{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:65O6ZI6D2XSEEGP55RCPUGT3I4","short_pith_number":"pith:65O6ZI6D","schema_version":"1.0","canonical_sha256":"f75deca3c3d5e44219fdec44fa1a7b47250aefe97f39660489bdb14f38798722","source":{"kind":"arxiv","id":"2207.01203","version":3},"attestation_state":"computed","paper":{"title":"Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bhiksha Raj, Jinglu Wang, Xiang Li, Xiaohao Xu, Xiao Li, Yan Lu","submitted_at":"2022-07-04T05:08:09Z","abstract_excerpt":"Referring Video Object Segmentation (R-VOS) is a challenging task that aims to segment an object in a video based on a linguistic expression. Most existing R-VOS methods have a critical assumption: the object referred to must appear in the video. This assumption, which we refer to as semantic consensus, is often violated in real-world scenarios, where the expression may be queried against false videos. In this work, we highlight the need for a robust R-VOS model that can handle semantic mismatches. Accordingly, we propose an extended task called Robust R-VOS, which accepts unpaired video-text "},"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":"2207.01203","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-04T05:08:09Z","cross_cats_sorted":[],"title_canon_sha256":"dba74d231b8ad8b5c24a503eb7b2465d7caad2dab846cf6a82bc901190b7006b","abstract_canon_sha256":"e7a6e912af02fdba4bc9e323042d61ed6972c7b3c21ce7c8cb95baf5256149e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:39.672380Z","signature_b64":"NKhrXE7bvTe0J5VU/hdGwpRuEY6z2oLFU0trWzRojNDjRBDzLDdrM/HdX0nrYQqfz6duscHdKd7zj6+Pa83SBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f75deca3c3d5e44219fdec44fa1a7b47250aefe97f39660489bdb14f38798722","last_reissued_at":"2026-07-05T06:42:39.671874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:39.671874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bhiksha Raj, Jinglu Wang, Xiang Li, Xiaohao Xu, Xiao Li, Yan Lu","submitted_at":"2022-07-04T05:08:09Z","abstract_excerpt":"Referring Video Object Segmentation (R-VOS) is a challenging task that aims to segment an object in a video based on a linguistic expression. Most existing R-VOS methods have a critical assumption: the object referred to must appear in the video. This assumption, which we refer to as semantic consensus, is often violated in real-world scenarios, where the expression may be queried against false videos. In this work, we highlight the need for a robust R-VOS model that can handle semantic mismatches. Accordingly, we propose an extended task called Robust R-VOS, which accepts unpaired video-text "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.01203","kind":"arxiv","version":3},"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/2207.01203/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":"2207.01203","created_at":"2026-07-05T06:42:39.671936+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.01203v3","created_at":"2026-07-05T06:42:39.671936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.01203","created_at":"2026-07-05T06:42:39.671936+00:00"},{"alias_kind":"pith_short_12","alias_value":"65O6ZI6D2XSE","created_at":"2026-07-05T06:42:39.671936+00:00"},{"alias_kind":"pith_short_16","alias_value":"65O6ZI6D2XSEEGP5","created_at":"2026-07-05T06:42:39.671936+00:00"},{"alias_kind":"pith_short_8","alias_value":"65O6ZI6D","created_at":"2026-07-05T06:42:39.671936+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":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/65O6ZI6D2XSEEGP55RCPUGT3I4","json":"https://pith.science/pith/65O6ZI6D2XSEEGP55RCPUGT3I4.json","graph_json":"https://pith.science/api/pith-number/65O6ZI6D2XSEEGP55RCPUGT3I4/graph.json","events_json":"https://pith.science/api/pith-number/65O6ZI6D2XSEEGP55RCPUGT3I4/events.json","paper":"https://pith.science/paper/65O6ZI6D"},"agent_actions":{"view_html":"https://pith.science/pith/65O6ZI6D2XSEEGP55RCPUGT3I4","download_json":"https://pith.science/pith/65O6ZI6D2XSEEGP55RCPUGT3I4.json","view_paper":"https://pith.science/paper/65O6ZI6D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.01203&json=true","fetch_graph":"https://pith.science/api/pith-number/65O6ZI6D2XSEEGP55RCPUGT3I4/graph.json","fetch_events":"https://pith.science/api/pith-number/65O6ZI6D2XSEEGP55RCPUGT3I4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65O6ZI6D2XSEEGP55RCPUGT3I4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65O6ZI6D2XSEEGP55RCPUGT3I4/action/storage_attestation","attest_author":"https://pith.science/pith/65O6ZI6D2XSEEGP55RCPUGT3I4/action/author_attestation","sign_citation":"https://pith.science/pith/65O6ZI6D2XSEEGP55RCPUGT3I4/action/citation_signature","submit_replication":"https://pith.science/pith/65O6ZI6D2XSEEGP55RCPUGT3I4/action/replication_record"}},"created_at":"2026-07-05T06:42:39.671936+00:00","updated_at":"2026-07-05T06:42:39.671936+00:00"}