{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XABYAEUYUW5YGGF6Y246Y4RYRL","short_pith_number":"pith:XABYAEUY","schema_version":"1.0","canonical_sha256":"b803801298a5bb8318bec6b9ec72388ad362f9a6ee0872c4a1967f863132fa3b","source":{"kind":"arxiv","id":"2201.12596","version":3},"attestation_state":"computed","paper":{"title":"MVPTR: Multi-Level Semantic Alignment for Vision-Language Pre-Training via Multi-Stage Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Huaixiao Tou, Jingjing Chen, Xuanjing Huang, Zejun Li, Zhihao Fan, Zhongyu Wei","submitted_at":"2022-01-29T14:30:59Z","abstract_excerpt":"Previous vision-language pre-training models mainly construct multi-modal inputs with tokens and objects (pixels) followed by performing cross-modality interaction between them. We argue that the input of only tokens and object features limits high-level semantic alignment like phrase-to-region grounding. Meanwhile, multi-level alignments are inherently consistent and able to facilitate the representation learning synergistically. Therefore, in this paper, we propose to learn Multi-level semantic alignment for Vision-language Pre-TRaining (MVPTR). In MVPTR, we follow the nested structure of bo"},"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":"2201.12596","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-29T14:30:59Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"c25eed216791c2cde5613369733e04ebd2cc74b2769503cb8eb6824dc225bf77","abstract_canon_sha256":"c18100aa5fd10cc08f1637bbbd2ec4d939ae687799891ae5289d1e475a80e223"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:24.062923Z","signature_b64":"O2CJ/k8ODTUO5mxUMtuI85lME0qLZ3TPwHj890PcMuugGF529ElKiN9D5EX6Q27CC/+nBM4dJAJV87cBSpYhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b803801298a5bb8318bec6b9ec72388ad362f9a6ee0872c4a1967f863132fa3b","last_reissued_at":"2026-07-05T04:57:24.062489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:24.062489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MVPTR: Multi-Level Semantic Alignment for Vision-Language Pre-Training via Multi-Stage Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Huaixiao Tou, Jingjing Chen, Xuanjing Huang, Zejun Li, Zhihao Fan, Zhongyu Wei","submitted_at":"2022-01-29T14:30:59Z","abstract_excerpt":"Previous vision-language pre-training models mainly construct multi-modal inputs with tokens and objects (pixels) followed by performing cross-modality interaction between them. We argue that the input of only tokens and object features limits high-level semantic alignment like phrase-to-region grounding. Meanwhile, multi-level alignments are inherently consistent and able to facilitate the representation learning synergistically. Therefore, in this paper, we propose to learn Multi-level semantic alignment for Vision-language Pre-TRaining (MVPTR). In MVPTR, we follow the nested structure of bo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.12596","kind":"arxiv","version":3},"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/2201.12596/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":"2201.12596","created_at":"2026-07-05T04:57:24.062546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.12596v3","created_at":"2026-07-05T04:57:24.062546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.12596","created_at":"2026-07-05T04:57:24.062546+00:00"},{"alias_kind":"pith_short_12","alias_value":"XABYAEUYUW5Y","created_at":"2026-07-05T04:57:24.062546+00:00"},{"alias_kind":"pith_short_16","alias_value":"XABYAEUYUW5YGGF6","created_at":"2026-07-05T04:57:24.062546+00:00"},{"alias_kind":"pith_short_8","alias_value":"XABYAEUY","created_at":"2026-07-05T04:57:24.062546+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/XABYAEUYUW5YGGF6Y246Y4RYRL","json":"https://pith.science/pith/XABYAEUYUW5YGGF6Y246Y4RYRL.json","graph_json":"https://pith.science/api/pith-number/XABYAEUYUW5YGGF6Y246Y4RYRL/graph.json","events_json":"https://pith.science/api/pith-number/XABYAEUYUW5YGGF6Y246Y4RYRL/events.json","paper":"https://pith.science/paper/XABYAEUY"},"agent_actions":{"view_html":"https://pith.science/pith/XABYAEUYUW5YGGF6Y246Y4RYRL","download_json":"https://pith.science/pith/XABYAEUYUW5YGGF6Y246Y4RYRL.json","view_paper":"https://pith.science/paper/XABYAEUY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.12596&json=true","fetch_graph":"https://pith.science/api/pith-number/XABYAEUYUW5YGGF6Y246Y4RYRL/graph.json","fetch_events":"https://pith.science/api/pith-number/XABYAEUYUW5YGGF6Y246Y4RYRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XABYAEUYUW5YGGF6Y246Y4RYRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XABYAEUYUW5YGGF6Y246Y4RYRL/action/storage_attestation","attest_author":"https://pith.science/pith/XABYAEUYUW5YGGF6Y246Y4RYRL/action/author_attestation","sign_citation":"https://pith.science/pith/XABYAEUYUW5YGGF6Y246Y4RYRL/action/citation_signature","submit_replication":"https://pith.science/pith/XABYAEUYUW5YGGF6Y246Y4RYRL/action/replication_record"}},"created_at":"2026-07-05T04:57:24.062546+00:00","updated_at":"2026-07-05T04:57:24.062546+00:00"}