{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SXYPGQ5NDMGLUGXGYAVGFKYMB4","short_pith_number":"pith:SXYPGQ5N","schema_version":"1.0","canonical_sha256":"95f0f343ad1b0cba1ae6c02a62ab0c0f0a9aa19e052a61188376643064d8baa9","source":{"kind":"arxiv","id":"2411.19141","version":1},"attestation_state":"computed","paper":{"title":"On Moving Object Segmentation from Monocular Video with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Christian Homeyer, Christoph Schn\\\"orr","submitted_at":"2024-11-28T13:42:35Z","abstract_excerpt":"Moving object detection and segmentation from a single moving camera is a challenging task, requiring an understanding of recognition, motion and 3D geometry. Combining both recognition and reconstruction boils down to a fusion problem, where appearance and motion features need to be combined for classification and segmentation. In this paper, we present a novel fusion architecture for monocular motion segmentation - M3Former, which leverages the strong performance of transformers for segmentation and multi-modal fusion. As reconstructing motion from monocular video is ill-posed, we systematic"},"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":"2411.19141","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-28T13:42:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7aa96dfaa140f499a4ed5e0f1d80aa50fd73d4b4bc332571e01e0e40c0d1a202","abstract_canon_sha256":"af21f5ff11760d38f4406536d5d801d02fbca7545ce7f6a362c4da202307f19d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:57.826250Z","signature_b64":"sSB+zooyl0jqV1pMgsFLV0j08Z6BBGFm6P+xHrf++R6Do+eXNfx05jt9nCP2LoL/Rl/yDPXmNstg2tTi65iGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95f0f343ad1b0cba1ae6c02a62ab0c0f0a9aa19e052a61188376643064d8baa9","last_reissued_at":"2026-07-05T09:41:57.825741Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:57.825741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Moving Object Segmentation from Monocular Video with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Christian Homeyer, Christoph Schn\\\"orr","submitted_at":"2024-11-28T13:42:35Z","abstract_excerpt":"Moving object detection and segmentation from a single moving camera is a challenging task, requiring an understanding of recognition, motion and 3D geometry. Combining both recognition and reconstruction boils down to a fusion problem, where appearance and motion features need to be combined for classification and segmentation. In this paper, we present a novel fusion architecture for monocular motion segmentation - M3Former, which leverages the strong performance of transformers for segmentation and multi-modal fusion. As reconstructing motion from monocular video is ill-posed, we systematic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19141","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/2411.19141/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":"2411.19141","created_at":"2026-07-05T09:41:57.825802+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.19141v1","created_at":"2026-07-05T09:41:57.825802+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19141","created_at":"2026-07-05T09:41:57.825802+00:00"},{"alias_kind":"pith_short_12","alias_value":"SXYPGQ5NDMGL","created_at":"2026-07-05T09:41:57.825802+00:00"},{"alias_kind":"pith_short_16","alias_value":"SXYPGQ5NDMGLUGXG","created_at":"2026-07-05T09:41:57.825802+00:00"},{"alias_kind":"pith_short_8","alias_value":"SXYPGQ5N","created_at":"2026-07-05T09:41:57.825802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01535","citing_title":"STAR-VLM: Spatiotemporal Grounding Vision-Language Models for Motion and Velocity Estimation via Automotive Radar Supervision","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SXYPGQ5NDMGLUGXGYAVGFKYMB4","json":"https://pith.science/pith/SXYPGQ5NDMGLUGXGYAVGFKYMB4.json","graph_json":"https://pith.science/api/pith-number/SXYPGQ5NDMGLUGXGYAVGFKYMB4/graph.json","events_json":"https://pith.science/api/pith-number/SXYPGQ5NDMGLUGXGYAVGFKYMB4/events.json","paper":"https://pith.science/paper/SXYPGQ5N"},"agent_actions":{"view_html":"https://pith.science/pith/SXYPGQ5NDMGLUGXGYAVGFKYMB4","download_json":"https://pith.science/pith/SXYPGQ5NDMGLUGXGYAVGFKYMB4.json","view_paper":"https://pith.science/paper/SXYPGQ5N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.19141&json=true","fetch_graph":"https://pith.science/api/pith-number/SXYPGQ5NDMGLUGXGYAVGFKYMB4/graph.json","fetch_events":"https://pith.science/api/pith-number/SXYPGQ5NDMGLUGXGYAVGFKYMB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SXYPGQ5NDMGLUGXGYAVGFKYMB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SXYPGQ5NDMGLUGXGYAVGFKYMB4/action/storage_attestation","attest_author":"https://pith.science/pith/SXYPGQ5NDMGLUGXGYAVGFKYMB4/action/author_attestation","sign_citation":"https://pith.science/pith/SXYPGQ5NDMGLUGXGYAVGFKYMB4/action/citation_signature","submit_replication":"https://pith.science/pith/SXYPGQ5NDMGLUGXGYAVGFKYMB4/action/replication_record"}},"created_at":"2026-07-05T09:41:57.825802+00:00","updated_at":"2026-07-05T09:41:57.825802+00:00"}