{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QRVB75S3FIXRF2DJLXVRPP5WAG","short_pith_number":"pith:QRVB75S3","schema_version":"1.0","canonical_sha256":"846a1ff65b2a2f12e8695deb17bfb6018fa621cfb973ac552c195dfdbed6b5b9","source":{"kind":"arxiv","id":"2509.06956","version":1},"attestation_state":"computed","paper":{"title":"H$_{2}$OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hong Liu, Mengyuan Liu, Nicu Sebe, Pichao Wang, Shijian Lu, Wenhao Li","submitted_at":"2025-09-08T17:59:59Z","abstract_excerpt":"Transformers have been successfully applied in the field of video-based 3D human pose estimation. However, the high computational costs of these video pose transformers (VPTs) make them impractical on resource-constrained devices. In this paper, we present a hierarchical plug-and-play pruning-and-recovering framework, called Hierarchical Hourglass Tokenizer (H$_{2}$OT), for efficient transformer-based 3D human pose estimation from videos. H$_{2}$OT begins with progressively pruning pose tokens of redundant frames and ends with recovering full-length sequences, resulting in a few pose tokens in"},"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":"2509.06956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-08T17:59:59Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"57271ae2c76701c79dbaf2dcadfd25465bd3e58a3a92c163c5f2ca5b73f06a3a","abstract_canon_sha256":"88211c7a64fa95b04f38631e3d4fcc85c3d0924c143e4fc39f267acd6780935c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:56.045515Z","signature_b64":"aIYKyxFq1IY5S/Caq3/pbamsFwMApWKpTGPIr7LS+2ow2fFibjspQe0Pf3MNFVw3ihytdkQkawHu5RabwwRDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"846a1ff65b2a2f12e8695deb17bfb6018fa621cfb973ac552c195dfdbed6b5b9","last_reissued_at":"2026-07-05T12:06:56.045013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:56.045013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"H$_{2}$OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hong Liu, Mengyuan Liu, Nicu Sebe, Pichao Wang, Shijian Lu, Wenhao Li","submitted_at":"2025-09-08T17:59:59Z","abstract_excerpt":"Transformers have been successfully applied in the field of video-based 3D human pose estimation. However, the high computational costs of these video pose transformers (VPTs) make them impractical on resource-constrained devices. In this paper, we present a hierarchical plug-and-play pruning-and-recovering framework, called Hierarchical Hourglass Tokenizer (H$_{2}$OT), for efficient transformer-based 3D human pose estimation from videos. H$_{2}$OT begins with progressively pruning pose tokens of redundant frames and ends with recovering full-length sequences, resulting in a few pose tokens in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06956","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/2509.06956/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":"2509.06956","created_at":"2026-07-05T12:06:56.045070+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06956v1","created_at":"2026-07-05T12:06:56.045070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06956","created_at":"2026-07-05T12:06:56.045070+00:00"},{"alias_kind":"pith_short_12","alias_value":"QRVB75S3FIXR","created_at":"2026-07-05T12:06:56.045070+00:00"},{"alias_kind":"pith_short_16","alias_value":"QRVB75S3FIXRF2DJ","created_at":"2026-07-05T12:06:56.045070+00:00"},{"alias_kind":"pith_short_8","alias_value":"QRVB75S3","created_at":"2026-07-05T12:06:56.045070+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/QRVB75S3FIXRF2DJLXVRPP5WAG","json":"https://pith.science/pith/QRVB75S3FIXRF2DJLXVRPP5WAG.json","graph_json":"https://pith.science/api/pith-number/QRVB75S3FIXRF2DJLXVRPP5WAG/graph.json","events_json":"https://pith.science/api/pith-number/QRVB75S3FIXRF2DJLXVRPP5WAG/events.json","paper":"https://pith.science/paper/QRVB75S3"},"agent_actions":{"view_html":"https://pith.science/pith/QRVB75S3FIXRF2DJLXVRPP5WAG","download_json":"https://pith.science/pith/QRVB75S3FIXRF2DJLXVRPP5WAG.json","view_paper":"https://pith.science/paper/QRVB75S3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06956&json=true","fetch_graph":"https://pith.science/api/pith-number/QRVB75S3FIXRF2DJLXVRPP5WAG/graph.json","fetch_events":"https://pith.science/api/pith-number/QRVB75S3FIXRF2DJLXVRPP5WAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QRVB75S3FIXRF2DJLXVRPP5WAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QRVB75S3FIXRF2DJLXVRPP5WAG/action/storage_attestation","attest_author":"https://pith.science/pith/QRVB75S3FIXRF2DJLXVRPP5WAG/action/author_attestation","sign_citation":"https://pith.science/pith/QRVB75S3FIXRF2DJLXVRPP5WAG/action/citation_signature","submit_replication":"https://pith.science/pith/QRVB75S3FIXRF2DJLXVRPP5WAG/action/replication_record"}},"created_at":"2026-07-05T12:06:56.045070+00:00","updated_at":"2026-07-05T12:06:56.045070+00:00"}