{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MTGXZVM3H6Y6AA4DEHO3VRINO2","short_pith_number":"pith:MTGXZVM3","schema_version":"1.0","canonical_sha256":"64cd7cd59b3fb1e0038321ddbac50d76a893f36c59abcc587dccead9f7e032d0","source":{"kind":"arxiv","id":"2209.13508","version":2},"attestation_state":"computed","paper":{"title":"Motion Transformer with Global Intention Localization and Local Movement Refinement","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernt Schiele, Dengxin Dai, Li Jiang, Shaoshuai Shi","submitted_at":"2022-09-27T16:23:14Z","abstract_excerpt":"Predicting multimodal future behavior of traffic participants is essential for robotic vehicles to make safe decisions. Existing works explore to directly predict future trajectories based on latent features or utilize dense goal candidates to identify agent's destinations, where the former strategy converges slowly since all motion modes are derived from the same feature while the latter strategy has efficiency issue since its performance highly relies on the density of goal candidates. In this paper, we propose Motion TRansformer (MTR) framework that models motion prediction as the joint opt"},"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":"2209.13508","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-27T16:23:14Z","cross_cats_sorted":[],"title_canon_sha256":"f6bf2d9f6fb7fd0b2f6448619af397b922a79dfc829fe3fbbc659c14111bec99","abstract_canon_sha256":"5ff89e0b520d5b07d078e6f5bde5785e869fa9c1e131c45c47fbb9270ac467fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:22.540893Z","signature_b64":"OFwzgudlt0l8oJSjo/YV0RKnrKOXPzg349NCpayvhBkepWrssMthKx0tQRpExVD7Hy6flk8r6Mexfy0o3bafBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64cd7cd59b3fb1e0038321ddbac50d76a893f36c59abcc587dccead9f7e032d0","last_reissued_at":"2026-07-05T05:52:22.540501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:22.540501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Motion Transformer with Global Intention Localization and Local Movement Refinement","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernt Schiele, Dengxin Dai, Li Jiang, Shaoshuai Shi","submitted_at":"2022-09-27T16:23:14Z","abstract_excerpt":"Predicting multimodal future behavior of traffic participants is essential for robotic vehicles to make safe decisions. Existing works explore to directly predict future trajectories based on latent features or utilize dense goal candidates to identify agent's destinations, where the former strategy converges slowly since all motion modes are derived from the same feature while the latter strategy has efficiency issue since its performance highly relies on the density of goal candidates. In this paper, we propose Motion TRansformer (MTR) framework that models motion prediction as the joint opt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.13508","kind":"arxiv","version":2},"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/2209.13508/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":"2209.13508","created_at":"2026-07-05T05:52:22.540558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.13508v2","created_at":"2026-07-05T05:52:22.540558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.13508","created_at":"2026-07-05T05:52:22.540558+00:00"},{"alias_kind":"pith_short_12","alias_value":"MTGXZVM3H6Y6","created_at":"2026-07-05T05:52:22.540558+00:00"},{"alias_kind":"pith_short_16","alias_value":"MTGXZVM3H6Y6AA4D","created_at":"2026-07-05T05:52:22.540558+00:00"},{"alias_kind":"pith_short_8","alias_value":"MTGXZVM3","created_at":"2026-07-05T05:52:22.540558+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23588","citing_title":"A Generative Model for Closed-Loop Microsimulation of Signalized Intersections","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14201","citing_title":"MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14201","citing_title":"MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01393","citing_title":"Recall to Predict: Grounding Motion Forecasting in Interpretable Motion Bank","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16783","citing_title":"EdgeVTP: Exploration of Latency-efficient Trajectory Prediction for Edge-based Embedded Vision Applications","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MTGXZVM3H6Y6AA4DEHO3VRINO2","json":"https://pith.science/pith/MTGXZVM3H6Y6AA4DEHO3VRINO2.json","graph_json":"https://pith.science/api/pith-number/MTGXZVM3H6Y6AA4DEHO3VRINO2/graph.json","events_json":"https://pith.science/api/pith-number/MTGXZVM3H6Y6AA4DEHO3VRINO2/events.json","paper":"https://pith.science/paper/MTGXZVM3"},"agent_actions":{"view_html":"https://pith.science/pith/MTGXZVM3H6Y6AA4DEHO3VRINO2","download_json":"https://pith.science/pith/MTGXZVM3H6Y6AA4DEHO3VRINO2.json","view_paper":"https://pith.science/paper/MTGXZVM3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.13508&json=true","fetch_graph":"https://pith.science/api/pith-number/MTGXZVM3H6Y6AA4DEHO3VRINO2/graph.json","fetch_events":"https://pith.science/api/pith-number/MTGXZVM3H6Y6AA4DEHO3VRINO2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MTGXZVM3H6Y6AA4DEHO3VRINO2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MTGXZVM3H6Y6AA4DEHO3VRINO2/action/storage_attestation","attest_author":"https://pith.science/pith/MTGXZVM3H6Y6AA4DEHO3VRINO2/action/author_attestation","sign_citation":"https://pith.science/pith/MTGXZVM3H6Y6AA4DEHO3VRINO2/action/citation_signature","submit_replication":"https://pith.science/pith/MTGXZVM3H6Y6AA4DEHO3VRINO2/action/replication_record"}},"created_at":"2026-07-05T05:52:22.540558+00:00","updated_at":"2026-07-05T05:52:22.540558+00:00"}