{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4O7ERPROW6FSFK6WCSQJTO7JO6","short_pith_number":"pith:4O7ERPRO","schema_version":"1.0","canonical_sha256":"e3be48be2eb78b22abd614a099bbe9778dfa40e8361b30b962a16690afea6486","source":{"kind":"arxiv","id":"2203.16768","version":1},"attestation_state":"computed","paper":{"title":"ReSTR: Convolution-free Referring Image Segmentation Using Transformers","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cuiling Lan, Dongwon Kim, Namyup Kim, Suha Kwak, Wenjun Zeng","submitted_at":"2022-03-31T02:55:39Z","abstract_excerpt":"Referring image segmentation is an advanced semantic segmentation task where target is not a predefined class but is described in natural language. Most of existing methods for this task rely heavily on convolutional neural networks, which however have trouble capturing long-range dependencies between entities in the language expression and are not flexible enough for modeling interactions between the two different modalities. To address these issues, we present the first convolution-free model for referring image segmentation using transformers, dubbed ReSTR. Since it extracts features of bot"},"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":"2203.16768","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-31T02:55:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a26ec4ecc78e3b4e40b2c279663b486eb2ac875d04c11d4c3d5f4025b93e47f2","abstract_canon_sha256":"c64785b3ae135bb3cae373ca1562e260cca3c17b330c08d5de77d33f0f6f33c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:16.104378Z","signature_b64":"k8smTbbHwxT/n9/8hWVlXS1wbO3pRh/CGaSPxWRFmXaPQrZMw/cWxB9V4XVdk7XaXC+6iPRRUcAf/PtyhdPYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3be48be2eb78b22abd614a099bbe9778dfa40e8361b30b962a16690afea6486","last_reissued_at":"2026-07-05T04:10:16.103997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:16.103997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReSTR: Convolution-free Referring Image Segmentation Using Transformers","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cuiling Lan, Dongwon Kim, Namyup Kim, Suha Kwak, Wenjun Zeng","submitted_at":"2022-03-31T02:55:39Z","abstract_excerpt":"Referring image segmentation is an advanced semantic segmentation task where target is not a predefined class but is described in natural language. Most of existing methods for this task rely heavily on convolutional neural networks, which however have trouble capturing long-range dependencies between entities in the language expression and are not flexible enough for modeling interactions between the two different modalities. To address these issues, we present the first convolution-free model for referring image segmentation using transformers, dubbed ReSTR. Since it extracts features of bot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16768","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/2203.16768/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":"2203.16768","created_at":"2026-07-05T04:10:16.104050+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.16768v1","created_at":"2026-07-05T04:10:16.104050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16768","created_at":"2026-07-05T04:10:16.104050+00:00"},{"alias_kind":"pith_short_12","alias_value":"4O7ERPROW6FS","created_at":"2026-07-05T04:10:16.104050+00:00"},{"alias_kind":"pith_short_16","alias_value":"4O7ERPROW6FSFK6W","created_at":"2026-07-05T04:10:16.104050+00:00"},{"alias_kind":"pith_short_8","alias_value":"4O7ERPRO","created_at":"2026-07-05T04:10:16.104050+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4O7ERPROW6FSFK6WCSQJTO7JO6","json":"https://pith.science/pith/4O7ERPROW6FSFK6WCSQJTO7JO6.json","graph_json":"https://pith.science/api/pith-number/4O7ERPROW6FSFK6WCSQJTO7JO6/graph.json","events_json":"https://pith.science/api/pith-number/4O7ERPROW6FSFK6WCSQJTO7JO6/events.json","paper":"https://pith.science/paper/4O7ERPRO"},"agent_actions":{"view_html":"https://pith.science/pith/4O7ERPROW6FSFK6WCSQJTO7JO6","download_json":"https://pith.science/pith/4O7ERPROW6FSFK6WCSQJTO7JO6.json","view_paper":"https://pith.science/paper/4O7ERPRO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.16768&json=true","fetch_graph":"https://pith.science/api/pith-number/4O7ERPROW6FSFK6WCSQJTO7JO6/graph.json","fetch_events":"https://pith.science/api/pith-number/4O7ERPROW6FSFK6WCSQJTO7JO6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4O7ERPROW6FSFK6WCSQJTO7JO6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4O7ERPROW6FSFK6WCSQJTO7JO6/action/storage_attestation","attest_author":"https://pith.science/pith/4O7ERPROW6FSFK6WCSQJTO7JO6/action/author_attestation","sign_citation":"https://pith.science/pith/4O7ERPROW6FSFK6WCSQJTO7JO6/action/citation_signature","submit_replication":"https://pith.science/pith/4O7ERPROW6FSFK6WCSQJTO7JO6/action/replication_record"}},"created_at":"2026-07-05T04:10:16.104050+00:00","updated_at":"2026-07-05T04:10:16.104050+00:00"}