{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GRE5F4TWOSXQTQZASUHCZ4ITCK","short_pith_number":"pith:GRE5F4TW","schema_version":"1.0","canonical_sha256":"3449d2f27674af09c320950e2cf1131288e679e20b7f59491421c5d9d9f1747a","source":{"kind":"arxiv","id":"2105.04143","version":2},"attestation_state":"computed","paper":{"title":"Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Bo Chen, Dandan Guo, Mingyuan Zhou, Ruiying Lu, Zequn Zeng","submitted_at":"2021-05-10T06:55:39Z","abstract_excerpt":"Observing a set of images and their corresponding paragraph-captions, a challenging task is to learn how to produce a semantically coherent paragraph to describe the visual content of an image. Inspired by recent successes in integrating semantic topics into this task, this paper develops a plug-and-play hierarchical-topic-guided image paragraph generation framework, which couples a visual extractor with a deep topic model to guide the learning of a language model. To capture the correlations between the image and text at multiple levels of abstraction and learn the semantic topics from images"},"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":"2105.04143","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-10T06:55:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"51fe508569c8da6b2102af1227d3de97d7d8294c1d53c05b6792522fb51057b7","abstract_canon_sha256":"29f296fa9f2126eb63914f73fb4f7fa08956038ff1c5d606d6f4f72ed91cb872"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:43:17.992408Z","signature_b64":"8o22R+TNPWuDJls87m9cOEijTZhyXazG7NfMbT+pdJxItzax/5z3sa6XUXN6qmfJ4CmjwgE7taPCaX9uql4pAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3449d2f27674af09c320950e2cf1131288e679e20b7f59491421c5d9d9f1747a","last_reissued_at":"2026-07-05T04:43:17.992038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:43:17.992038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Bo Chen, Dandan Guo, Mingyuan Zhou, Ruiying Lu, Zequn Zeng","submitted_at":"2021-05-10T06:55:39Z","abstract_excerpt":"Observing a set of images and their corresponding paragraph-captions, a challenging task is to learn how to produce a semantically coherent paragraph to describe the visual content of an image. Inspired by recent successes in integrating semantic topics into this task, this paper develops a plug-and-play hierarchical-topic-guided image paragraph generation framework, which couples a visual extractor with a deep topic model to guide the learning of a language model. To capture the correlations between the image and text at multiple levels of abstraction and learn the semantic topics from images"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.04143","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/2105.04143/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":"2105.04143","created_at":"2026-07-05T04:43:17.992094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.04143v2","created_at":"2026-07-05T04:43:17.992094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.04143","created_at":"2026-07-05T04:43:17.992094+00:00"},{"alias_kind":"pith_short_12","alias_value":"GRE5F4TWOSXQ","created_at":"2026-07-05T04:43:17.992094+00:00"},{"alias_kind":"pith_short_16","alias_value":"GRE5F4TWOSXQTQZA","created_at":"2026-07-05T04:43:17.992094+00:00"},{"alias_kind":"pith_short_8","alias_value":"GRE5F4TW","created_at":"2026-07-05T04:43:17.992094+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/GRE5F4TWOSXQTQZASUHCZ4ITCK","json":"https://pith.science/pith/GRE5F4TWOSXQTQZASUHCZ4ITCK.json","graph_json":"https://pith.science/api/pith-number/GRE5F4TWOSXQTQZASUHCZ4ITCK/graph.json","events_json":"https://pith.science/api/pith-number/GRE5F4TWOSXQTQZASUHCZ4ITCK/events.json","paper":"https://pith.science/paper/GRE5F4TW"},"agent_actions":{"view_html":"https://pith.science/pith/GRE5F4TWOSXQTQZASUHCZ4ITCK","download_json":"https://pith.science/pith/GRE5F4TWOSXQTQZASUHCZ4ITCK.json","view_paper":"https://pith.science/paper/GRE5F4TW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.04143&json=true","fetch_graph":"https://pith.science/api/pith-number/GRE5F4TWOSXQTQZASUHCZ4ITCK/graph.json","fetch_events":"https://pith.science/api/pith-number/GRE5F4TWOSXQTQZASUHCZ4ITCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GRE5F4TWOSXQTQZASUHCZ4ITCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GRE5F4TWOSXQTQZASUHCZ4ITCK/action/storage_attestation","attest_author":"https://pith.science/pith/GRE5F4TWOSXQTQZASUHCZ4ITCK/action/author_attestation","sign_citation":"https://pith.science/pith/GRE5F4TWOSXQTQZASUHCZ4ITCK/action/citation_signature","submit_replication":"https://pith.science/pith/GRE5F4TWOSXQTQZASUHCZ4ITCK/action/replication_record"}},"created_at":"2026-07-05T04:43:17.992094+00:00","updated_at":"2026-07-05T04:43:17.992094+00:00"}