRP3MZCCSHAZN","created_at":"2026-07-05T10:31:03.512090+00:00"},{"alias_kind":"pith_short_8","alias_value":"L3ZLRP3M","created_at":"2026-07-05T10:31:03.512090+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L3ZLRP3MZCCSHAZNXUX6ARF5D3","json":"https://pith.science/pith/L3ZLRP3MZCCSHAZNXUX6ARF5D3.json","graph_json":"https://pith.science/api/pith-number/L3ZLRP3MZCCSHAZNXUX6ARF5D3/graph.json","events_json":"https://pith.science/api/pith-number/L3ZLRP3MZCCSHAZNXUX6ARF5D3/events.json","paper":"https://pith.science/paper/L3ZLRP3M"},"agent_actions":{"view_html":"https://pith.science/pith/L3ZLRP3MZCCSHAZNXUX6ARF5D3","download_json":"https://pith.science/pith/L3ZLRP3MZCCSHAZNXUX6ARF5D3.json","view_paper":"https://pith.science/paper/L3ZLRP3M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10678&json=true","fetch_graph":"https://pith.science/api/pith-number/L3ZLRP3MZCCSHAZNXUX6ARF5D3/graph.json","fetch_events":"https://pith.science/api/pith-number/L3ZLRP3MZCCSHAZNXUX6ARF5D3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L3ZLRP3MZCCSHAZNXUX6ARF5D3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L3ZLRP3MZCCSHAZNXUX6ARF5D3/action/storage_attestation","attest_author":"https://pith.science/pith/L3ZLRP3MZCCSHAZNXUX6ARF5D3/action/author_attestation","sign_citation":"https://pith.science/pith/L3ZLRP3MZCCSHAZNXUX6ARF5D3/action/citation_signature","submit_replication":"https://pith.science/pith/L3ZLRP3MZCCSHAZNXUX6ARF5D3/action/replication_record"}},"created_at":"2026-07-05T10:31:03.512090+00:00","updated_at":"2026-07-05T10:31:03.512090+00:00"}