{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6OIQZ4RXPWXY343IFOBJAF7R6K","short_pith_number":"pith:6OIQZ4RX","schema_version":"1.0","canonical_sha256":"f3910cf2377daf8df3682b829017f1f2a1a740da790ecf53e8debfc568c75733","source":{"kind":"arxiv","id":"1804.09534","version":1},"attestation_state":"computed","paper":{"title":"Hand Pose Estimation via Latent 2.5D Heatmap Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jan Kautz, Juergen Gall, Pavlo Molchanov, Thomas Breuel, Umar Iqbal","submitted_at":"2018-04-25T13:16:26Z","abstract_excerpt":"Estimating the 3D pose of a hand is an essential part of human-computer interaction. Estimating 3D pose using depth or multi-view sensors has become easier with recent advances in computer vision, however, regressing pose from a single RGB image is much less straightforward. The main difficulty arises from the fact that 3D pose requires some form of depth estimates, which are ambiguous given only an RGB image. In this paper we propose a new method for 3D hand pose estimation from a monocular image through a novel 2.5D pose representation. Our new representation estimates pose up to a scaling f"},"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":"1804.09534","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-25T13:16:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"968f06baa6ba6264c2e20bd973a7d3386d5aaa1774ca65ba02bb7759694bfcf3","abstract_canon_sha256":"89f5b65e58597eb75d538a06a58695f576a09559e6df8b50bb219f04e7ea8e20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:31.520576Z","signature_b64":"PeGhCbq6mVdfpE5pR7bONIIu7P24FMpLp4t0xKjq/VozlLgux4ED46n+yJ7rAqjQS1Durtj4kCV5qHLw4XpGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3910cf2377daf8df3682b829017f1f2a1a740da790ecf53e8debfc568c75733","last_reissued_at":"2026-05-18T00:17:31.519972Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:31.519972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hand Pose Estimation via Latent 2.5D Heatmap Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jan Kautz, Juergen Gall, Pavlo Molchanov, Thomas Breuel, Umar Iqbal","submitted_at":"2018-04-25T13:16:26Z","abstract_excerpt":"Estimating the 3D pose of a hand is an essential part of human-computer interaction. Estimating 3D pose using depth or multi-view sensors has become easier with recent advances in computer vision, however, regressing pose from a single RGB image is much less straightforward. The main difficulty arises from the fact that 3D pose requires some form of depth estimates, which are ambiguous given only an RGB image. In this paper we propose a new method for 3D hand pose estimation from a monocular image through a novel 2.5D pose representation. Our new representation estimates pose up to a scaling f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.09534","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":""},"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":"1804.09534","created_at":"2026-05-18T00:17:31.520077+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.09534v1","created_at":"2026-05-18T00:17:31.520077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.09534","created_at":"2026-05-18T00:17:31.520077+00:00"},{"alias_kind":"pith_short_12","alias_value":"6OIQZ4RXPWXY","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"6OIQZ4RXPWXY343I","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"6OIQZ4RX","created_at":"2026-05-18T12:32:11.075285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.13083","citing_title":"TouchAnything: A Dataset and Framework for Bimanual Tactile Estimation from Egocentric Video","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6OIQZ4RXPWXY343IFOBJAF7R6K","json":"https://pith.science/pith/6OIQZ4RXPWXY343IFOBJAF7R6K.json","graph_json":"https://pith.science/api/pith-number/6OIQZ4RXPWXY343IFOBJAF7R6K/graph.json","events_json":"https://pith.science/api/pith-number/6OIQZ4RXPWXY343IFOBJAF7R6K/events.json","paper":"https://pith.science/paper/6OIQZ4RX"},"agent_actions":{"view_html":"https://pith.science/pith/6OIQZ4RXPWXY343IFOBJAF7R6K","download_json":"https://pith.science/pith/6OIQZ4RXPWXY343IFOBJAF7R6K.json","view_paper":"https://pith.science/paper/6OIQZ4RX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.09534&json=true","fetch_graph":"https://pith.science/api/pith-number/6OIQZ4RXPWXY343IFOBJAF7R6K/graph.json","fetch_events":"https://pith.science/api/pith-number/6OIQZ4RXPWXY343IFOBJAF7R6K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6OIQZ4RXPWXY343IFOBJAF7R6K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6OIQZ4RXPWXY343IFOBJAF7R6K/action/storage_attestation","attest_author":"https://pith.science/pith/6OIQZ4RXPWXY343IFOBJAF7R6K/action/author_attestation","sign_citation":"https://pith.science/pith/6OIQZ4RXPWXY343IFOBJAF7R6K/action/citation_signature","submit_replication":"https://pith.science/pith/6OIQZ4RXPWXY343IFOBJAF7R6K/action/replication_record"}},"created_at":"2026-05-18T00:17:31.520077+00:00","updated_at":"2026-05-18T00:17:31.520077+00:00"}