{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CV4QEXQAFGUQDHG7MFJH2ZKBPX","short_pith_number":"pith:CV4QEXQA","schema_version":"1.0","canonical_sha256":"1579025e0029a9019cdf61527d65417df16dd39ca78b6aab80ec0d462436d0b8","source":{"kind":"arxiv","id":"2605.21714","version":1},"attestation_state":"computed","paper":{"title":"AVI-HT: Adaptive Vision-IMU Fusion for 3D Hand Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Ankit Kumar, Ergys Ristani, Li Guan, Mia Huang, Taylor Niehues, Vatsal Mehta, Ziyi Kou","submitted_at":"2026-05-20T20:19:24Z","abstract_excerpt":"We present AVI-HT, an adaptive visual-IMU fusion approach for tracking 3D hand poses by jointly modeling the egocentric image with on-glove 6-DoF IMU signals. AVI-HT achieves significantly improved accuracy and availability, particularly in hand-object interaction (HOI) scenarios involving heavy visual occlusion. Two complementary ingredients underpin its success: (1) synchronized multi-modal training data pairing on-body vision-IMU sensor streams with ground-truth 3D hand poses from a motion-capture system, and (2) a cross-sensor deep attention mechanism that adaptively modulates the trust as"},"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":"2605.21714","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T20:19:24Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"96810ad00a030b6c759d7513cc641c39e561b364da5d2cfddf5c59d4db8b796f","abstract_canon_sha256":"59465fcd537f42105e4b5245fce480eeca19a9ce376c6576be94363ce8a46dbe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:29.068299Z","signature_b64":"gUREYH5LG8cGKQNql6BgwXlghyr7PTKsRYbzEmOYeh55pNyElh1Z09w0rCTJP4ag91e7EbnnXpHWpRritTWOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1579025e0029a9019cdf61527d65417df16dd39ca78b6aab80ec0d462436d0b8","last_reissued_at":"2026-05-22T01:03:29.067864Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:29.067864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AVI-HT: Adaptive Vision-IMU Fusion for 3D Hand Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Ankit Kumar, Ergys Ristani, Li Guan, Mia Huang, Taylor Niehues, Vatsal Mehta, Ziyi Kou","submitted_at":"2026-05-20T20:19:24Z","abstract_excerpt":"We present AVI-HT, an adaptive visual-IMU fusion approach for tracking 3D hand poses by jointly modeling the egocentric image with on-glove 6-DoF IMU signals. AVI-HT achieves significantly improved accuracy and availability, particularly in hand-object interaction (HOI) scenarios involving heavy visual occlusion. Two complementary ingredients underpin its success: (1) synchronized multi-modal training data pairing on-body vision-IMU sensor streams with ground-truth 3D hand poses from a motion-capture system, and (2) a cross-sensor deep attention mechanism that adaptively modulates the trust as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21714","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/2605.21714/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":"2605.21714","created_at":"2026-05-22T01:03:29.067925+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21714v1","created_at":"2026-05-22T01:03:29.067925+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21714","created_at":"2026-05-22T01:03:29.067925+00:00"},{"alias_kind":"pith_short_12","alias_value":"CV4QEXQAFGUQ","created_at":"2026-05-22T01:03:29.067925+00:00"},{"alias_kind":"pith_short_16","alias_value":"CV4QEXQAFGUQDHG7","created_at":"2026-05-22T01:03:29.067925+00:00"},{"alias_kind":"pith_short_8","alias_value":"CV4QEXQA","created_at":"2026-05-22T01:03:29.067925+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CV4QEXQAFGUQDHG7MFJH2ZKBPX","json":"https://pith.science/pith/CV4QEXQAFGUQDHG7MFJH2ZKBPX.json","graph_json":"https://pith.science/api/pith-number/CV4QEXQAFGUQDHG7MFJH2ZKBPX/graph.json","events_json":"https://pith.science/api/pith-number/CV4QEXQAFGUQDHG7MFJH2ZKBPX/events.json","paper":"https://pith.science/paper/CV4QEXQA"},"agent_actions":{"view_html":"https://pith.science/pith/CV4QEXQAFGUQDHG7MFJH2ZKBPX","download_json":"https://pith.science/pith/CV4QEXQAFGUQDHG7MFJH2ZKBPX.json","view_paper":"https://pith.science/paper/CV4QEXQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21714&json=true","fetch_graph":"https://pith.science/api/pith-number/CV4QEXQAFGUQDHG7MFJH2ZKBPX/graph.json","fetch_events":"https://pith.science/api/pith-number/CV4QEXQAFGUQDHG7MFJH2ZKBPX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CV4QEXQAFGUQDHG7MFJH2ZKBPX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CV4QEXQAFGUQDHG7MFJH2ZKBPX/action/storage_attestation","attest_author":"https://pith.science/pith/CV4QEXQAFGUQDHG7MFJH2ZKBPX/action/author_attestation","sign_citation":"https://pith.science/pith/CV4QEXQAFGUQDHG7MFJH2ZKBPX/action/citation_signature","submit_replication":"https://pith.science/pith/CV4QEXQAFGUQDHG7MFJH2ZKBPX/action/replication_record"}},"created_at":"2026-05-22T01:03:29.067925+00:00","updated_at":"2026-05-22T01:03:29.067925+00:00"}