{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4QDOXFWSILBJRLCVIGOPOFUNYB","short_pith_number":"pith:4QDOXFWS","schema_version":"1.0","canonical_sha256":"e406eb96d242c298ac55419cf7168dc04ebae4ede964b061704456ab3944593d","source":{"kind":"arxiv","id":"2110.12442","version":1},"attestation_state":"computed","paper":{"title":"Bangla Image Caption Generation through CNN-Transformer based Encoder-Decoder Network","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Faria Afrin, Md Abdullah Al Nasim, Md Aminul Haque Palash, Raisa Mallik, Sathishkumar Samiappan, Sourav Saha","submitted_at":"2021-10-24T13:33:23Z","abstract_excerpt":"Automatic Image Captioning is the never-ending effort of creating syntactically and validating the accuracy of textual descriptions of an image in natural language with context. The encoder-decoder structure used throughout existing Bengali Image Captioning (BIC) research utilized abstract image feature vectors as the encoder's input. We propose a novel transformer-based architecture with an attention mechanism with a pre-trained ResNet-101 model image encoder for feature extraction from images. Experiments demonstrate that the language decoder in our technique captures fine-grained informatio"},"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":"2110.12442","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-24T13:33:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f8f88110d3ab1a05aad5d558168fd0aa57800547248ee4fffc9d84b82836a421","abstract_canon_sha256":"836c2fc484e2da195220294f346cf70348e0056ca73c810c0d62f950b9e10609"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:20.433772Z","signature_b64":"CofI5QG4fPS45jDSCqhdLGpj3GZcVyP8zPa8OT+qq/Gy/HPc5zPLAe+yXCgg98rpvqEUbXzxiaEPfcmOE2rMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e406eb96d242c298ac55419cf7168dc04ebae4ede964b061704456ab3944593d","last_reissued_at":"2026-07-05T03:25:20.433446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:20.433446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bangla Image Caption Generation through CNN-Transformer based Encoder-Decoder Network","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Faria Afrin, Md Abdullah Al Nasim, Md Aminul Haque Palash, Raisa Mallik, Sathishkumar Samiappan, Sourav Saha","submitted_at":"2021-10-24T13:33:23Z","abstract_excerpt":"Automatic Image Captioning is the never-ending effort of creating syntactically and validating the accuracy of textual descriptions of an image in natural language with context. The encoder-decoder structure used throughout existing Bengali Image Captioning (BIC) research utilized abstract image feature vectors as the encoder's input. We propose a novel transformer-based architecture with an attention mechanism with a pre-trained ResNet-101 model image encoder for feature extraction from images. Experiments demonstrate that the language decoder in our technique captures fine-grained informatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12442","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/2110.12442/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":"2110.12442","created_at":"2026-07-05T03:25:20.433494+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.12442v1","created_at":"2026-07-05T03:25:20.433494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12442","created_at":"2026-07-05T03:25:20.433494+00:00"},{"alias_kind":"pith_short_12","alias_value":"4QDOXFWSILBJ","created_at":"2026-07-05T03:25:20.433494+00:00"},{"alias_kind":"pith_short_16","alias_value":"4QDOXFWSILBJRLCV","created_at":"2026-07-05T03:25:20.433494+00:00"},{"alias_kind":"pith_short_8","alias_value":"4QDOXFWS","created_at":"2026-07-05T03:25:20.433494+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/4QDOXFWSILBJRLCVIGOPOFUNYB","json":"https://pith.science/pith/4QDOXFWSILBJRLCVIGOPOFUNYB.json","graph_json":"https://pith.science/api/pith-number/4QDOXFWSILBJRLCVIGOPOFUNYB/graph.json","events_json":"https://pith.science/api/pith-number/4QDOXFWSILBJRLCVIGOPOFUNYB/events.json","paper":"https://pith.science/paper/4QDOXFWS"},"agent_actions":{"view_html":"https://pith.science/pith/4QDOXFWSILBJRLCVIGOPOFUNYB","download_json":"https://pith.science/pith/4QDOXFWSILBJRLCVIGOPOFUNYB.json","view_paper":"https://pith.science/paper/4QDOXFWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.12442&json=true","fetch_graph":"https://pith.science/api/pith-number/4QDOXFWSILBJRLCVIGOPOFUNYB/graph.json","fetch_events":"https://pith.science/api/pith-number/4QDOXFWSILBJRLCVIGOPOFUNYB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4QDOXFWSILBJRLCVIGOPOFUNYB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4QDOXFWSILBJRLCVIGOPOFUNYB/action/storage_attestation","attest_author":"https://pith.science/pith/4QDOXFWSILBJRLCVIGOPOFUNYB/action/author_attestation","sign_citation":"https://pith.science/pith/4QDOXFWSILBJRLCVIGOPOFUNYB/action/citation_signature","submit_replication":"https://pith.science/pith/4QDOXFWSILBJRLCVIGOPOFUNYB/action/replication_record"}},"created_at":"2026-07-05T03:25:20.433494+00:00","updated_at":"2026-07-05T03:25:20.433494+00:00"}