{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6GF4E752JQ7HY7DAM4AK2NUOKD","short_pith_number":"pith:6GF4E752","schema_version":"1.0","canonical_sha256":"f18bc27fba4c3e7c7c606700ad368e50d8334ef9e314fcca0fa829e3577a82fc","source":{"kind":"arxiv","id":"1903.07520","version":2},"attestation_state":"computed","paper":{"title":"EV-IMO: Motion Segmentation Dataset and Learning Pipeline for Event Cameras","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anton Mitrokhin, Chengxi Ye, Cornelia Fermuller, Tobi Delbruck, Yiannis Aloimonos","submitted_at":"2019-03-18T15:51:25Z","abstract_excerpt":"We present the first event-based learning approach for motion segmentation in indoor scenes and the first event-based dataset - EV-IMO - which includes accurate pixel-wise motion masks, egomotion and ground truth depth. Our approach is based on an efficient implementation of the SfM learning pipeline using a low parameter neural network architecture on event data. In addition to camera egomotion and a dense depth map, the network estimates pixel-wise independently moving object segmentation and computes per-object 3D translational velocities for moving objects. We also train a shallow network "},"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":"1903.07520","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-18T15:51:25Z","cross_cats_sorted":[],"title_canon_sha256":"90008b673a93bcb813d9eaf496d822b67b5a52e03b71c9fe454663aa504d1cca","abstract_canon_sha256":"25efb7e72d2e67bd1848a23d1ab4e06d434968380e5d33eb010346b0490ec7f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:32:48.880578Z","signature_b64":"S1HlHUUaRRcU4kd1cxwjelHMWIP5FdxznUwsGv4PfP2zi22xKcks4cdRV23tTxnyGfQoT3pcmQnY/behZpReBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f18bc27fba4c3e7c7c606700ad368e50d8334ef9e314fcca0fa829e3577a82fc","last_reissued_at":"2026-07-05T00:32:48.880103Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:32:48.880103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EV-IMO: Motion Segmentation Dataset and Learning Pipeline for Event Cameras","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anton Mitrokhin, Chengxi Ye, Cornelia Fermuller, Tobi Delbruck, Yiannis Aloimonos","submitted_at":"2019-03-18T15:51:25Z","abstract_excerpt":"We present the first event-based learning approach for motion segmentation in indoor scenes and the first event-based dataset - EV-IMO - which includes accurate pixel-wise motion masks, egomotion and ground truth depth. Our approach is based on an efficient implementation of the SfM learning pipeline using a low parameter neural network architecture on event data. In addition to camera egomotion and a dense depth map, the network estimates pixel-wise independently moving object segmentation and computes per-object 3D translational velocities for moving objects. We also train a shallow network "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.07520","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/1903.07520/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":"1903.07520","created_at":"2026-07-05T00:32:48.880161+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.07520v2","created_at":"2026-07-05T00:32:48.880161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.07520","created_at":"2026-07-05T00:32:48.880161+00:00"},{"alias_kind":"pith_short_12","alias_value":"6GF4E752JQ7H","created_at":"2026-07-05T00:32:48.880161+00:00"},{"alias_kind":"pith_short_16","alias_value":"6GF4E752JQ7HY7DA","created_at":"2026-07-05T00:32:48.880161+00:00"},{"alias_kind":"pith_short_8","alias_value":"6GF4E752","created_at":"2026-07-05T00:32:48.880161+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.01547","citing_title":"Aerial multi-object tracking by detection using deep association networks","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6GF4E752JQ7HY7DAM4AK2NUOKD","json":"https://pith.science/pith/6GF4E752JQ7HY7DAM4AK2NUOKD.json","graph_json":"https://pith.science/api/pith-number/6GF4E752JQ7HY7DAM4AK2NUOKD/graph.json","events_json":"https://pith.science/api/pith-number/6GF4E752JQ7HY7DAM4AK2NUOKD/events.json","paper":"https://pith.science/paper/6GF4E752"},"agent_actions":{"view_html":"https://pith.science/pith/6GF4E752JQ7HY7DAM4AK2NUOKD","download_json":"https://pith.science/pith/6GF4E752JQ7HY7DAM4AK2NUOKD.json","view_paper":"https://pith.science/paper/6GF4E752","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.07520&json=true","fetch_graph":"https://pith.science/api/pith-number/6GF4E752JQ7HY7DAM4AK2NUOKD/graph.json","fetch_events":"https://pith.science/api/pith-number/6GF4E752JQ7HY7DAM4AK2NUOKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6GF4E752JQ7HY7DAM4AK2NUOKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6GF4E752JQ7HY7DAM4AK2NUOKD/action/storage_attestation","attest_author":"https://pith.science/pith/6GF4E752JQ7HY7DAM4AK2NUOKD/action/author_attestation","sign_citation":"https://pith.science/pith/6GF4E752JQ7HY7DAM4AK2NUOKD/action/citation_signature","submit_replication":"https://pith.science/pith/6GF4E752JQ7HY7DAM4AK2NUOKD/action/replication_record"}},"created_at":"2026-07-05T00:32:48.880161+00:00","updated_at":"2026-07-05T00:32:48.880161+00:00"}