{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:77R5MVD5EE2AYYQFJUAPBTUYDO","short_pith_number":"pith:77R5MVD5","schema_version":"1.0","canonical_sha256":"ffe3d6547d21340c62054d00f0ce981bb9581ca0cb60f16ddc79b7baaf10c84c","source":{"kind":"arxiv","id":"2201.02074","version":3},"attestation_state":"computed","paper":{"title":"EM-driven unsupervised learning for efficient motion segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ana\\\"is Badoual, Etienne Meunier, Patrick Bouthemy","submitted_at":"2022-01-06T14:35:45Z","abstract_excerpt":"In this paper, we present a CNN-based fully unsupervised method for motion segmentation from optical flow. We assume that the input optical flow can be represented as a piecewise set of parametric motion models, typically, affine or quadratic motion models. The core idea of our work is to leverage the Expectation-Maximization (EM) framework in order to design in a well-founded manner a loss function and a training procedure of our motion segmentation neural network that does not require either ground-truth or manual annotation. However, in contrast to the classical iterative EM, once the netwo"},"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":"2201.02074","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-06T14:35:45Z","cross_cats_sorted":[],"title_canon_sha256":"c3e6a5c381f5eb45ee5972c38517dc9029d6fdd79efafb6b8eaa65b70642f591","abstract_canon_sha256":"59dcad6b599fea6daab592c20c1e5c420cc3186fb22eaea606980d775b16ad0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:50.085543Z","signature_b64":"Me15s5monjq5XX0TSJjBDCseO3cLapWrXkfWhfQqPF00lwMXz2vDiWAE+Q910y2KcaEJn/1qTjdM+dCbczznBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffe3d6547d21340c62054d00f0ce981bb9581ca0cb60f16ddc79b7baaf10c84c","last_reissued_at":"2026-07-05T05:03:50.085063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:50.085063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EM-driven unsupervised learning for efficient motion segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ana\\\"is Badoual, Etienne Meunier, Patrick Bouthemy","submitted_at":"2022-01-06T14:35:45Z","abstract_excerpt":"In this paper, we present a CNN-based fully unsupervised method for motion segmentation from optical flow. We assume that the input optical flow can be represented as a piecewise set of parametric motion models, typically, affine or quadratic motion models. The core idea of our work is to leverage the Expectation-Maximization (EM) framework in order to design in a well-founded manner a loss function and a training procedure of our motion segmentation neural network that does not require either ground-truth or manual annotation. However, in contrast to the classical iterative EM, once the netwo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.02074","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/2201.02074/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":"2201.02074","created_at":"2026-07-05T05:03:50.085118+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.02074v3","created_at":"2026-07-05T05:03:50.085118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.02074","created_at":"2026-07-05T05:03:50.085118+00:00"},{"alias_kind":"pith_short_12","alias_value":"77R5MVD5EE2A","created_at":"2026-07-05T05:03:50.085118+00:00"},{"alias_kind":"pith_short_16","alias_value":"77R5MVD5EE2AYYQF","created_at":"2026-07-05T05:03:50.085118+00:00"},{"alias_kind":"pith_short_8","alias_value":"77R5MVD5","created_at":"2026-07-05T05:03:50.085118+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.12392","citing_title":"Learning segmentation from point trajectories","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/77R5MVD5EE2AYYQFJUAPBTUYDO","json":"https://pith.science/pith/77R5MVD5EE2AYYQFJUAPBTUYDO.json","graph_json":"https://pith.science/api/pith-number/77R5MVD5EE2AYYQFJUAPBTUYDO/graph.json","events_json":"https://pith.science/api/pith-number/77R5MVD5EE2AYYQFJUAPBTUYDO/events.json","paper":"https://pith.science/paper/77R5MVD5"},"agent_actions":{"view_html":"https://pith.science/pith/77R5MVD5EE2AYYQFJUAPBTUYDO","download_json":"https://pith.science/pith/77R5MVD5EE2AYYQFJUAPBTUYDO.json","view_paper":"https://pith.science/paper/77R5MVD5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.02074&json=true","fetch_graph":"https://pith.science/api/pith-number/77R5MVD5EE2AYYQFJUAPBTUYDO/graph.json","fetch_events":"https://pith.science/api/pith-number/77R5MVD5EE2AYYQFJUAPBTUYDO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/77R5MVD5EE2AYYQFJUAPBTUYDO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/77R5MVD5EE2AYYQFJUAPBTUYDO/action/storage_attestation","attest_author":"https://pith.science/pith/77R5MVD5EE2AYYQFJUAPBTUYDO/action/author_attestation","sign_citation":"https://pith.science/pith/77R5MVD5EE2AYYQFJUAPBTUYDO/action/citation_signature","submit_replication":"https://pith.science/pith/77R5MVD5EE2AYYQFJUAPBTUYDO/action/replication_record"}},"created_at":"2026-07-05T05:03:50.085118+00:00","updated_at":"2026-07-05T05:03:50.085118+00:00"}