{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PPSZZIYS2FX4EREESFOHDABE2R","short_pith_number":"pith:PPSZZIYS","schema_version":"1.0","canonical_sha256":"7be59ca312d16fc24484915c718024d452483473cf6bd8e6f716c35eced70ae2","source":{"kind":"arxiv","id":"2503.03535","version":1},"attestation_state":"computed","paper":{"title":"Unified Human Localization and Trajectory Prediction with Monocular Vision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Alexandre Alahi, Celine Demonsant, Po-Chien Luan, Yang Gao","submitted_at":"2025-03-05T14:18:39Z","abstract_excerpt":"Conventional human trajectory prediction models rely on clean curated data, requiring specialized equipment or manual labeling, which is often impractical for robotic applications. The existing predictors tend to overfit to clean observation affecting their robustness when used with noisy inputs. In this work, we propose MonoTransmotion (MT), a Transformer-based framework that uses only a monocular camera to jointly solve localization and prediction tasks. Our framework has two main modules: Bird's Eye View (BEV) localization and trajectory prediction. The BEV localization module estimates the"},"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":"2503.03535","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-05T14:18:39Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"2df424a3d4e007a44e0f08abe84a7ec8714f7a9f33dd91e0516cb1b2031b5ef6","abstract_canon_sha256":"2ba93ed097d8eb14a1522a305228a018f9ece02e0b8ee3d579143a8605fbf839"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:47.325524Z","signature_b64":"Epgf/JAa3bDFeDmks8EQgkuf2TbBkWU8XulC2kh2B4pbCNU84CO1mHnyQdICH2s+vE+brPorisrizwirfo0wAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7be59ca312d16fc24484915c718024d452483473cf6bd8e6f716c35eced70ae2","last_reissued_at":"2026-07-05T10:24:47.324732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:47.324732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Human Localization and Trajectory Prediction with Monocular Vision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Alexandre Alahi, Celine Demonsant, Po-Chien Luan, Yang Gao","submitted_at":"2025-03-05T14:18:39Z","abstract_excerpt":"Conventional human trajectory prediction models rely on clean curated data, requiring specialized equipment or manual labeling, which is often impractical for robotic applications. The existing predictors tend to overfit to clean observation affecting their robustness when used with noisy inputs. In this work, we propose MonoTransmotion (MT), a Transformer-based framework that uses only a monocular camera to jointly solve localization and prediction tasks. Our framework has two main modules: Bird's Eye View (BEV) localization and trajectory prediction. The BEV localization module estimates the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03535","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/2503.03535/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":"2503.03535","created_at":"2026-07-05T10:24:47.324852+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.03535v1","created_at":"2026-07-05T10:24:47.324852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03535","created_at":"2026-07-05T10:24:47.324852+00:00"},{"alias_kind":"pith_short_12","alias_value":"PPSZZIYS2FX4","created_at":"2026-07-05T10:24:47.324852+00:00"},{"alias_kind":"pith_short_16","alias_value":"PPSZZIYS2FX4EREE","created_at":"2026-07-05T10:24:47.324852+00:00"},{"alias_kind":"pith_short_8","alias_value":"PPSZZIYS","created_at":"2026-07-05T10:24:47.324852+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15424","citing_title":"Social-Mamba: Socially-Aware Trajectory Forecasting with State-Space Models","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PPSZZIYS2FX4EREESFOHDABE2R","json":"https://pith.science/pith/PPSZZIYS2FX4EREESFOHDABE2R.json","graph_json":"https://pith.science/api/pith-number/PPSZZIYS2FX4EREESFOHDABE2R/graph.json","events_json":"https://pith.science/api/pith-number/PPSZZIYS2FX4EREESFOHDABE2R/events.json","paper":"https://pith.science/paper/PPSZZIYS"},"agent_actions":{"view_html":"https://pith.science/pith/PPSZZIYS2FX4EREESFOHDABE2R","download_json":"https://pith.science/pith/PPSZZIYS2FX4EREESFOHDABE2R.json","view_paper":"https://pith.science/paper/PPSZZIYS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.03535&json=true","fetch_graph":"https://pith.science/api/pith-number/PPSZZIYS2FX4EREESFOHDABE2R/graph.json","fetch_events":"https://pith.science/api/pith-number/PPSZZIYS2FX4EREESFOHDABE2R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PPSZZIYS2FX4EREESFOHDABE2R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PPSZZIYS2FX4EREESFOHDABE2R/action/storage_attestation","attest_author":"https://pith.science/pith/PPSZZIYS2FX4EREESFOHDABE2R/action/author_attestation","sign_citation":"https://pith.science/pith/PPSZZIYS2FX4EREESFOHDABE2R/action/citation_signature","submit_replication":"https://pith.science/pith/PPSZZIYS2FX4EREESFOHDABE2R/action/replication_record"}},"created_at":"2026-07-05T10:24:47.324852+00:00","updated_at":"2026-07-05T10:24:47.324852+00:00"}