{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HMVMRQ2RC2B4OKB5VV6AOELULX","short_pith_number":"pith:HMVMRQ2R","schema_version":"1.0","canonical_sha256":"3b2ac8c3511683c7283dad7c0711745dee5b661ae61c9a8cef745f8f7a743739","source":{"kind":"arxiv","id":"2111.10747","version":2},"attestation_state":"computed","paper":{"title":"MaIL: A Unified Mask-Image-Language Trimodal Network for Referring Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianbiao Mei, Mengmeng Wang, Yong Liu, Zizhang Li","submitted_at":"2021-11-21T05:54:17Z","abstract_excerpt":"Referring image segmentation is a typical multi-modal task, which aims at generating a binary mask for referent described in given language expressions. Prior arts adopt a bimodal solution, taking images and languages as two modalities within an encoder-fusion-decoder pipeline. However, this pipeline is sub-optimal for the target task for two reasons. First, they only fuse high-level features produced by uni-modal encoders separately, which hinders sufficient cross-modal learning. Second, the uni-modal encoders are pre-trained independently, which brings inconsistency between pre-trained uni-m"},"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":"2111.10747","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-21T05:54:17Z","cross_cats_sorted":[],"title_canon_sha256":"ed5d8b8e0e163458c090b6f6cfa31f9ffc4944f89c35febe10b3b5b6ab62adbb","abstract_canon_sha256":"fa6f95876e4628964a6cbee0a296ee0e25eb504c5d635a4197293eedf123e345"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:57.496513Z","signature_b64":"7YWtipwnip2USN39eLMO+6kHaJjk/qQ3kT4mKyKZawhrVos2JZd4XSCgFONhcmsq7xNKVj1vzrd2SQBjPbg3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b2ac8c3511683c7283dad7c0711745dee5b661ae61c9a8cef745f8f7a743739","last_reissued_at":"2026-07-05T03:34:57.496081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:57.496081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MaIL: A Unified Mask-Image-Language Trimodal Network for Referring Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianbiao Mei, Mengmeng Wang, Yong Liu, Zizhang Li","submitted_at":"2021-11-21T05:54:17Z","abstract_excerpt":"Referring image segmentation is a typical multi-modal task, which aims at generating a binary mask for referent described in given language expressions. Prior arts adopt a bimodal solution, taking images and languages as two modalities within an encoder-fusion-decoder pipeline. However, this pipeline is sub-optimal for the target task for two reasons. First, they only fuse high-level features produced by uni-modal encoders separately, which hinders sufficient cross-modal learning. Second, the uni-modal encoders are pre-trained independently, which brings inconsistency between pre-trained uni-m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10747","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/2111.10747/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":"2111.10747","created_at":"2026-07-05T03:34:57.496132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.10747v2","created_at":"2026-07-05T03:34:57.496132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10747","created_at":"2026-07-05T03:34:57.496132+00:00"},{"alias_kind":"pith_short_12","alias_value":"HMVMRQ2RC2B4","created_at":"2026-07-05T03:34:57.496132+00:00"},{"alias_kind":"pith_short_16","alias_value":"HMVMRQ2RC2B4OKB5","created_at":"2026-07-05T03:34:57.496132+00:00"},{"alias_kind":"pith_short_8","alias_value":"HMVMRQ2R","created_at":"2026-07-05T03:34:57.496132+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19242","citing_title":"Deformable Attentive Visual Enhancement for Referring Segmentation Using Vision-Language Model","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HMVMRQ2RC2B4OKB5VV6AOELULX","json":"https://pith.science/pith/HMVMRQ2RC2B4OKB5VV6AOELULX.json","graph_json":"https://pith.science/api/pith-number/HMVMRQ2RC2B4OKB5VV6AOELULX/graph.json","events_json":"https://pith.science/api/pith-number/HMVMRQ2RC2B4OKB5VV6AOELULX/events.json","paper":"https://pith.science/paper/HMVMRQ2R"},"agent_actions":{"view_html":"https://pith.science/pith/HMVMRQ2RC2B4OKB5VV6AOELULX","download_json":"https://pith.science/pith/HMVMRQ2RC2B4OKB5VV6AOELULX.json","view_paper":"https://pith.science/paper/HMVMRQ2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.10747&json=true","fetch_graph":"https://pith.science/api/pith-number/HMVMRQ2RC2B4OKB5VV6AOELULX/graph.json","fetch_events":"https://pith.science/api/pith-number/HMVMRQ2RC2B4OKB5VV6AOELULX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HMVMRQ2RC2B4OKB5VV6AOELULX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HMVMRQ2RC2B4OKB5VV6AOELULX/action/storage_attestation","attest_author":"https://pith.science/pith/HMVMRQ2RC2B4OKB5VV6AOELULX/action/author_attestation","sign_citation":"https://pith.science/pith/HMVMRQ2RC2B4OKB5VV6AOELULX/action/citation_signature","submit_replication":"https://pith.science/pith/HMVMRQ2RC2B4OKB5VV6AOELULX/action/replication_record"}},"created_at":"2026-07-05T03:34:57.496132+00:00","updated_at":"2026-07-05T03:34:57.496132+00:00"}