{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L3WCHMTMBQAGMQZGJLHMBCRWOI","short_pith_number":"pith:L3WCHMTM","schema_version":"1.0","canonical_sha256":"5eec23b26c0c006643264acec08a36721a319ff9897011d0c0ae97b029054ebb","source":{"kind":"arxiv","id":"2501.14607","version":2},"attestation_state":"computed","paper":{"title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaolei Tan, Jian-Fang Hu, Jianguo Zhang, Kun-Yu Lin, Tianming Liang, Wei-Shi Zheng","submitted_at":"2025-01-24T16:24:15Z","abstract_excerpt":"Referring video object segmentation (RVOS) aims to segment target objects throughout a video based on a text description. This is challenging as it involves deep vision-language understanding, pixel-level dense prediction and spatiotemporal reasoning. Despite notable progress in recent years, existing methods still exhibit a noticeable gap when considering all these aspects. In this work, we propose \\textbf{ReferDINO}, a strong RVOS model that inherits region-level vision-language alignment from foundational visual grounding models, and is further endowed with pixel-level dense perception and "},"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":"2501.14607","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-24T16:24:15Z","cross_cats_sorted":[],"title_canon_sha256":"8a3071381f729804700bbec1692a88681e1b096aa7e4b033e90d32038ca79fc0","abstract_canon_sha256":"338b23eb2cd04a6f05c4a641414f2f18ca2a14b41279c7dea7ecf1c7283108b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:05.952574Z","signature_b64":"DwPD7I0Yg65A2AD5Dx+3yka+XIytYOtCAW0b33PWRgJqozMFwRGNsfEaKwe6E4XsFChTJdVUfBpk4uEiLYKGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5eec23b26c0c006643264acec08a36721a319ff9897011d0c0ae97b029054ebb","last_reissued_at":"2026-07-05T11:29:05.952093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:05.952093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaolei Tan, Jian-Fang Hu, Jianguo Zhang, Kun-Yu Lin, Tianming Liang, Wei-Shi Zheng","submitted_at":"2025-01-24T16:24:15Z","abstract_excerpt":"Referring video object segmentation (RVOS) aims to segment target objects throughout a video based on a text description. This is challenging as it involves deep vision-language understanding, pixel-level dense prediction and spatiotemporal reasoning. Despite notable progress in recent years, existing methods still exhibit a noticeable gap when considering all these aspects. In this work, we propose \\textbf{ReferDINO}, a strong RVOS model that inherits region-level vision-language alignment from foundational visual grounding models, and is further endowed with pixel-level dense perception and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14607","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/2501.14607/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":"2501.14607","created_at":"2026-07-05T11:29:05.952153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14607v2","created_at":"2026-07-05T11:29:05.952153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14607","created_at":"2026-07-05T11:29:05.952153+00:00"},{"alias_kind":"pith_short_12","alias_value":"L3WCHMTMBQAG","created_at":"2026-07-05T11:29:05.952153+00:00"},{"alias_kind":"pith_short_16","alias_value":"L3WCHMTMBQAGMQZG","created_at":"2026-07-05T11:29:05.952153+00:00"},{"alias_kind":"pith_short_8","alias_value":"L3WCHMTM","created_at":"2026-07-05T11:29:05.952153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.13584","citing_title":"Temporal-Conditional Referring Video Object Segmentation with Noise-Free Text-to-Video Diffusion Model","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L3WCHMTMBQAGMQZGJLHMBCRWOI","json":"https://pith.science/pith/L3WCHMTMBQAGMQZGJLHMBCRWOI.json","graph_json":"https://pith.science/api/pith-number/L3WCHMTMBQAGMQZGJLHMBCRWOI/graph.json","events_json":"https://pith.science/api/pith-number/L3WCHMTMBQAGMQZGJLHMBCRWOI/events.json","paper":"https://pith.science/paper/L3WCHMTM"},"agent_actions":{"view_html":"https://pith.science/pith/L3WCHMTMBQAGMQZGJLHMBCRWOI","download_json":"https://pith.science/pith/L3WCHMTMBQAGMQZGJLHMBCRWOI.json","view_paper":"https://pith.science/paper/L3WCHMTM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14607&json=true","fetch_graph":"https://pith.science/api/pith-number/L3WCHMTMBQAGMQZGJLHMBCRWOI/graph.json","fetch_events":"https://pith.science/api/pith-number/L3WCHMTMBQAGMQZGJLHMBCRWOI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L3WCHMTMBQAGMQZGJLHMBCRWOI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L3WCHMTMBQAGMQZGJLHMBCRWOI/action/storage_attestation","attest_author":"https://pith.science/pith/L3WCHMTMBQAGMQZGJLHMBCRWOI/action/author_attestation","sign_citation":"https://pith.science/pith/L3WCHMTMBQAGMQZGJLHMBCRWOI/action/citation_signature","submit_replication":"https://pith.science/pith/L3WCHMTMBQAGMQZGJLHMBCRWOI/action/replication_record"}},"created_at":"2026-07-05T11:29:05.952153+00:00","updated_at":"2026-07-05T11:29:05.952153+00:00"}