{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZBUVYI2W4DWCMWZXP3UQ5XR6CJ","short_pith_number":"pith:ZBUVYI2W","schema_version":"1.0","canonical_sha256":"c8695c2356e0ec265b377ee90ede3e127ac08f9854e76b0295ffd5f6ec053c57","source":{"kind":"arxiv","id":"2305.17011","version":1},"attestation_state":"computed","paper":{"title":"SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shuyan Li, Xiu Li, Yansong Tang, Yicheng Xiao, Yitong Wang, Yong Liu, Yujiu Yang, Zhuoyan Luo","submitted_at":"2023-05-26T15:13:44Z","abstract_excerpt":"This paper studies referring video object segmentation (RVOS) by boosting video-level visual-linguistic alignment. Recent approaches model the RVOS task as a sequence prediction problem and perform multi-modal interaction as well as segmentation for each frame separately. However, the lack of a global view of video content leads to difficulties in effectively utilizing inter-frame relationships and understanding textual descriptions of object temporal variations. To address this issue, we propose Semantic-assisted Object Cluster (SOC), which aggregates video content and textual guidance for un"},"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":"2305.17011","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-26T15:13:44Z","cross_cats_sorted":[],"title_canon_sha256":"a4693d03039ed1ebdf3c40340b89ee45e9a20b4df0e5069a6ee57b584638b8d0","abstract_canon_sha256":"e3279e44f5b227c5cf0cf6ef66d52a87329b08fc548ad9a5dec0d4ecd77a2866"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:20.047197Z","signature_b64":"xDBOLeW4wJvG3KNYNE5ThOymaSdkZfG71FYqVgys9kuOayW59Ul6skgdokBYA6rVXtDkRe3BTOikARQtrfdVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8695c2356e0ec265b377ee90ede3e127ac08f9854e76b0295ffd5f6ec053c57","last_reissued_at":"2026-07-05T06:14:20.046862Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:20.046862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shuyan Li, Xiu Li, Yansong Tang, Yicheng Xiao, Yitong Wang, Yong Liu, Yujiu Yang, Zhuoyan Luo","submitted_at":"2023-05-26T15:13:44Z","abstract_excerpt":"This paper studies referring video object segmentation (RVOS) by boosting video-level visual-linguistic alignment. Recent approaches model the RVOS task as a sequence prediction problem and perform multi-modal interaction as well as segmentation for each frame separately. However, the lack of a global view of video content leads to difficulties in effectively utilizing inter-frame relationships and understanding textual descriptions of object temporal variations. To address this issue, we propose Semantic-assisted Object Cluster (SOC), which aggregates video content and textual guidance for un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17011","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/2305.17011/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":"2305.17011","created_at":"2026-07-05T06:14:20.046915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.17011v1","created_at":"2026-07-05T06:14:20.046915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17011","created_at":"2026-07-05T06:14:20.046915+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBUVYI2W4DWC","created_at":"2026-07-05T06:14:20.046915+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBUVYI2W4DWCMWZX","created_at":"2026-07-05T06:14:20.046915+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBUVYI2W","created_at":"2026-07-05T06:14:20.046915+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07171","citing_title":"EventRR: Event Referential Reasoning for Referring Video Object Segmentation","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZBUVYI2W4DWCMWZXP3UQ5XR6CJ","json":"https://pith.science/pith/ZBUVYI2W4DWCMWZXP3UQ5XR6CJ.json","graph_json":"https://pith.science/api/pith-number/ZBUVYI2W4DWCMWZXP3UQ5XR6CJ/graph.json","events_json":"https://pith.science/api/pith-number/ZBUVYI2W4DWCMWZXP3UQ5XR6CJ/events.json","paper":"https://pith.science/paper/ZBUVYI2W"},"agent_actions":{"view_html":"https://pith.science/pith/ZBUVYI2W4DWCMWZXP3UQ5XR6CJ","download_json":"https://pith.science/pith/ZBUVYI2W4DWCMWZXP3UQ5XR6CJ.json","view_paper":"https://pith.science/paper/ZBUVYI2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.17011&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBUVYI2W4DWCMWZXP3UQ5XR6CJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBUVYI2W4DWCMWZXP3UQ5XR6CJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBUVYI2W4DWCMWZXP3UQ5XR6CJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBUVYI2W4DWCMWZXP3UQ5XR6CJ/action/storage_attestation","attest_author":"https://pith.science/pith/ZBUVYI2W4DWCMWZXP3UQ5XR6CJ/action/author_attestation","sign_citation":"https://pith.science/pith/ZBUVYI2W4DWCMWZXP3UQ5XR6CJ/action/citation_signature","submit_replication":"https://pith.science/pith/ZBUVYI2W4DWCMWZXP3UQ5XR6CJ/action/replication_record"}},"created_at":"2026-07-05T06:14:20.046915+00:00","updated_at":"2026-07-05T06:14:20.046915+00:00"}