{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RITKXJV32EEZDCJLQ2JLYBI3NK","short_pith_number":"pith:RITKXJV3","schema_version":"1.0","canonical_sha256":"8a26aba6bbd10991892b8692bc051b6aaba9409f5720d3684bc0ba132c216543","source":{"kind":"arxiv","id":"2211.06235","version":1},"attestation_state":"computed","paper":{"title":"HumanDiffusion: a Coarse-to-Fine Alignment Diffusion Framework for Controllable Text-Driven Person Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binghao Zhao, Jianxin Sun, Kaiduo Zhang, Kunbo Zhang, Muyi Sun, Tieniu Tan, Zhenan Sun","submitted_at":"2022-11-11T14:30:34Z","abstract_excerpt":"Text-driven person image generation is an emerging and challenging task in cross-modality image generation. Controllable person image generation promotes a wide range of applications such as digital human interaction and virtual try-on. However, previous methods mostly employ single-modality information as the prior condition (e.g. pose-guided person image generation), or utilize the preset words for text-driven human synthesis. Introducing a sentence composed of free words with an editable semantic pose map to describe person appearance is a more user-friendly way. In this paper, we propose H"},"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":"2211.06235","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-11T14:30:34Z","cross_cats_sorted":[],"title_canon_sha256":"820fdc85182d5c2699e78bdb9752309b4b54955f9c18ff397b0209c865075e78","abstract_canon_sha256":"61c11cdc41ac6330c2405d93aea12e85fc35e09dd0e9897ede33a711d986b8c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:18.466480Z","signature_b64":"OnWjDymb1MKrHJY+/+WaWeFEA7Z8hKSpRW0LfOKs2nRiLN4qyQ3Hp6VJG7JMXd7pdKtiHVU6phbfPPtZKuxRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a26aba6bbd10991892b8692bc051b6aaba9409f5720d3684bc0ba132c216543","last_reissued_at":"2026-07-05T05:15:18.466078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:18.466078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HumanDiffusion: a Coarse-to-Fine Alignment Diffusion Framework for Controllable Text-Driven Person Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binghao Zhao, Jianxin Sun, Kaiduo Zhang, Kunbo Zhang, Muyi Sun, Tieniu Tan, Zhenan Sun","submitted_at":"2022-11-11T14:30:34Z","abstract_excerpt":"Text-driven person image generation is an emerging and challenging task in cross-modality image generation. Controllable person image generation promotes a wide range of applications such as digital human interaction and virtual try-on. However, previous methods mostly employ single-modality information as the prior condition (e.g. pose-guided person image generation), or utilize the preset words for text-driven human synthesis. Introducing a sentence composed of free words with an editable semantic pose map to describe person appearance is a more user-friendly way. In this paper, we propose H"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06235","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/2211.06235/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":"2211.06235","created_at":"2026-07-05T05:15:18.466131+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.06235v1","created_at":"2026-07-05T05:15:18.466131+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06235","created_at":"2026-07-05T05:15:18.466131+00:00"},{"alias_kind":"pith_short_12","alias_value":"RITKXJV32EEZ","created_at":"2026-07-05T05:15:18.466131+00:00"},{"alias_kind":"pith_short_16","alias_value":"RITKXJV32EEZDCJL","created_at":"2026-07-05T05:15:18.466131+00:00"},{"alias_kind":"pith_short_8","alias_value":"RITKXJV3","created_at":"2026-07-05T05:15:18.466131+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.12173","citing_title":"ComposeAnyone: Controllable Layout-to-Human Generation with Decoupled Multimodal Conditions","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RITKXJV32EEZDCJLQ2JLYBI3NK","json":"https://pith.science/pith/RITKXJV32EEZDCJLQ2JLYBI3NK.json","graph_json":"https://pith.science/api/pith-number/RITKXJV32EEZDCJLQ2JLYBI3NK/graph.json","events_json":"https://pith.science/api/pith-number/RITKXJV32EEZDCJLQ2JLYBI3NK/events.json","paper":"https://pith.science/paper/RITKXJV3"},"agent_actions":{"view_html":"https://pith.science/pith/RITKXJV32EEZDCJLQ2JLYBI3NK","download_json":"https://pith.science/pith/RITKXJV32EEZDCJLQ2JLYBI3NK.json","view_paper":"https://pith.science/paper/RITKXJV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.06235&json=true","fetch_graph":"https://pith.science/api/pith-number/RITKXJV32EEZDCJLQ2JLYBI3NK/graph.json","fetch_events":"https://pith.science/api/pith-number/RITKXJV32EEZDCJLQ2JLYBI3NK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RITKXJV32EEZDCJLQ2JLYBI3NK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RITKXJV32EEZDCJLQ2JLYBI3NK/action/storage_attestation","attest_author":"https://pith.science/pith/RITKXJV32EEZDCJLQ2JLYBI3NK/action/author_attestation","sign_citation":"https://pith.science/pith/RITKXJV32EEZDCJLQ2JLYBI3NK/action/citation_signature","submit_replication":"https://pith.science/pith/RITKXJV32EEZDCJLQ2JLYBI3NK/action/replication_record"}},"created_at":"2026-07-05T05:15:18.466131+00:00","updated_at":"2026-07-05T05:15:18.466131+00:00"}