{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:244DPRNZKFP66PSCEFY4IJ5FKI","short_pith_number":"pith:244DPRNZ","schema_version":"1.0","canonical_sha256":"d73837c5b9515fef3e422171c427a55217b80a0b5441a0c9fbf11555b193db4c","source":{"kind":"arxiv","id":"2606.30598","version":1},"attestation_state":"computed","paper":{"title":"Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dima Damen, Jiahe Zhao, Michael J. Black, Shashank Tripathi, Siddhant Bansal, Zhifan Zhu","submitted_at":"2026-06-29T17:38:12Z","abstract_excerpt":"Estimating accurate 3D hand-object pose from in-the-wild egocentric RGB remains challenging due to severe occlusions and ambiguous contact. Existing learning-based methods often struggle to generalise to in-the-wild scenes and are limited by the scarcity of supervision. We address these issues with two contributions. First, we introduce EPIC-Contact, an in-the-wild egocentric dataset of 2.3K clips (62.3K frames) with dense, bijective 3D hand-object contact correspondences and posed meshes. Second, we propose HOPformer, an end-to-end transformer that jointly predicts bi-manual hand and object p"},"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":"2606.30598","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T17:38:12Z","cross_cats_sorted":[],"title_canon_sha256":"0c9a40f587a2b911c2ca9f96f5cf4148f315acce566a323124d4bfaf1e5df6f6","abstract_canon_sha256":"a963406e71b7fce21e23e741e84a12da89e82a2a9ffcdd10896437894fd92ff2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:18:22.141665Z","signature_b64":"B16Knu8t4N3YTCgMPPraW3lZ5Pw0yHlyEEdWH7cE9eR+aMM7cIspV7C3JzBPTFR6kvqphPsw2RILHX1aNxlBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d73837c5b9515fef3e422171c427a55217b80a0b5441a0c9fbf11555b193db4c","last_reissued_at":"2026-06-30T02:18:22.140847Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:18:22.140847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dima Damen, Jiahe Zhao, Michael J. Black, Shashank Tripathi, Siddhant Bansal, Zhifan Zhu","submitted_at":"2026-06-29T17:38:12Z","abstract_excerpt":"Estimating accurate 3D hand-object pose from in-the-wild egocentric RGB remains challenging due to severe occlusions and ambiguous contact. Existing learning-based methods often struggle to generalise to in-the-wild scenes and are limited by the scarcity of supervision. We address these issues with two contributions. First, we introduce EPIC-Contact, an in-the-wild egocentric dataset of 2.3K clips (62.3K frames) with dense, bijective 3D hand-object contact correspondences and posed meshes. Second, we propose HOPformer, an end-to-end transformer that jointly predicts bi-manual hand and object p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30598","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/2606.30598/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":"2606.30598","created_at":"2026-06-30T02:18:22.140983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30598v1","created_at":"2026-06-30T02:18:22.140983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30598","created_at":"2026-06-30T02:18:22.140983+00:00"},{"alias_kind":"pith_short_12","alias_value":"244DPRNZKFP6","created_at":"2026-06-30T02:18:22.140983+00:00"},{"alias_kind":"pith_short_16","alias_value":"244DPRNZKFP66PSC","created_at":"2026-06-30T02:18:22.140983+00:00"},{"alias_kind":"pith_short_8","alias_value":"244DPRNZ","created_at":"2026-06-30T02:18:22.140983+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/244DPRNZKFP66PSCEFY4IJ5FKI","json":"https://pith.science/pith/244DPRNZKFP66PSCEFY4IJ5FKI.json","graph_json":"https://pith.science/api/pith-number/244DPRNZKFP66PSCEFY4IJ5FKI/graph.json","events_json":"https://pith.science/api/pith-number/244DPRNZKFP66PSCEFY4IJ5FKI/events.json","paper":"https://pith.science/paper/244DPRNZ"},"agent_actions":{"view_html":"https://pith.science/pith/244DPRNZKFP66PSCEFY4IJ5FKI","download_json":"https://pith.science/pith/244DPRNZKFP66PSCEFY4IJ5FKI.json","view_paper":"https://pith.science/paper/244DPRNZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30598&json=true","fetch_graph":"https://pith.science/api/pith-number/244DPRNZKFP66PSCEFY4IJ5FKI/graph.json","fetch_events":"https://pith.science/api/pith-number/244DPRNZKFP66PSCEFY4IJ5FKI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/244DPRNZKFP66PSCEFY4IJ5FKI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/244DPRNZKFP66PSCEFY4IJ5FKI/action/storage_attestation","attest_author":"https://pith.science/pith/244DPRNZKFP66PSCEFY4IJ5FKI/action/author_attestation","sign_citation":"https://pith.science/pith/244DPRNZKFP66PSCEFY4IJ5FKI/action/citation_signature","submit_replication":"https://pith.science/pith/244DPRNZKFP66PSCEFY4IJ5FKI/action/replication_record"}},"created_at":"2026-06-30T02:18:22.140983+00:00","updated_at":"2026-06-30T02:18:22.140983+00:00"}