{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RGZDQOTLSYIFZJUX3BDMYOJWMP","short_pith_number":"pith:RGZDQOTL","schema_version":"1.0","canonical_sha256":"89b2383a6b96105ca697d846cc393663d1f8db0651f867be351ccf8f119542b4","source":{"kind":"arxiv","id":"2305.05226","version":2},"attestation_state":"computed","paper":{"title":"Multi-Teacher Knowledge Distillation For Text Image Machine Translation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengqing Zong, Cong Ma, Mei Tu, Yang Zhao, Yaping Zhang, Yu Zhou","submitted_at":"2023-05-09T07:41:17Z","abstract_excerpt":"Text image machine translation (TIMT) has been widely used in various real-world applications, which translates source language texts in images into another target language sentence. Existing methods on TIMT are mainly divided into two categories: the recognition-then-translation pipeline model and the end-to-end model. However, how to transfer knowledge from the pipeline model into the end-to-end model remains an unsolved problem. In this paper, we propose a novel Multi-Teacher Knowledge Distillation (MTKD) method to effectively distillate knowledge into the end-to-end TIMT model from the pip"},"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":"2305.05226","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-09T07:41:17Z","cross_cats_sorted":[],"title_canon_sha256":"4939d84f8406196f084adc00b2e037442fd0211b2a3e7a161e76df2ec8f3cb9a","abstract_canon_sha256":"2d4176cfcfd33c12d389b086ca51fc8dc58dac9bd43da786ddfc7998963fa0d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:08:56.023177Z","signature_b64":"6CaV0wYGxfQQqKyHlQE+GkN6s8kDIwnJFWeQvJpGGffKde+06zx8E7x4lKGn+6nflGr0tSmvdW8tYRyQ4PvSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89b2383a6b96105ca697d846cc393663d1f8db0651f867be351ccf8f119542b4","last_reissued_at":"2026-07-05T06:08:56.022689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:08:56.022689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Teacher Knowledge Distillation For Text Image Machine Translation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengqing Zong, Cong Ma, Mei Tu, Yang Zhao, Yaping Zhang, Yu Zhou","submitted_at":"2023-05-09T07:41:17Z","abstract_excerpt":"Text image machine translation (TIMT) has been widely used in various real-world applications, which translates source language texts in images into another target language sentence. Existing methods on TIMT are mainly divided into two categories: the recognition-then-translation pipeline model and the end-to-end model. However, how to transfer knowledge from the pipeline model into the end-to-end model remains an unsolved problem. In this paper, we propose a novel Multi-Teacher Knowledge Distillation (MTKD) method to effectively distillate knowledge into the end-to-end TIMT model from the pip"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05226","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/2305.05226/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":"2305.05226","created_at":"2026-07-05T06:08:56.022747+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.05226v2","created_at":"2026-07-05T06:08:56.022747+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05226","created_at":"2026-07-05T06:08:56.022747+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGZDQOTLSYIF","created_at":"2026-07-05T06:08:56.022747+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGZDQOTLSYIFZJUX","created_at":"2026-07-05T06:08:56.022747+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGZDQOTL","created_at":"2026-07-05T06:08:56.022747+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/RGZDQOTLSYIFZJUX3BDMYOJWMP","json":"https://pith.science/pith/RGZDQOTLSYIFZJUX3BDMYOJWMP.json","graph_json":"https://pith.science/api/pith-number/RGZDQOTLSYIFZJUX3BDMYOJWMP/graph.json","events_json":"https://pith.science/api/pith-number/RGZDQOTLSYIFZJUX3BDMYOJWMP/events.json","paper":"https://pith.science/paper/RGZDQOTL"},"agent_actions":{"view_html":"https://pith.science/pith/RGZDQOTLSYIFZJUX3BDMYOJWMP","download_json":"https://pith.science/pith/RGZDQOTLSYIFZJUX3BDMYOJWMP.json","view_paper":"https://pith.science/paper/RGZDQOTL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.05226&json=true","fetch_graph":"https://pith.science/api/pith-number/RGZDQOTLSYIFZJUX3BDMYOJWMP/graph.json","fetch_events":"https://pith.science/api/pith-number/RGZDQOTLSYIFZJUX3BDMYOJWMP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGZDQOTLSYIFZJUX3BDMYOJWMP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGZDQOTLSYIFZJUX3BDMYOJWMP/action/storage_attestation","attest_author":"https://pith.science/pith/RGZDQOTLSYIFZJUX3BDMYOJWMP/action/author_attestation","sign_citation":"https://pith.science/pith/RGZDQOTLSYIFZJUX3BDMYOJWMP/action/citation_signature","submit_replication":"https://pith.science/pith/RGZDQOTLSYIFZJUX3BDMYOJWMP/action/replication_record"}},"created_at":"2026-07-05T06:08:56.022747+00:00","updated_at":"2026-07-05T06:08:56.022747+00:00"}