{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XMAC7HKD3RWAY4QLDIJIVRUIPW","short_pith_number":"pith:XMAC7HKD","schema_version":"1.0","canonical_sha256":"bb002f9d43dc6c0c720b1a128ac6887d8586e6319ffe9d25b986c9d5b3b2c5fc","source":{"kind":"arxiv","id":"2307.00536","version":2},"attestation_state":"computed","paper":{"title":"Bidirectional Correlation-Driven Inter-Frame Interaction Transformer for Referring Video Object Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fu Rong, Lefei Zhang, Meng Lan, Wei Yu, Zuchao Li","submitted_at":"2023-07-02T10:29:35Z","abstract_excerpt":"Referring video object segmentation (RVOS) aims to segment the target object in a video sequence described by a language expression. Typical multimodal Transformer based RVOS approaches process video sequence in a frame-independent manner to reduce the high computational cost, which however restricts the performance due to the lack of inter-frame interaction for temporal coherence modeling and spatio-temporal representation learning of the referred object. Besides, the absence of sufficient cross-modal interactions results in weak correlation between the visual and linguistic features, which i"},"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":"2307.00536","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-02T10:29:35Z","cross_cats_sorted":[],"title_canon_sha256":"4d390ec9e38fd647d362a66efa9cdacec0196f0f2ad7ba3c3a3ebb6d99636725","abstract_canon_sha256":"656ed1a9073df99dec624c4a2ebac031c6d123bc1837085a3a350fad6283c751"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:27.198848Z","signature_b64":"+FVzBeLm3yuCEVySTkULg//aGzg+Z60EpmvWSrpwyoNeGfiGxcJVHtaXMd4iK0jzZzvQQROC/hrMib2TVCrbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb002f9d43dc6c0c720b1a128ac6887d8586e6319ffe9d25b986c9d5b3b2c5fc","last_reissued_at":"2026-07-05T06:51:27.198413Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:27.198413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bidirectional Correlation-Driven Inter-Frame Interaction Transformer for Referring Video Object Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fu Rong, Lefei Zhang, Meng Lan, Wei Yu, Zuchao Li","submitted_at":"2023-07-02T10:29:35Z","abstract_excerpt":"Referring video object segmentation (RVOS) aims to segment the target object in a video sequence described by a language expression. Typical multimodal Transformer based RVOS approaches process video sequence in a frame-independent manner to reduce the high computational cost, which however restricts the performance due to the lack of inter-frame interaction for temporal coherence modeling and spatio-temporal representation learning of the referred object. Besides, the absence of sufficient cross-modal interactions results in weak correlation between the visual and linguistic features, which i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00536","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/2307.00536/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":"2307.00536","created_at":"2026-07-05T06:51:27.198476+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.00536v2","created_at":"2026-07-05T06:51:27.198476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00536","created_at":"2026-07-05T06:51:27.198476+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMAC7HKD3RWA","created_at":"2026-07-05T06:51:27.198476+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMAC7HKD3RWAY4QL","created_at":"2026-07-05T06:51:27.198476+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMAC7HKD","created_at":"2026-07-05T06:51:27.198476+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.21809","citing_title":"VoCap: Video Object Captioning and Segmentation from Any Prompt","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XMAC7HKD3RWAY4QLDIJIVRUIPW","json":"https://pith.science/pith/XMAC7HKD3RWAY4QLDIJIVRUIPW.json","graph_json":"https://pith.science/api/pith-number/XMAC7HKD3RWAY4QLDIJIVRUIPW/graph.json","events_json":"https://pith.science/api/pith-number/XMAC7HKD3RWAY4QLDIJIVRUIPW/events.json","paper":"https://pith.science/paper/XMAC7HKD"},"agent_actions":{"view_html":"https://pith.science/pith/XMAC7HKD3RWAY4QLDIJIVRUIPW","download_json":"https://pith.science/pith/XMAC7HKD3RWAY4QLDIJIVRUIPW.json","view_paper":"https://pith.science/paper/XMAC7HKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.00536&json=true","fetch_graph":"https://pith.science/api/pith-number/XMAC7HKD3RWAY4QLDIJIVRUIPW/graph.json","fetch_events":"https://pith.science/api/pith-number/XMAC7HKD3RWAY4QLDIJIVRUIPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMAC7HKD3RWAY4QLDIJIVRUIPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMAC7HKD3RWAY4QLDIJIVRUIPW/action/storage_attestation","attest_author":"https://pith.science/pith/XMAC7HKD3RWAY4QLDIJIVRUIPW/action/author_attestation","sign_citation":"https://pith.science/pith/XMAC7HKD3RWAY4QLDIJIVRUIPW/action/citation_signature","submit_replication":"https://pith.science/pith/XMAC7HKD3RWAY4QLDIJIVRUIPW/action/replication_record"}},"created_at":"2026-07-05T06:51:27.198476+00:00","updated_at":"2026-07-05T06:51:27.198476+00:00"}