{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YTYRUV3SLHVTCJ75U6R77SGKJP","short_pith_number":"pith:YTYRUV3S","schema_version":"1.0","canonical_sha256":"c4f11a577259eb3127fda7a3ffc8ca4bfaacfa517ff26bbb05644a19bbc1262d","source":{"kind":"arxiv","id":"2503.23509","version":2},"attestation_state":"computed","paper":{"title":"ReferDINO-Plus: 2nd Solution for 4th PVUW MeViS Challenge at CVPR 2025","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haichao Jiang, Jian-Fang Hu, Tianming Liang, Wei-Shi Zheng","submitted_at":"2025-03-30T16:43:04Z","abstract_excerpt":"Referring Video Object Segmentation (RVOS) aims to segment target objects throughout a video based on a text description. This task has attracted increasing attention in the field of computer vision due to its promising applications in video editing and human-agent interaction. Recently, ReferDINO has demonstrated promising performance in this task by adapting object-level vision-language knowledge from pretrained foundational image models. In this report, we further enhance its capabilities by incorporating the advantages of SAM2 in mask quality and object consistency. In addition, to effecti"},"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":"2503.23509","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-30T16:43:04Z","cross_cats_sorted":[],"title_canon_sha256":"92154698426f6ab6accefc3f85effb2555c5cfacc60e2966eaf2cacc9291ab8c","abstract_canon_sha256":"a6957e9f7ca0009dee7d566350f0feb65b576d517789f26bc14aec7932a6b343"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:43.603016Z","signature_b64":"b3OtAXuPP9mJIeIhTQFm9cNwlYctnXhH2iuXlfXVSmXaS6AUb3Ddc0g1y/8sgq3y/FwMgJqSPvz2YmBx5E8eCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4f11a577259eb3127fda7a3ffc8ca4bfaacfa517ff26bbb05644a19bbc1262d","last_reissued_at":"2026-07-05T11:11:43.602535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:43.602535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReferDINO-Plus: 2nd Solution for 4th PVUW MeViS Challenge at CVPR 2025","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haichao Jiang, Jian-Fang Hu, Tianming Liang, Wei-Shi Zheng","submitted_at":"2025-03-30T16:43:04Z","abstract_excerpt":"Referring Video Object Segmentation (RVOS) aims to segment target objects throughout a video based on a text description. This task has attracted increasing attention in the field of computer vision due to its promising applications in video editing and human-agent interaction. Recently, ReferDINO has demonstrated promising performance in this task by adapting object-level vision-language knowledge from pretrained foundational image models. In this report, we further enhance its capabilities by incorporating the advantages of SAM2 in mask quality and object consistency. In addition, to effecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23509","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/2503.23509/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":"2503.23509","created_at":"2026-07-05T11:11:43.602589+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.23509v2","created_at":"2026-07-05T11:11:43.602589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23509","created_at":"2026-07-05T11:11:43.602589+00:00"},{"alias_kind":"pith_short_12","alias_value":"YTYRUV3SLHVT","created_at":"2026-07-05T11:11:43.602589+00:00"},{"alias_kind":"pith_short_16","alias_value":"YTYRUV3SLHVTCJ75","created_at":"2026-07-05T11:11:43.602589+00:00"},{"alias_kind":"pith_short_8","alias_value":"YTYRUV3S","created_at":"2026-07-05T11:11:43.602589+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/YTYRUV3SLHVTCJ75U6R77SGKJP","json":"https://pith.science/pith/YTYRUV3SLHVTCJ75U6R77SGKJP.json","graph_json":"https://pith.science/api/pith-number/YTYRUV3SLHVTCJ75U6R77SGKJP/graph.json","events_json":"https://pith.science/api/pith-number/YTYRUV3SLHVTCJ75U6R77SGKJP/events.json","paper":"https://pith.science/paper/YTYRUV3S"},"agent_actions":{"view_html":"https://pith.science/pith/YTYRUV3SLHVTCJ75U6R77SGKJP","download_json":"https://pith.science/pith/YTYRUV3SLHVTCJ75U6R77SGKJP.json","view_paper":"https://pith.science/paper/YTYRUV3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.23509&json=true","fetch_graph":"https://pith.science/api/pith-number/YTYRUV3SLHVTCJ75U6R77SGKJP/graph.json","fetch_events":"https://pith.science/api/pith-number/YTYRUV3SLHVTCJ75U6R77SGKJP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YTYRUV3SLHVTCJ75U6R77SGKJP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YTYRUV3SLHVTCJ75U6R77SGKJP/action/storage_attestation","attest_author":"https://pith.science/pith/YTYRUV3SLHVTCJ75U6R77SGKJP/action/author_attestation","sign_citation":"https://pith.science/pith/YTYRUV3SLHVTCJ75U6R77SGKJP/action/citation_signature","submit_replication":"https://pith.science/pith/YTYRUV3SLHVTCJ75U6R77SGKJP/action/replication_record"}},"created_at":"2026-07-05T11:11:43.602589+00:00","updated_at":"2026-07-05T11:11:43.602589+00:00"}