{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GV2OPBL6AO5K52FDF5GXYTGPVL","short_pith_number":"pith:GV2OPBL6","schema_version":"1.0","canonical_sha256":"3574e7857e03baaee8a32f4d7c4ccfaae16946d81f809e7350b1023f976981c2","source":{"kind":"arxiv","id":"2302.07387","version":2},"attestation_state":"computed","paper":{"title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hui Ding, Jiang Liu, Ravi Kumar Satzoda, R. Manmatha, Vijay Mahadevan, Yuting Zhang, Zhaowei Cai","submitted_at":"2023-02-14T23:00:25Z","abstract_excerpt":"In this work, instead of directly predicting the pixel-level segmentation masks, the problem of referring image segmentation is formulated as sequential polygon generation, and the predicted polygons can be later converted into segmentation masks. This is enabled by a new sequence-to-sequence framework, Polygon Transformer (PolyFormer), which takes a sequence of image patches and text query tokens as input, and outputs a sequence of polygon vertices autoregressively. For more accurate geometric localization, we propose a regression-based decoder, which predicts the precise floating-point coord"},"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":"2302.07387","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-14T23:00:25Z","cross_cats_sorted":[],"title_canon_sha256":"bbcf64b19a805687e91e818acac9fc2c2581f34276b5ef8b54966dfcd7a20ff8","abstract_canon_sha256":"0d0817441f385d6c9f389d2138d129fc22917a6ebed92f9ce203478d45986de5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:55:19.186040Z","signature_b64":"3fBPDUIugN87Ax8eAeqkco5QgCWMss7SOu66+0drTESHg0LzdLskHw/8GCz0mKayYK2e2m240vZaBaOtxdItCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3574e7857e03baaee8a32f4d7c4ccfaae16946d81f809e7350b1023f976981c2","last_reissued_at":"2026-07-05T05:55:19.185542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:55:19.185542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hui Ding, Jiang Liu, Ravi Kumar Satzoda, R. Manmatha, Vijay Mahadevan, Yuting Zhang, Zhaowei Cai","submitted_at":"2023-02-14T23:00:25Z","abstract_excerpt":"In this work, instead of directly predicting the pixel-level segmentation masks, the problem of referring image segmentation is formulated as sequential polygon generation, and the predicted polygons can be later converted into segmentation masks. This is enabled by a new sequence-to-sequence framework, Polygon Transformer (PolyFormer), which takes a sequence of image patches and text query tokens as input, and outputs a sequence of polygon vertices autoregressively. For more accurate geometric localization, we propose a regression-based decoder, which predicts the precise floating-point coord"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.07387","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/2302.07387/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":"2302.07387","created_at":"2026-07-05T05:55:19.185600+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.07387v2","created_at":"2026-07-05T05:55:19.185600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.07387","created_at":"2026-07-05T05:55:19.185600+00:00"},{"alias_kind":"pith_short_12","alias_value":"GV2OPBL6AO5K","created_at":"2026-07-05T05:55:19.185600+00:00"},{"alias_kind":"pith_short_16","alias_value":"GV2OPBL6AO5K52FD","created_at":"2026-07-05T05:55:19.185600+00:00"},{"alias_kind":"pith_short_8","alias_value":"GV2OPBL6","created_at":"2026-07-05T05:55:19.185600+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02593","citing_title":"Moondream Segmentation: From Words to Masks","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GV2OPBL6AO5K52FDF5GXYTGPVL","json":"https://pith.science/pith/GV2OPBL6AO5K52FDF5GXYTGPVL.json","graph_json":"https://pith.science/api/pith-number/GV2OPBL6AO5K52FDF5GXYTGPVL/graph.json","events_json":"https://pith.science/api/pith-number/GV2OPBL6AO5K52FDF5GXYTGPVL/events.json","paper":"https://pith.science/paper/GV2OPBL6"},"agent_actions":{"view_html":"https://pith.science/pith/GV2OPBL6AO5K52FDF5GXYTGPVL","download_json":"https://pith.science/pith/GV2OPBL6AO5K52FDF5GXYTGPVL.json","view_paper":"https://pith.science/paper/GV2OPBL6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.07387&json=true","fetch_graph":"https://pith.science/api/pith-number/GV2OPBL6AO5K52FDF5GXYTGPVL/graph.json","fetch_events":"https://pith.science/api/pith-number/GV2OPBL6AO5K52FDF5GXYTGPVL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GV2OPBL6AO5K52FDF5GXYTGPVL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GV2OPBL6AO5K52FDF5GXYTGPVL/action/storage_attestation","attest_author":"https://pith.science/pith/GV2OPBL6AO5K52FDF5GXYTGPVL/action/author_attestation","sign_citation":"https://pith.science/pith/GV2OPBL6AO5K52FDF5GXYTGPVL/action/citation_signature","submit_replication":"https://pith.science/pith/GV2OPBL6AO5K52FDF5GXYTGPVL/action/replication_record"}},"created_at":"2026-07-05T05:55:19.185600+00:00","updated_at":"2026-07-05T05:55:19.185600+00:00"}