{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:32BTYVHW33SZNCHNBR7G4PR3PJ","short_pith_number":"pith:32BTYVHW","schema_version":"1.0","canonical_sha256":"de833c54f6dee59688ed0c7e6e3e3b7a4ab665c1431831368c7b3d3a7eb8b3f7","source":{"kind":"arxiv","id":"2310.10975","version":2},"attestation_state":"computed","paper":{"title":"NICE: Improving Panoptic Narrative Detection and Segmentation with Cascading Collaborative Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haowei Wang, Jiayi Ji, Rongrong Ji, Tianyu Guo, Xiaoshuai Sun, Yilong Yang, Yiyi Zhou","submitted_at":"2023-10-17T03:42:12Z","abstract_excerpt":"Panoptic Narrative Detection (PND) and Segmentation (PNS) are two challenging tasks that involve identifying and locating multiple targets in an image according to a long narrative description. In this paper, we propose a unified and effective framework called NICE that can jointly learn these two panoptic narrative recognition tasks. Existing visual grounding tasks use a two-branch paradigm, but applying this directly to PND and PNS can result in prediction conflict due to their intrinsic many-to-many alignment property. To address this, we introduce two cascading modules based on the barycen"},"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":"2310.10975","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-17T03:42:12Z","cross_cats_sorted":[],"title_canon_sha256":"747a96aa1f9ffbf84d07598f557be039ae347ca7a640e4e44ea5554bfaa4bd82","abstract_canon_sha256":"1489f04b8f81b8511fc99723b5932b55ba43404b5958466c3c919457e1e5b9cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:32.596749Z","signature_b64":"E41hjHlfJyG+klDgoS2Je6cdjVwDteUE2Vd5JWMqAnoZygjTixsI6Rl8ml8uOgRuaepmitGxss/TiKPtPx3VDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de833c54f6dee59688ed0c7e6e3e3b7a4ab665c1431831368c7b3d3a7eb8b3f7","last_reissued_at":"2026-07-05T07:03:32.596282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:32.596282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NICE: Improving Panoptic Narrative Detection and Segmentation with Cascading Collaborative Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haowei Wang, Jiayi Ji, Rongrong Ji, Tianyu Guo, Xiaoshuai Sun, Yilong Yang, Yiyi Zhou","submitted_at":"2023-10-17T03:42:12Z","abstract_excerpt":"Panoptic Narrative Detection (PND) and Segmentation (PNS) are two challenging tasks that involve identifying and locating multiple targets in an image according to a long narrative description. In this paper, we propose a unified and effective framework called NICE that can jointly learn these two panoptic narrative recognition tasks. Existing visual grounding tasks use a two-branch paradigm, but applying this directly to PND and PNS can result in prediction conflict due to their intrinsic many-to-many alignment property. To address this, we introduce two cascading modules based on the barycen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10975","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/2310.10975/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":"2310.10975","created_at":"2026-07-05T07:03:32.596341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10975v2","created_at":"2026-07-05T07:03:32.596341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10975","created_at":"2026-07-05T07:03:32.596341+00:00"},{"alias_kind":"pith_short_12","alias_value":"32BTYVHW33SZ","created_at":"2026-07-05T07:03:32.596341+00:00"},{"alias_kind":"pith_short_16","alias_value":"32BTYVHW33SZNCHN","created_at":"2026-07-05T07:03:32.596341+00:00"},{"alias_kind":"pith_short_8","alias_value":"32BTYVHW","created_at":"2026-07-05T07:03:32.596341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.16919","citing_title":"TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction","ref_index":66,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/32BTYVHW33SZNCHNBR7G4PR3PJ","json":"https://pith.science/pith/32BTYVHW33SZNCHNBR7G4PR3PJ.json","graph_json":"https://pith.science/api/pith-number/32BTYVHW33SZNCHNBR7G4PR3PJ/graph.json","events_json":"https://pith.science/api/pith-number/32BTYVHW33SZNCHNBR7G4PR3PJ/events.json","paper":"https://pith.science/paper/32BTYVHW"},"agent_actions":{"view_html":"https://pith.science/pith/32BTYVHW33SZNCHNBR7G4PR3PJ","download_json":"https://pith.science/pith/32BTYVHW33SZNCHNBR7G4PR3PJ.json","view_paper":"https://pith.science/paper/32BTYVHW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10975&json=true","fetch_graph":"https://pith.science/api/pith-number/32BTYVHW33SZNCHNBR7G4PR3PJ/graph.json","fetch_events":"https://pith.science/api/pith-number/32BTYVHW33SZNCHNBR7G4PR3PJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/32BTYVHW33SZNCHNBR7G4PR3PJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/32BTYVHW33SZNCHNBR7G4PR3PJ/action/storage_attestation","attest_author":"https://pith.science/pith/32BTYVHW33SZNCHNBR7G4PR3PJ/action/author_attestation","sign_citation":"https://pith.science/pith/32BTYVHW33SZNCHNBR7G4PR3PJ/action/citation_signature","submit_replication":"https://pith.science/pith/32BTYVHW33SZNCHNBR7G4PR3PJ/action/replication_record"}},"created_at":"2026-07-05T07:03:32.596341+00:00","updated_at":"2026-07-05T07:03:32.596341+00:00"}