{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:D4QI374DUFO26PYBKTREPBWM3I","short_pith_number":"pith:D4QI374D","schema_version":"1.0","canonical_sha256":"1f208dff83a15daf3f0154e24786ccda20f5af5708d9ffba93fac641dc65079f","source":{"kind":"arxiv","id":"2210.14395","version":1},"attestation_state":"computed","paper":{"title":"IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and Text","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alireza Dirafzoon, Amy Bearman, Andrea Madotto, Aparajita Saraf, Babak Damavandi, Seungwhan Moon, Zhaojiang Lin","submitted_at":"2022-10-26T00:22:41Z","abstract_excerpt":"We present IMU2CLIP, a novel pre-training approach to align Inertial Measurement Unit (IMU) motion sensor recordings with video and text, by projecting them into the joint representation space of Contrastive Language-Image Pre-training (CLIP). The proposed approach allows IMU2CLIP to translate human motions (as measured by IMU sensors) into their corresponding textual descriptions and videos -- while preserving the transitivity across these modalities.\n  We explore several new IMU-based applications that IMU2CLIP enables, such as motion-based media retrieval and natural language reasoning task"},"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":"2210.14395","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-26T00:22:41Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"3d28ea7aba2626af45dc09dc18881252adc18935bce9daaa5a05ad3324f174d7","abstract_canon_sha256":"dafaa08f77e79a304d495c919625ab8a8a9d2386e8626baa1a3360d091955180"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:44.500283Z","signature_b64":"D36sSxlHZ4H384tgSvn8zS5VL9mTbLitUQRZzjCWqQ7aYyuJ7f/Bmmy7wm263QMtfD/vuZI2gHoYkGTYTxk8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f208dff83a15daf3f0154e24786ccda20f5af5708d9ffba93fac641dc65079f","last_reissued_at":"2026-07-05T05:10:44.499864Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:44.499864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and Text","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alireza Dirafzoon, Amy Bearman, Andrea Madotto, Aparajita Saraf, Babak Damavandi, Seungwhan Moon, Zhaojiang Lin","submitted_at":"2022-10-26T00:22:41Z","abstract_excerpt":"We present IMU2CLIP, a novel pre-training approach to align Inertial Measurement Unit (IMU) motion sensor recordings with video and text, by projecting them into the joint representation space of Contrastive Language-Image Pre-training (CLIP). The proposed approach allows IMU2CLIP to translate human motions (as measured by IMU sensors) into their corresponding textual descriptions and videos -- while preserving the transitivity across these modalities.\n  We explore several new IMU-based applications that IMU2CLIP enables, such as motion-based media retrieval and natural language reasoning task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14395","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/2210.14395/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":"2210.14395","created_at":"2026-07-05T05:10:44.499920+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.14395v1","created_at":"2026-07-05T05:10:44.499920+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14395","created_at":"2026-07-05T05:10:44.499920+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4QI374DUFO2","created_at":"2026-07-05T05:10:44.499920+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4QI374DUFO26PYB","created_at":"2026-07-05T05:10:44.499920+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4QI374D","created_at":"2026-07-05T05:10:44.499920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08117","citing_title":"Modular Retrieval-Augmented Generalization for Human Action Recognition","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19564","citing_title":"EgoSelf: From Memory to Personalized Egocentric Assistant","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17065","citing_title":"BasketHAR: A Multimodal Dataset for Human Activity Recognition and Sport Analysis in Basketball Training Scenarios","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D4QI374DUFO26PYBKTREPBWM3I","json":"https://pith.science/pith/D4QI374DUFO26PYBKTREPBWM3I.json","graph_json":"https://pith.science/api/pith-number/D4QI374DUFO26PYBKTREPBWM3I/graph.json","events_json":"https://pith.science/api/pith-number/D4QI374DUFO26PYBKTREPBWM3I/events.json","paper":"https://pith.science/paper/D4QI374D"},"agent_actions":{"view_html":"https://pith.science/pith/D4QI374DUFO26PYBKTREPBWM3I","download_json":"https://pith.science/pith/D4QI374DUFO26PYBKTREPBWM3I.json","view_paper":"https://pith.science/paper/D4QI374D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.14395&json=true","fetch_graph":"https://pith.science/api/pith-number/D4QI374DUFO26PYBKTREPBWM3I/graph.json","fetch_events":"https://pith.science/api/pith-number/D4QI374DUFO26PYBKTREPBWM3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4QI374DUFO26PYBKTREPBWM3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4QI374DUFO26PYBKTREPBWM3I/action/storage_attestation","attest_author":"https://pith.science/pith/D4QI374DUFO26PYBKTREPBWM3I/action/author_attestation","sign_citation":"https://pith.science/pith/D4QI374DUFO26PYBKTREPBWM3I/action/citation_signature","submit_replication":"https://pith.science/pith/D4QI374DUFO26PYBKTREPBWM3I/action/replication_record"}},"created_at":"2026-07-05T05:10:44.499920+00:00","updated_at":"2026-07-05T05:10:44.499920+00:00"}