{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VM24PSFCSBSKS2DPXVGOJNFL6J","short_pith_number":"pith:VM24PSFC","schema_version":"1.0","canonical_sha256":"ab35c7c8a29064a9686fbd4ce4b4abf25a6704916a0596c040255a8c39547f91","source":{"kind":"arxiv","id":"2110.09783","version":1},"attestation_state":"computed","paper":{"title":"Spatial-Temporal Transformer for 3D Point Cloud Sequences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Liu, Qiuhong Ke, Tingting Xie, Yimin Wei, Yulan Guo","submitted_at":"2021-10-19T07:55:47Z","abstract_excerpt":"Effective learning of spatial-temporal information within a point cloud sequence is highly important for many down-stream tasks such as 4D semantic segmentation and 3D action recognition. In this paper, we propose a novel framework named Point Spatial-Temporal Transformer (PST2) to learn spatial-temporal representations from dynamic 3D point cloud sequences. Our PST2 consists of two major modules: a Spatio-Temporal Self-Attention (STSA) module and a Resolution Embedding (RE) module. Our STSA module is introduced to capture the spatial-temporal context information across adjacent frames, while "},"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":"2110.09783","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-19T07:55:47Z","cross_cats_sorted":[],"title_canon_sha256":"7ebb172d62cfeedbd40e8a22a1da8b28e9c0368ba16ec75a57ea0e20311cf120","abstract_canon_sha256":"5e21d80436976d192c8e9a2193a8ad0616d531b1614b5865c296c53abbebfc7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:58.987233Z","signature_b64":"/eMmr+IH0+5PzGtgis44LjkiGRFbG3/bgIiGoBEfx5EC2LGHHlaCV2ELyWltWqSOxh0UydhpF/250OMaJJA/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab35c7c8a29064a9686fbd4ce4b4abf25a6704916a0596c040255a8c39547f91","last_reissued_at":"2026-07-05T03:23:58.986776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:58.986776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatial-Temporal Transformer for 3D Point Cloud Sequences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Liu, Qiuhong Ke, Tingting Xie, Yimin Wei, Yulan Guo","submitted_at":"2021-10-19T07:55:47Z","abstract_excerpt":"Effective learning of spatial-temporal information within a point cloud sequence is highly important for many down-stream tasks such as 4D semantic segmentation and 3D action recognition. In this paper, we propose a novel framework named Point Spatial-Temporal Transformer (PST2) to learn spatial-temporal representations from dynamic 3D point cloud sequences. Our PST2 consists of two major modules: a Spatio-Temporal Self-Attention (STSA) module and a Resolution Embedding (RE) module. Our STSA module is introduced to capture the spatial-temporal context information across adjacent frames, while "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09783","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/2110.09783/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":"2110.09783","created_at":"2026-07-05T03:23:58.986835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.09783v1","created_at":"2026-07-05T03:23:58.986835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09783","created_at":"2026-07-05T03:23:58.986835+00:00"},{"alias_kind":"pith_short_12","alias_value":"VM24PSFCSBSK","created_at":"2026-07-05T03:23:58.986835+00:00"},{"alias_kind":"pith_short_16","alias_value":"VM24PSFCSBSKS2DP","created_at":"2026-07-05T03:23:58.986835+00:00"},{"alias_kind":"pith_short_8","alias_value":"VM24PSFC","created_at":"2026-07-05T03:23:58.986835+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/VM24PSFCSBSKS2DPXVGOJNFL6J","json":"https://pith.science/pith/VM24PSFCSBSKS2DPXVGOJNFL6J.json","graph_json":"https://pith.science/api/pith-number/VM24PSFCSBSKS2DPXVGOJNFL6J/graph.json","events_json":"https://pith.science/api/pith-number/VM24PSFCSBSKS2DPXVGOJNFL6J/events.json","paper":"https://pith.science/paper/VM24PSFC"},"agent_actions":{"view_html":"https://pith.science/pith/VM24PSFCSBSKS2DPXVGOJNFL6J","download_json":"https://pith.science/pith/VM24PSFCSBSKS2DPXVGOJNFL6J.json","view_paper":"https://pith.science/paper/VM24PSFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.09783&json=true","fetch_graph":"https://pith.science/api/pith-number/VM24PSFCSBSKS2DPXVGOJNFL6J/graph.json","fetch_events":"https://pith.science/api/pith-number/VM24PSFCSBSKS2DPXVGOJNFL6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VM24PSFCSBSKS2DPXVGOJNFL6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VM24PSFCSBSKS2DPXVGOJNFL6J/action/storage_attestation","attest_author":"https://pith.science/pith/VM24PSFCSBSKS2DPXVGOJNFL6J/action/author_attestation","sign_citation":"https://pith.science/pith/VM24PSFCSBSKS2DPXVGOJNFL6J/action/citation_signature","submit_replication":"https://pith.science/pith/VM24PSFCSBSKS2DPXVGOJNFL6J/action/replication_record"}},"created_at":"2026-07-05T03:23:58.986835+00:00","updated_at":"2026-07-05T03:23:58.986835+00:00"}