{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:42LBJG6R65DVG5NPDJKVQMJDF5","short_pith_number":"pith:42LBJG6R","schema_version":"1.0","canonical_sha256":"e696149bd1f7475375af1a555831232f4678a41ba07e67a0a1d8156269087009","source":{"kind":"arxiv","id":"2203.09043","version":1},"attestation_state":"computed","paper":{"title":"Latent Image Animator: Learning to Animate Images via Latent Space Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antitza Dantcheva, Di Yang, Francois Bremond, Yaohui Wang","submitted_at":"2022-03-17T02:45:34Z","abstract_excerpt":"Due to the remarkable progress of deep generative models, animating images has become increasingly efficient, whereas associated results have become increasingly realistic. Current animation-approaches commonly exploit structure representation extracted from driving videos. Such structure representation is instrumental in transferring motion from driving videos to still images. However, such approaches fail in case the source image and driving video encompass large appearance variation. Moreover, the extraction of structure information requires additional modules that endow the animation-model"},"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":"2203.09043","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-17T02:45:34Z","cross_cats_sorted":[],"title_canon_sha256":"7b26337e38a5749692c5dae235a59a291226801eb85c9d8fc8975a6791b7018a","abstract_canon_sha256":"bec4550541f93153b1e3a5bc81a5613fd2965d8e940e12346e5cba0d5a18a73b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:06.457978Z","signature_b64":"06/mxRAXvPsXFtYCertUXGb9Vxobfp7414DjKlttgsLwo/WhksUgKZT4PCrjoWObLknGeY2P3TuCEXA1S6g1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e696149bd1f7475375af1a555831232f4678a41ba07e67a0a1d8156269087009","last_reissued_at":"2026-07-05T04:06:06.457432Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:06.457432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Image Animator: Learning to Animate Images via Latent Space Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antitza Dantcheva, Di Yang, Francois Bremond, Yaohui Wang","submitted_at":"2022-03-17T02:45:34Z","abstract_excerpt":"Due to the remarkable progress of deep generative models, animating images has become increasingly efficient, whereas associated results have become increasingly realistic. Current animation-approaches commonly exploit structure representation extracted from driving videos. Such structure representation is instrumental in transferring motion from driving videos to still images. However, such approaches fail in case the source image and driving video encompass large appearance variation. Moreover, the extraction of structure information requires additional modules that endow the animation-model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.09043","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/2203.09043/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":"2203.09043","created_at":"2026-07-05T04:06:06.457488+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.09043v1","created_at":"2026-07-05T04:06:06.457488+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.09043","created_at":"2026-07-05T04:06:06.457488+00:00"},{"alias_kind":"pith_short_12","alias_value":"42LBJG6R65DV","created_at":"2026-07-05T04:06:06.457488+00:00"},{"alias_kind":"pith_short_16","alias_value":"42LBJG6R65DVG5NP","created_at":"2026-07-05T04:06:06.457488+00:00"},{"alias_kind":"pith_short_8","alias_value":"42LBJG6R","created_at":"2026-07-05T04:06:06.457488+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06903","citing_title":"Beyond Skeletons: Learning Animation Directly from Driving Videos with Same2X Training Strategy","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2510.03548","citing_title":"Unmasking Puppeteers: Leveraging Biometric Leakage to Expose Impersonation in AI-Based Videoconferencing","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09534","citing_title":"AUHead: Realistic Emotional Talking Head Generation via Action Units Control","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2310.06114","citing_title":"Learning Interactive Real-World Simulators","ref_index":132,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25255","citing_title":"Personalized Cross-Modal Emotional Correlation Learning for Speech-Preserving Facial Expression Manipulation","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/42LBJG6R65DVG5NPDJKVQMJDF5","json":"https://pith.science/pith/42LBJG6R65DVG5NPDJKVQMJDF5.json","graph_json":"https://pith.science/api/pith-number/42LBJG6R65DVG5NPDJKVQMJDF5/graph.json","events_json":"https://pith.science/api/pith-number/42LBJG6R65DVG5NPDJKVQMJDF5/events.json","paper":"https://pith.science/paper/42LBJG6R"},"agent_actions":{"view_html":"https://pith.science/pith/42LBJG6R65DVG5NPDJKVQMJDF5","download_json":"https://pith.science/pith/42LBJG6R65DVG5NPDJKVQMJDF5.json","view_paper":"https://pith.science/paper/42LBJG6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.09043&json=true","fetch_graph":"https://pith.science/api/pith-number/42LBJG6R65DVG5NPDJKVQMJDF5/graph.json","fetch_events":"https://pith.science/api/pith-number/42LBJG6R65DVG5NPDJKVQMJDF5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42LBJG6R65DVG5NPDJKVQMJDF5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42LBJG6R65DVG5NPDJKVQMJDF5/action/storage_attestation","attest_author":"https://pith.science/pith/42LBJG6R65DVG5NPDJKVQMJDF5/action/author_attestation","sign_citation":"https://pith.science/pith/42LBJG6R65DVG5NPDJKVQMJDF5/action/citation_signature","submit_replication":"https://pith.science/pith/42LBJG6R65DVG5NPDJKVQMJDF5/action/replication_record"}},"created_at":"2026-07-05T04:06:06.457488+00:00","updated_at":"2026-07-05T04:06:06.457488+00:00"}