{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7RPYIVSAJR5BQZD27Z7KM4ULIF","short_pith_number":"pith:7RPYIVSA","schema_version":"1.0","canonical_sha256":"fc5f8456404c7a18647afe7ea6728b414aadf31fac988bc7f54bd017284d043e","source":{"kind":"arxiv","id":"2303.09534","version":1},"attestation_state":"computed","paper":{"title":"InCrowdFormer: On-Ground Pedestrian World Model From Egocentric Views","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ko Nishino, Mai Nishimura, Shohei Nobuhara","submitted_at":"2023-03-16T17:51:02Z","abstract_excerpt":"We introduce an on-ground Pedestrian World Model, a computational model that can predict how pedestrians move around an observer in the crowd on the ground plane, but from just the egocentric-views of the observer. Our model, InCrowdFormer, fully leverages the Transformer architecture by modeling pedestrian interaction and egocentric to top-down view transformation with attention, and autoregressively predicts on-ground positions of a variable number of people with an encoder-decoder architecture. We encode the uncertainties arising from unknown pedestrian heights with latent codes to predict "},"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":"2303.09534","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T17:51:02Z","cross_cats_sorted":[],"title_canon_sha256":"a1f2468651c3e9a0652d2a6891a436791efe9d7afcbc7b600a27c8c0dc931db3","abstract_canon_sha256":"a76fd0a16a04cf85a1d18d49341a3133bb0a762d1f7de8b1ff73e736c188f248"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:54.624266Z","signature_b64":"/6xXxCUMrsK06AamTZkOQw/Wxc5ssltLUhIGLFxlsBA1UfoKE50mHY+FY8Q4eMAWnlG9iQpxu1zqmR7vAfQlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc5f8456404c7a18647afe7ea6728b414aadf31fac988bc7f54bd017284d043e","last_reissued_at":"2026-07-05T05:51:54.623785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:54.623785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InCrowdFormer: On-Ground Pedestrian World Model From Egocentric Views","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ko Nishino, Mai Nishimura, Shohei Nobuhara","submitted_at":"2023-03-16T17:51:02Z","abstract_excerpt":"We introduce an on-ground Pedestrian World Model, a computational model that can predict how pedestrians move around an observer in the crowd on the ground plane, but from just the egocentric-views of the observer. Our model, InCrowdFormer, fully leverages the Transformer architecture by modeling pedestrian interaction and egocentric to top-down view transformation with attention, and autoregressively predicts on-ground positions of a variable number of people with an encoder-decoder architecture. We encode the uncertainties arising from unknown pedestrian heights with latent codes to predict "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09534","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.09534/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":"2303.09534","created_at":"2026-07-05T05:51:54.623841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.09534v1","created_at":"2026-07-05T05:51:54.623841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09534","created_at":"2026-07-05T05:51:54.623841+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RPYIVSAJR5B","created_at":"2026-07-05T05:51:54.623841+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RPYIVSAJR5BQZD2","created_at":"2026-07-05T05:51:54.623841+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RPYIVSA","created_at":"2026-07-05T05:51:54.623841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06253","citing_title":"Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision","ref_index":95,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7RPYIVSAJR5BQZD27Z7KM4ULIF","json":"https://pith.science/pith/7RPYIVSAJR5BQZD27Z7KM4ULIF.json","graph_json":"https://pith.science/api/pith-number/7RPYIVSAJR5BQZD27Z7KM4ULIF/graph.json","events_json":"https://pith.science/api/pith-number/7RPYIVSAJR5BQZD27Z7KM4ULIF/events.json","paper":"https://pith.science/paper/7RPYIVSA"},"agent_actions":{"view_html":"https://pith.science/pith/7RPYIVSAJR5BQZD27Z7KM4ULIF","download_json":"https://pith.science/pith/7RPYIVSAJR5BQZD27Z7KM4ULIF.json","view_paper":"https://pith.science/paper/7RPYIVSA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.09534&json=true","fetch_graph":"https://pith.science/api/pith-number/7RPYIVSAJR5BQZD27Z7KM4ULIF/graph.json","fetch_events":"https://pith.science/api/pith-number/7RPYIVSAJR5BQZD27Z7KM4ULIF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RPYIVSAJR5BQZD27Z7KM4ULIF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RPYIVSAJR5BQZD27Z7KM4ULIF/action/storage_attestation","attest_author":"https://pith.science/pith/7RPYIVSAJR5BQZD27Z7KM4ULIF/action/author_attestation","sign_citation":"https://pith.science/pith/7RPYIVSAJR5BQZD27Z7KM4ULIF/action/citation_signature","submit_replication":"https://pith.science/pith/7RPYIVSAJR5BQZD27Z7KM4ULIF/action/replication_record"}},"created_at":"2026-07-05T05:51:54.623841+00:00","updated_at":"2026-07-05T05:51:54.623841+00:00"}