{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MQCWRWC4FU3I2PKKIXWLMEVZ3K","short_pith_number":"pith:MQCWRWC4","schema_version":"1.0","canonical_sha256":"640568d85c2d368d3d4a45ecb612b9da9c39bd0253aed40f695e20323b3c565d","source":{"kind":"arxiv","id":"2408.10129","version":2},"attestation_state":"computed","paper":{"title":"UNINEXT-Cutie: The 1st Solution for LSVOS Challenge RVOS Track","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feiyu Pan, Hao Fang, Runmin Cong, Wei Zhang, Xiankai Lu","submitted_at":"2024-08-19T16:15:56Z","abstract_excerpt":"Referring video object segmentation (RVOS) relies on natural language expressions to segment target objects in video. In this year, LSVOS Challenge RVOS Track replaced the origin YouTube-RVOS benchmark with MeViS. MeViS focuses on referring the target object in a video through its motion descriptions instead of static attributes, posing a greater challenge to RVOS task. In this work, we integrate strengths of that leading RVOS and VOS models to build up a simple and effective pipeline for RVOS. Firstly, We finetune the state-of-the-art RVOS model to obtain mask sequences that are correlated wi"},"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":"2408.10129","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-19T16:15:56Z","cross_cats_sorted":[],"title_canon_sha256":"965e9473125bece2e1ac66aa7a9dc422bf851b0cea267c90ddaa18ea6103c2fd","abstract_canon_sha256":"768cb6fdd3b915c87e27fd6b2a3a3effa2e72d5c1399a26fd6ae928ce9b8b64a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:46.919940Z","signature_b64":"X9iVG2Fj2dnU9GWJ9smehh82nT4jQW6POyQ3ZMiO8tqASE8PnNvvnujIh5/Cfrjth4NcV+7boIovpd/qFdfVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"640568d85c2d368d3d4a45ecb612b9da9c39bd0253aed40f695e20323b3c565d","last_reissued_at":"2026-07-05T08:58:46.919465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:46.919465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UNINEXT-Cutie: The 1st Solution for LSVOS Challenge RVOS Track","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feiyu Pan, Hao Fang, Runmin Cong, Wei Zhang, Xiankai Lu","submitted_at":"2024-08-19T16:15:56Z","abstract_excerpt":"Referring video object segmentation (RVOS) relies on natural language expressions to segment target objects in video. In this year, LSVOS Challenge RVOS Track replaced the origin YouTube-RVOS benchmark with MeViS. MeViS focuses on referring the target object in a video through its motion descriptions instead of static attributes, posing a greater challenge to RVOS task. In this work, we integrate strengths of that leading RVOS and VOS models to build up a simple and effective pipeline for RVOS. Firstly, We finetune the state-of-the-art RVOS model to obtain mask sequences that are correlated wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10129","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/2408.10129/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":"2408.10129","created_at":"2026-07-05T08:58:46.919520+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10129v2","created_at":"2026-07-05T08:58:46.919520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10129","created_at":"2026-07-05T08:58:46.919520+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQCWRWC4FU3I","created_at":"2026-07-05T08:58:46.919520+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQCWRWC4FU3I2PKK","created_at":"2026-07-05T08:58:46.919520+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQCWRWC4","created_at":"2026-07-05T08:58:46.919520+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/MQCWRWC4FU3I2PKKIXWLMEVZ3K","json":"https://pith.science/pith/MQCWRWC4FU3I2PKKIXWLMEVZ3K.json","graph_json":"https://pith.science/api/pith-number/MQCWRWC4FU3I2PKKIXWLMEVZ3K/graph.json","events_json":"https://pith.science/api/pith-number/MQCWRWC4FU3I2PKKIXWLMEVZ3K/events.json","paper":"https://pith.science/paper/MQCWRWC4"},"agent_actions":{"view_html":"https://pith.science/pith/MQCWRWC4FU3I2PKKIXWLMEVZ3K","download_json":"https://pith.science/pith/MQCWRWC4FU3I2PKKIXWLMEVZ3K.json","view_paper":"https://pith.science/paper/MQCWRWC4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10129&json=true","fetch_graph":"https://pith.science/api/pith-number/MQCWRWC4FU3I2PKKIXWLMEVZ3K/graph.json","fetch_events":"https://pith.science/api/pith-number/MQCWRWC4FU3I2PKKIXWLMEVZ3K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQCWRWC4FU3I2PKKIXWLMEVZ3K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQCWRWC4FU3I2PKKIXWLMEVZ3K/action/storage_attestation","attest_author":"https://pith.science/pith/MQCWRWC4FU3I2PKKIXWLMEVZ3K/action/author_attestation","sign_citation":"https://pith.science/pith/MQCWRWC4FU3I2PKKIXWLMEVZ3K/action/citation_signature","submit_replication":"https://pith.science/pith/MQCWRWC4FU3I2PKKIXWLMEVZ3K/action/replication_record"}},"created_at":"2026-07-05T08:58:46.919520+00:00","updated_at":"2026-07-05T08:58:46.919520+00:00"}