{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UK3SECORUZB77OM27PNTX55H77","short_pith_number":"pith:UK3SECOR","schema_version":"1.0","canonical_sha256":"a2b72209d1a643ffb99afbdb3bf7a7ffed415efe0f2bfac81203b2a352e9f07e","source":{"kind":"arxiv","id":"2409.18127","version":1},"attestation_state":"computed","paper":{"title":"EgoLM: Multi-Modal Language Model of Egocentric Motions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangzhou Hong, Hyo Jin Kim, Lingni Ma, Richard Newcombe, Vladimir Guzov, Yuting Ye, Ziwei Liu","submitted_at":"2024-09-26T17:59:31Z","abstract_excerpt":"As the prevalence of wearable devices, learning egocentric motions becomes essential to develop contextual AI. In this work, we present EgoLM, a versatile framework that tracks and understands egocentric motions from multi-modal inputs, e.g., egocentric videos and motion sensors. EgoLM exploits rich contexts for the disambiguation of egomotion tracking and understanding, which are ill-posed under single modality conditions. To facilitate the versatile and multi-modal framework, our key insight is to model the joint distribution of egocentric motions and natural languages using large language m"},"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":"2409.18127","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-26T17:59:31Z","cross_cats_sorted":[],"title_canon_sha256":"4e53035f99f8802c83b1df9a1303fbe5e0984824880249525abec096119d9452","abstract_canon_sha256":"207a136e040ee2d5aeb2dd54534e47c4a3020d8c03a860ceca919fcb16ea8b32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:21.056684Z","signature_b64":"WVhgzyTeDImSM4B5jQGCznGwXODOe+/2J0CyZfBpzbO1RFsbE8JfJX79ZVT84tljyHkUl7kqdU2njDgjQG/jAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2b72209d1a643ffb99afbdb3bf7a7ffed415efe0f2bfac81203b2a352e9f07e","last_reissued_at":"2026-07-05T09:12:21.056068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:21.056068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EgoLM: Multi-Modal Language Model of Egocentric Motions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangzhou Hong, Hyo Jin Kim, Lingni Ma, Richard Newcombe, Vladimir Guzov, Yuting Ye, Ziwei Liu","submitted_at":"2024-09-26T17:59:31Z","abstract_excerpt":"As the prevalence of wearable devices, learning egocentric motions becomes essential to develop contextual AI. In this work, we present EgoLM, a versatile framework that tracks and understands egocentric motions from multi-modal inputs, e.g., egocentric videos and motion sensors. EgoLM exploits rich contexts for the disambiguation of egomotion tracking and understanding, which are ill-posed under single modality conditions. To facilitate the versatile and multi-modal framework, our key insight is to model the joint distribution of egocentric motions and natural languages using large language m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18127","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/2409.18127/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":"2409.18127","created_at":"2026-07-05T09:12:21.056134+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18127v1","created_at":"2026-07-05T09:12:21.056134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18127","created_at":"2026-07-05T09:12:21.056134+00:00"},{"alias_kind":"pith_short_12","alias_value":"UK3SECORUZB7","created_at":"2026-07-05T09:12:21.056134+00:00"},{"alias_kind":"pith_short_16","alias_value":"UK3SECORUZB77OM2","created_at":"2026-07-05T09:12:21.056134+00:00"},{"alias_kind":"pith_short_8","alias_value":"UK3SECOR","created_at":"2026-07-05T09:12:21.056134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13041","citing_title":"EgoForce: Robust Online Egocentric Motion Reconstruction via Diffusion Forcing","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UK3SECORUZB77OM27PNTX55H77","json":"https://pith.science/pith/UK3SECORUZB77OM27PNTX55H77.json","graph_json":"https://pith.science/api/pith-number/UK3SECORUZB77OM27PNTX55H77/graph.json","events_json":"https://pith.science/api/pith-number/UK3SECORUZB77OM27PNTX55H77/events.json","paper":"https://pith.science/paper/UK3SECOR"},"agent_actions":{"view_html":"https://pith.science/pith/UK3SECORUZB77OM27PNTX55H77","download_json":"https://pith.science/pith/UK3SECORUZB77OM27PNTX55H77.json","view_paper":"https://pith.science/paper/UK3SECOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18127&json=true","fetch_graph":"https://pith.science/api/pith-number/UK3SECORUZB77OM27PNTX55H77/graph.json","fetch_events":"https://pith.science/api/pith-number/UK3SECORUZB77OM27PNTX55H77/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UK3SECORUZB77OM27PNTX55H77/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UK3SECORUZB77OM27PNTX55H77/action/storage_attestation","attest_author":"https://pith.science/pith/UK3SECORUZB77OM27PNTX55H77/action/author_attestation","sign_citation":"https://pith.science/pith/UK3SECORUZB77OM27PNTX55H77/action/citation_signature","submit_replication":"https://pith.science/pith/UK3SECORUZB77OM27PNTX55H77/action/replication_record"}},"created_at":"2026-07-05T09:12:21.056134+00:00","updated_at":"2026-07-05T09:12:21.056134+00:00"}