{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KMH7AYRSEDJZUEHEPIJO6VY6OY","short_pith_number":"pith:KMH7AYRS","schema_version":"1.0","canonical_sha256":"530ff0623220d39a10e47a12ef571e760f3dfc5786f0fa93577749ddfc567dc3","source":{"kind":"arxiv","id":"1812.08861","version":3},"attestation_state":"computed","paper":{"title":"Animating Arbitrary Objects via Deep Motion Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.ML"],"primary_cat":"cs.GR","authors_text":"Aliaksandr Siarohin, Elisa Ricci, Nicu Sebe, Sergey Tulyakov, St\\'ephane Lathuili\\`ere","submitted_at":"2018-12-20T21:45:56Z","abstract_excerpt":"This paper introduces a novel deep learning framework for image animation. Given an input image with a target object and a driving video sequence depicting a moving object, our framework generates a video in which the target object is animated according to the driving sequence. This is achieved through a deep architecture that decouples appearance and motion information. Our framework consists of three main modules: (i) a Keypoint Detector unsupervisely trained to extract object keypoints, (ii) a Dense Motion prediction network for generating dense heatmaps from sparse keypoints, in order to b"},"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":"1812.08861","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2018-12-20T21:45:56Z","cross_cats_sorted":["cs.CV","cs.LG","stat.ML"],"title_canon_sha256":"8c91ff61dfb35b0dd63301ee56fef3a61d449ff857d54a0fd81069658834a551","abstract_canon_sha256":"3494a5767d54e7e582b42c43d7c0a3749d47f9d7adf8ff76d6f3a77a2b73419c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:00:53.979077Z","signature_b64":"EKUCIwhBawO++7el+yGNwM57s+BXzdGVuey8+YgjCWiyefaFs6Fh2Ditqa6fiVfM1o+hF7XGF1kNokBQBpPRBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"530ff0623220d39a10e47a12ef571e760f3dfc5786f0fa93577749ddfc567dc3","last_reissued_at":"2026-07-05T00:00:53.978593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:00:53.978593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Animating Arbitrary Objects via Deep Motion Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.ML"],"primary_cat":"cs.GR","authors_text":"Aliaksandr Siarohin, Elisa Ricci, Nicu Sebe, Sergey Tulyakov, St\\'ephane Lathuili\\`ere","submitted_at":"2018-12-20T21:45:56Z","abstract_excerpt":"This paper introduces a novel deep learning framework for image animation. Given an input image with a target object and a driving video sequence depicting a moving object, our framework generates a video in which the target object is animated according to the driving sequence. This is achieved through a deep architecture that decouples appearance and motion information. Our framework consists of three main modules: (i) a Keypoint Detector unsupervisely trained to extract object keypoints, (ii) a Dense Motion prediction network for generating dense heatmaps from sparse keypoints, in order to b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.08861","kind":"arxiv","version":3},"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/1812.08861/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":"1812.08861","created_at":"2026-07-05T00:00:53.978651+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.08861v3","created_at":"2026-07-05T00:00:53.978651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.08861","created_at":"2026-07-05T00:00:53.978651+00:00"},{"alias_kind":"pith_short_12","alias_value":"KMH7AYRSEDJZ","created_at":"2026-07-05T00:00:53.978651+00:00"},{"alias_kind":"pith_short_16","alias_value":"KMH7AYRSEDJZUEHE","created_at":"2026-07-05T00:00:53.978651+00:00"},{"alias_kind":"pith_short_8","alias_value":"KMH7AYRS","created_at":"2026-07-05T00:00:53.978651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.02749","citing_title":"Video Interpolation and Prediction with Unsupervised Landmarks","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KMH7AYRSEDJZUEHEPIJO6VY6OY","json":"https://pith.science/pith/KMH7AYRSEDJZUEHEPIJO6VY6OY.json","graph_json":"https://pith.science/api/pith-number/KMH7AYRSEDJZUEHEPIJO6VY6OY/graph.json","events_json":"https://pith.science/api/pith-number/KMH7AYRSEDJZUEHEPIJO6VY6OY/events.json","paper":"https://pith.science/paper/KMH7AYRS"},"agent_actions":{"view_html":"https://pith.science/pith/KMH7AYRSEDJZUEHEPIJO6VY6OY","download_json":"https://pith.science/pith/KMH7AYRSEDJZUEHEPIJO6VY6OY.json","view_paper":"https://pith.science/paper/KMH7AYRS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.08861&json=true","fetch_graph":"https://pith.science/api/pith-number/KMH7AYRSEDJZUEHEPIJO6VY6OY/graph.json","fetch_events":"https://pith.science/api/pith-number/KMH7AYRSEDJZUEHEPIJO6VY6OY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KMH7AYRSEDJZUEHEPIJO6VY6OY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KMH7AYRSEDJZUEHEPIJO6VY6OY/action/storage_attestation","attest_author":"https://pith.science/pith/KMH7AYRSEDJZUEHEPIJO6VY6OY/action/author_attestation","sign_citation":"https://pith.science/pith/KMH7AYRSEDJZUEHEPIJO6VY6OY/action/citation_signature","submit_replication":"https://pith.science/pith/KMH7AYRSEDJZUEHEPIJO6VY6OY/action/replication_record"}},"created_at":"2026-07-05T00:00:53.978651+00:00","updated_at":"2026-07-05T00:00:53.978651+00:00"}