{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WC6O7FEXY4EC3SURIRNML75JON","short_pith_number":"pith:WC6O7FEX","schema_version":"1.0","canonical_sha256":"b0bcef9497c7082dca91445ac5ffa973609b48c041c57fba31d0bb3ac3d0cbc7","source":{"kind":"arxiv","id":"2112.02244","version":2},"attestation_state":"computed","paper":{"title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hengshuang Zhao, Jiaqi Wang, Kai Chen, Philip H.S. Torr, Yansong Tang, Zhao Yang","submitted_at":"2021-12-04T04:53:35Z","abstract_excerpt":"Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image. One of the key challenges behind this task is leveraging the referring expression for highlighting relevant positions in the image. A paradigm for tackling this problem is to leverage a powerful vision-language (\"cross-modal\") decoder to fuse features independently extracted from a vision encoder and a language encoder. Recent methods have made remarkable advancements in this paradigm by exploiting Transformers as cross-modal decoders"},"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":"2112.02244","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-04T04:53:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e9b675e8fa127f3a1ff1adc2568ea58de7cc43abe3da094c003dfe0c4c8fa0bc","abstract_canon_sha256":"b99a83b561d0698af4e41c992b63370790f06e95ce801f24094ed0a47f10c44b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:05.249946Z","signature_b64":"b6n4CNr8FxxHM156927PZ7bcp5GFlqhYwhJt2k7FrhWaeG6toXK6sZj+c3uQVTM9cGpuEuRhbu2po6srvwi/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0bcef9497c7082dca91445ac5ffa973609b48c041c57fba31d0bb3ac3d0cbc7","last_reissued_at":"2026-07-05T04:12:05.249451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:05.249451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hengshuang Zhao, Jiaqi Wang, Kai Chen, Philip H.S. Torr, Yansong Tang, Zhao Yang","submitted_at":"2021-12-04T04:53:35Z","abstract_excerpt":"Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image. One of the key challenges behind this task is leveraging the referring expression for highlighting relevant positions in the image. A paradigm for tackling this problem is to leverage a powerful vision-language (\"cross-modal\") decoder to fuse features independently extracted from a vision encoder and a language encoder. Recent methods have made remarkable advancements in this paradigm by exploiting Transformers as cross-modal decoders"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02244","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/2112.02244/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":"2112.02244","created_at":"2026-07-05T04:12:05.249515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.02244v2","created_at":"2026-07-05T04:12:05.249515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02244","created_at":"2026-07-05T04:12:05.249515+00:00"},{"alias_kind":"pith_short_12","alias_value":"WC6O7FEXY4EC","created_at":"2026-07-05T04:12:05.249515+00:00"},{"alias_kind":"pith_short_16","alias_value":"WC6O7FEXY4EC3SUR","created_at":"2026-07-05T04:12:05.249515+00:00"},{"alias_kind":"pith_short_8","alias_value":"WC6O7FEX","created_at":"2026-07-05T04:12:05.249515+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01077","citing_title":"VespaSeg: A Resource-Aware Ground-then-Segment Pipeline for Referring Expression Segmentation","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WC6O7FEXY4EC3SURIRNML75JON","json":"https://pith.science/pith/WC6O7FEXY4EC3SURIRNML75JON.json","graph_json":"https://pith.science/api/pith-number/WC6O7FEXY4EC3SURIRNML75JON/graph.json","events_json":"https://pith.science/api/pith-number/WC6O7FEXY4EC3SURIRNML75JON/events.json","paper":"https://pith.science/paper/WC6O7FEX"},"agent_actions":{"view_html":"https://pith.science/pith/WC6O7FEXY4EC3SURIRNML75JON","download_json":"https://pith.science/pith/WC6O7FEXY4EC3SURIRNML75JON.json","view_paper":"https://pith.science/paper/WC6O7FEX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.02244&json=true","fetch_graph":"https://pith.science/api/pith-number/WC6O7FEXY4EC3SURIRNML75JON/graph.json","fetch_events":"https://pith.science/api/pith-number/WC6O7FEXY4EC3SURIRNML75JON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WC6O7FEXY4EC3SURIRNML75JON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WC6O7FEXY4EC3SURIRNML75JON/action/storage_attestation","attest_author":"https://pith.science/pith/WC6O7FEXY4EC3SURIRNML75JON/action/author_attestation","sign_citation":"https://pith.science/pith/WC6O7FEXY4EC3SURIRNML75JON/action/citation_signature","submit_replication":"https://pith.science/pith/WC6O7FEXY4EC3SURIRNML75JON/action/replication_record"}},"created_at":"2026-07-05T04:12:05.249515+00:00","updated_at":"2026-07-05T04:12:05.249515+00:00"}