{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NAO3QES5K5S42DVFAXBDK2QY2W","short_pith_number":"pith:NAO3QES5","schema_version":"1.0","canonical_sha256":"681db8125d5765cd0ea505c2356a18d5adef9552e8da07dcf25c3f8f115943c4","source":{"kind":"arxiv","id":"2304.01186","version":2},"attestation_state":"computed","paper":{"title":"Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qifeng Chen, Siran Chen, Xiaodong Cun, Xintao Wang, Xiu Li, Yingqing He, Ying Shan, Yue Ma","submitted_at":"2023-04-03T17:55:14Z","abstract_excerpt":"Generating text-editable and pose-controllable character videos have an imperious demand in creating various digital human. Nevertheless, this task has been restricted by the absence of a comprehensive dataset featuring paired video-pose captions and the generative prior models for videos. In this work, we design a novel two-stage training scheme that can utilize easily obtained datasets (i.e.,image pose pair and pose-free video) and the pre-trained text-to-image (T2I) model to obtain the pose-controllable character videos. Specifically, in the first stage, only the keypoint-image pairs are us"},"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":"2304.01186","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-03T17:55:14Z","cross_cats_sorted":[],"title_canon_sha256":"4de4623b38eba6023c7463ae918f732c6e2e398fc6c48039292f8fc4fbd0010f","abstract_canon_sha256":"604856489064d3f56c326522c553daa2074fd0a2e89c2e5eefbac16dcc126d3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:38.291164Z","signature_b64":"xePJnZkVHlJ6c3IGd0VHpBwnP2dAFVNxHeQTExBfzweZJqc7SbG1C3bm4E6d6TRKj/GM6rpFiduzZVocCOOcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"681db8125d5765cd0ea505c2356a18d5adef9552e8da07dcf25c3f8f115943c4","last_reissued_at":"2026-07-05T07:29:38.290720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:38.290720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qifeng Chen, Siran Chen, Xiaodong Cun, Xintao Wang, Xiu Li, Yingqing He, Ying Shan, Yue Ma","submitted_at":"2023-04-03T17:55:14Z","abstract_excerpt":"Generating text-editable and pose-controllable character videos have an imperious demand in creating various digital human. Nevertheless, this task has been restricted by the absence of a comprehensive dataset featuring paired video-pose captions and the generative prior models for videos. In this work, we design a novel two-stage training scheme that can utilize easily obtained datasets (i.e.,image pose pair and pose-free video) and the pre-trained text-to-image (T2I) model to obtain the pose-controllable character videos. Specifically, in the first stage, only the keypoint-image pairs are us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.01186","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/2304.01186/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":"2304.01186","created_at":"2026-07-05T07:29:38.290772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.01186v2","created_at":"2026-07-05T07:29:38.290772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.01186","created_at":"2026-07-05T07:29:38.290772+00:00"},{"alias_kind":"pith_short_12","alias_value":"NAO3QES5K5S4","created_at":"2026-07-05T07:29:38.290772+00:00"},{"alias_kind":"pith_short_16","alias_value":"NAO3QES5K5S42DVF","created_at":"2026-07-05T07:29:38.290772+00:00"},{"alias_kind":"pith_short_8","alias_value":"NAO3QES5","created_at":"2026-07-05T07:29:38.290772+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19676","citing_title":"TeleMorpher: Toward Robust Simultaneous Motion-Location Editing","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30514","citing_title":"3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30514","citing_title":"3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18010","citing_title":"Functionalization via Structure Completion and Motion Rectification","ref_index":230,"is_internal_anchor":false},{"citing_arxiv_id":"2310.19512","citing_title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2404.02101","citing_title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","ref_index":133,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01720","citing_title":"SignVerse-2M: A Two-Million-Clip Pose-Native Universe of 55+ Sign Languages","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NAO3QES5K5S42DVFAXBDK2QY2W","json":"https://pith.science/pith/NAO3QES5K5S42DVFAXBDK2QY2W.json","graph_json":"https://pith.science/api/pith-number/NAO3QES5K5S42DVFAXBDK2QY2W/graph.json","events_json":"https://pith.science/api/pith-number/NAO3QES5K5S42DVFAXBDK2QY2W/events.json","paper":"https://pith.science/paper/NAO3QES5"},"agent_actions":{"view_html":"https://pith.science/pith/NAO3QES5K5S42DVFAXBDK2QY2W","download_json":"https://pith.science/pith/NAO3QES5K5S42DVFAXBDK2QY2W.json","view_paper":"https://pith.science/paper/NAO3QES5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.01186&json=true","fetch_graph":"https://pith.science/api/pith-number/NAO3QES5K5S42DVFAXBDK2QY2W/graph.json","fetch_events":"https://pith.science/api/pith-number/NAO3QES5K5S42DVFAXBDK2QY2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NAO3QES5K5S42DVFAXBDK2QY2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NAO3QES5K5S42DVFAXBDK2QY2W/action/storage_attestation","attest_author":"https://pith.science/pith/NAO3QES5K5S42DVFAXBDK2QY2W/action/author_attestation","sign_citation":"https://pith.science/pith/NAO3QES5K5S42DVFAXBDK2QY2W/action/citation_signature","submit_replication":"https://pith.science/pith/NAO3QES5K5S42DVFAXBDK2QY2W/action/replication_record"}},"created_at":"2026-07-05T07:29:38.290772+00:00","updated_at":"2026-07-05T07:29:38.290772+00:00"}