{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7V4O3JDVVEXDL74AFCZX2VJ7B7","short_pith_number":"pith:7V4O3JDV","schema_version":"1.0","canonical_sha256":"fd78eda475a92e35ff8028b37d553f0fea0cb951b4e0ddbe61a38fdae7705856","source":{"kind":"arxiv","id":"2103.11186","version":1},"attestation_state":"computed","paper":{"title":"3M: Multi-style image caption generation using Multi-modality features under Multi-UPDOWN model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brent Harrison, Chengxi Li","submitted_at":"2021-03-20T14:12:13Z","abstract_excerpt":"In this paper, we build a multi-style generative model for stylish image captioning which uses multi-modality image features, ResNeXt features and text features generated by DenseCap. We propose the 3M model, a Multi-UPDOWN caption model that encodes multi-modality features and decode them to captions. We demonstrate the effectiveness of our model on generating human-like captions by examining its performance on two datasets, the PERSONALITY-CAPTIONS dataset and the FlickrStyle10K dataset. We compare against a variety of state-of-the-art baselines on various automatic NLP metrics such as BLEU,"},"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":"2103.11186","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-20T14:12:13Z","cross_cats_sorted":[],"title_canon_sha256":"fac9e63472622b597d044925a54ee1a9b0722e6d7e778f6fdad387066a47dccc","abstract_canon_sha256":"9141d583b207c502db87b9fe8b65a2c9a3bce1feef50deaf2f9a8ea6bc607dc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:57.614887Z","signature_b64":"HbyIZtAWIbN+ExLRYN4U0nG97y6bq2KA3Q/N1vu20kumDAyl5q5ljfPb7xpr7TuZUy1zmS93Zsuiwy3t93JDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd78eda475a92e35ff8028b37d553f0fea0cb951b4e0ddbe61a38fdae7705856","last_reissued_at":"2026-07-05T02:24:57.614508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:57.614508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3M: Multi-style image caption generation using Multi-modality features under Multi-UPDOWN model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brent Harrison, Chengxi Li","submitted_at":"2021-03-20T14:12:13Z","abstract_excerpt":"In this paper, we build a multi-style generative model for stylish image captioning which uses multi-modality image features, ResNeXt features and text features generated by DenseCap. We propose the 3M model, a Multi-UPDOWN caption model that encodes multi-modality features and decode them to captions. We demonstrate the effectiveness of our model on generating human-like captions by examining its performance on two datasets, the PERSONALITY-CAPTIONS dataset and the FlickrStyle10K dataset. We compare against a variety of state-of-the-art baselines on various automatic NLP metrics such as BLEU,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.11186","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/2103.11186/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":"2103.11186","created_at":"2026-07-05T02:24:57.614566+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.11186v1","created_at":"2026-07-05T02:24:57.614566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.11186","created_at":"2026-07-05T02:24:57.614566+00:00"},{"alias_kind":"pith_short_12","alias_value":"7V4O3JDVVEXD","created_at":"2026-07-05T02:24:57.614566+00:00"},{"alias_kind":"pith_short_16","alias_value":"7V4O3JDVVEXDL74A","created_at":"2026-07-05T02:24:57.614566+00:00"},{"alias_kind":"pith_short_8","alias_value":"7V4O3JDV","created_at":"2026-07-05T02:24:57.614566+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/7V4O3JDVVEXDL74AFCZX2VJ7B7","json":"https://pith.science/pith/7V4O3JDVVEXDL74AFCZX2VJ7B7.json","graph_json":"https://pith.science/api/pith-number/7V4O3JDVVEXDL74AFCZX2VJ7B7/graph.json","events_json":"https://pith.science/api/pith-number/7V4O3JDVVEXDL74AFCZX2VJ7B7/events.json","paper":"https://pith.science/paper/7V4O3JDV"},"agent_actions":{"view_html":"https://pith.science/pith/7V4O3JDVVEXDL74AFCZX2VJ7B7","download_json":"https://pith.science/pith/7V4O3JDVVEXDL74AFCZX2VJ7B7.json","view_paper":"https://pith.science/paper/7V4O3JDV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.11186&json=true","fetch_graph":"https://pith.science/api/pith-number/7V4O3JDVVEXDL74AFCZX2VJ7B7/graph.json","fetch_events":"https://pith.science/api/pith-number/7V4O3JDVVEXDL74AFCZX2VJ7B7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7V4O3JDVVEXDL74AFCZX2VJ7B7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7V4O3JDVVEXDL74AFCZX2VJ7B7/action/storage_attestation","attest_author":"https://pith.science/pith/7V4O3JDVVEXDL74AFCZX2VJ7B7/action/author_attestation","sign_citation":"https://pith.science/pith/7V4O3JDVVEXDL74AFCZX2VJ7B7/action/citation_signature","submit_replication":"https://pith.science/pith/7V4O3JDVVEXDL74AFCZX2VJ7B7/action/replication_record"}},"created_at":"2026-07-05T02:24:57.614566+00:00","updated_at":"2026-07-05T02:24:57.614566+00:00"}