{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:M3XG4H2ZNK7IBG6JVR37SI3EHB","short_pith_number":"pith:M3XG4H2Z","schema_version":"1.0","canonical_sha256":"66ee6e1f596abe809bc9ac77f92364387939724fc6c4e11310dad9e01a38ce37","source":{"kind":"arxiv","id":"2103.15320","version":1},"attestation_state":"computed","paper":{"title":"TFPose: Direct Human Pose Estimation with Transformers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Weian Mao, Xinlong Wang, Yongtao Ge, Zhibin Wang, Zhi Tian","submitted_at":"2021-03-29T04:18:54Z","abstract_excerpt":"We propose a human pose estimation framework that solves the task in the regression-based fashion. Unlike previous regression-based methods, which often fall behind those state-of-the-art methods, we formulate the pose estimation task into a sequence prediction problem that can effectively be solved by transformers. Our framework is simple and direct, bypassing the drawbacks of the heatmap-based pose estimation. Moreover, with the attention mechanism in transformers, our proposed framework is able to adaptively attend to the features most relevant to the target keypoints, which largely overcom"},"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":"2103.15320","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-29T04:18:54Z","cross_cats_sorted":[],"title_canon_sha256":"20b807877a9982665520b0ba705359244ee5d712da39b370beb366bdc208c575","abstract_canon_sha256":"43a9882e6ce895e56533a2c25ced6fe8c6bd6311474eeac4fdd9d10011462d44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:27:04.802804Z","signature_b64":"dXNAS8LXrkkfYARexDaSPTKjcKNTo83ZkZO1VA7IWg+Aumey1b1jxXqerbkxrSBu5AcvqcwTX05b8dm3smVgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66ee6e1f596abe809bc9ac77f92364387939724fc6c4e11310dad9e01a38ce37","last_reissued_at":"2026-07-05T02:27:04.802364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:27:04.802364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TFPose: Direct Human Pose Estimation with Transformers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Weian Mao, Xinlong Wang, Yongtao Ge, Zhibin Wang, Zhi Tian","submitted_at":"2021-03-29T04:18:54Z","abstract_excerpt":"We propose a human pose estimation framework that solves the task in the regression-based fashion. Unlike previous regression-based methods, which often fall behind those state-of-the-art methods, we formulate the pose estimation task into a sequence prediction problem that can effectively be solved by transformers. Our framework is simple and direct, bypassing the drawbacks of the heatmap-based pose estimation. Moreover, with the attention mechanism in transformers, our proposed framework is able to adaptively attend to the features most relevant to the target keypoints, which largely overcom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.15320","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/2103.15320/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":"2103.15320","created_at":"2026-07-05T02:27:04.802433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.15320v1","created_at":"2026-07-05T02:27:04.802433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.15320","created_at":"2026-07-05T02:27:04.802433+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3XG4H2ZNK7I","created_at":"2026-07-05T02:27:04.802433+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3XG4H2ZNK7IBG6J","created_at":"2026-07-05T02:27:04.802433+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3XG4H2Z","created_at":"2026-07-05T02:27:04.802433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01873","citing_title":"Doctoral Thesis: Geometric Deep Learning For Camera Pose Prediction, Registration, Depth Estimation, and 3D Reconstruction","ref_index":156,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M3XG4H2ZNK7IBG6JVR37SI3EHB","json":"https://pith.science/pith/M3XG4H2ZNK7IBG6JVR37SI3EHB.json","graph_json":"https://pith.science/api/pith-number/M3XG4H2ZNK7IBG6JVR37SI3EHB/graph.json","events_json":"https://pith.science/api/pith-number/M3XG4H2ZNK7IBG6JVR37SI3EHB/events.json","paper":"https://pith.science/paper/M3XG4H2Z"},"agent_actions":{"view_html":"https://pith.science/pith/M3XG4H2ZNK7IBG6JVR37SI3EHB","download_json":"https://pith.science/pith/M3XG4H2ZNK7IBG6JVR37SI3EHB.json","view_paper":"https://pith.science/paper/M3XG4H2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.15320&json=true","fetch_graph":"https://pith.science/api/pith-number/M3XG4H2ZNK7IBG6JVR37SI3EHB/graph.json","fetch_events":"https://pith.science/api/pith-number/M3XG4H2ZNK7IBG6JVR37SI3EHB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3XG4H2ZNK7IBG6JVR37SI3EHB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3XG4H2ZNK7IBG6JVR37SI3EHB/action/storage_attestation","attest_author":"https://pith.science/pith/M3XG4H2ZNK7IBG6JVR37SI3EHB/action/author_attestation","sign_citation":"https://pith.science/pith/M3XG4H2ZNK7IBG6JVR37SI3EHB/action/citation_signature","submit_replication":"https://pith.science/pith/M3XG4H2ZNK7IBG6JVR37SI3EHB/action/replication_record"}},"created_at":"2026-07-05T02:27:04.802433+00:00","updated_at":"2026-07-05T02:27:04.802433+00:00"}