{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TYKR2AQOGP7Q6IO3UWC7YMPNQQ","short_pith_number":"pith:TYKR2AQO","schema_version":"1.0","canonical_sha256":"9e151d020e33ff0f21dba585fc31ed840158accfc21e457ae2cae286c5119890","source":{"kind":"arxiv","id":"2403.12042","version":2},"attestation_state":"computed","paper":{"title":"Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunming Qiao, Dongdong Chen, Gang Hua, Junsong Yuan, Xuelu Feng, Zixin Zhu","submitted_at":"2024-03-18T17:59:58Z","abstract_excerpt":"In this paper, we explore the visual representations produced from a pre-trained text-to-video (T2V) diffusion model for video understanding tasks. We hypothesize that the latent representation learned from a pretrained generative T2V model encapsulates rich semantics and coherent temporal correspondences, thereby naturally facilitating video understanding. Our hypothesis is validated through the classic referring video object segmentation (R-VOS) task. We introduce a novel framework, termed \"VD-IT\", tailored with dedicatedly designed components built upon a fixed pretrained T2V model. Specifi"},"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":"2403.12042","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T17:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"480f285e7ea35a7db024ecc11ca40050ba98d844026127c07d0b4d3d1a9da925","abstract_canon_sha256":"a9de7b3eea9049a7eca683f209edb9742f3ef3a9c7d0ffa56221f6a7227a94dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:39.657424Z","signature_b64":"XnNR6nVmcQhlNtw+Um+wzBB70kRBVx9HSlp4J46DSXq2SCbEP/nDdjXnKtGvlFlOOpZXV4o2fd/tMb+et8kbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e151d020e33ff0f21dba585fc31ed840158accfc21e457ae2cae286c5119890","last_reissued_at":"2026-07-05T08:40:39.656943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:39.656943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunming Qiao, Dongdong Chen, Gang Hua, Junsong Yuan, Xuelu Feng, Zixin Zhu","submitted_at":"2024-03-18T17:59:58Z","abstract_excerpt":"In this paper, we explore the visual representations produced from a pre-trained text-to-video (T2V) diffusion model for video understanding tasks. We hypothesize that the latent representation learned from a pretrained generative T2V model encapsulates rich semantics and coherent temporal correspondences, thereby naturally facilitating video understanding. Our hypothesis is validated through the classic referring video object segmentation (R-VOS) task. We introduce a novel framework, termed \"VD-IT\", tailored with dedicatedly designed components built upon a fixed pretrained T2V model. Specifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12042","kind":"arxiv","version":2},"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/2403.12042/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":"2403.12042","created_at":"2026-07-05T08:40:39.656991+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12042v2","created_at":"2026-07-05T08:40:39.656991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12042","created_at":"2026-07-05T08:40:39.656991+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYKR2AQOGP7Q","created_at":"2026-07-05T08:40:39.656991+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYKR2AQOGP7Q6IO3","created_at":"2026-07-05T08:40:39.656991+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYKR2AQO","created_at":"2026-07-05T08:40:39.656991+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09646","citing_title":"Do Video Foundation Models Understand Intuitive Physics? A Layerwise Probing Analysis","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18010","citing_title":"Functionalization via Structure Completion and Motion Rectification","ref_index":212,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TYKR2AQOGP7Q6IO3UWC7YMPNQQ","json":"https://pith.science/pith/TYKR2AQOGP7Q6IO3UWC7YMPNQQ.json","graph_json":"https://pith.science/api/pith-number/TYKR2AQOGP7Q6IO3UWC7YMPNQQ/graph.json","events_json":"https://pith.science/api/pith-number/TYKR2AQOGP7Q6IO3UWC7YMPNQQ/events.json","paper":"https://pith.science/paper/TYKR2AQO"},"agent_actions":{"view_html":"https://pith.science/pith/TYKR2AQOGP7Q6IO3UWC7YMPNQQ","download_json":"https://pith.science/pith/TYKR2AQOGP7Q6IO3UWC7YMPNQQ.json","view_paper":"https://pith.science/paper/TYKR2AQO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12042&json=true","fetch_graph":"https://pith.science/api/pith-number/TYKR2AQOGP7Q6IO3UWC7YMPNQQ/graph.json","fetch_events":"https://pith.science/api/pith-number/TYKR2AQOGP7Q6IO3UWC7YMPNQQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYKR2AQOGP7Q6IO3UWC7YMPNQQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYKR2AQOGP7Q6IO3UWC7YMPNQQ/action/storage_attestation","attest_author":"https://pith.science/pith/TYKR2AQOGP7Q6IO3UWC7YMPNQQ/action/author_attestation","sign_citation":"https://pith.science/pith/TYKR2AQOGP7Q6IO3UWC7YMPNQQ/action/citation_signature","submit_replication":"https://pith.science/pith/TYKR2AQOGP7Q6IO3UWC7YMPNQQ/action/replication_record"}},"created_at":"2026-07-05T08:40:39.656991+00:00","updated_at":"2026-07-05T08:40:39.656991+00:00"}