{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CMOMB3K7ODW5CHNN7KBUBKX24Y","short_pith_number":"pith:CMOMB3K7","schema_version":"1.0","canonical_sha256":"131cc0ed5f70edd11dadfa8340aafae60c693b0f1a45456ce50dc8555147204d","source":{"kind":"arxiv","id":"2503.22201","version":1},"attestation_state":"computed","paper":{"title":"Multi-modal Knowledge Distillation-based Human Trajectory Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daehee Park, Giwon Lee, Jaewoo Jeong, Kuk-Jin Yoon, Seohee Lee","submitted_at":"2025-03-28T07:32:51Z","abstract_excerpt":"Pedestrian trajectory forecasting is crucial in various applications such as autonomous driving and mobile robot navigation. In such applications, camera-based perception enables the extraction of additional modalities (human pose, text) to enhance prediction accuracy. Indeed, we find that textual descriptions play a crucial role in integrating additional modalities into a unified understanding. However, online extraction of text requires the use of VLM, which may not be feasible for resource-constrained systems. To address this challenge, we propose a multi-modal knowledge distillation framew"},"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":"2503.22201","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T07:32:51Z","cross_cats_sorted":[],"title_canon_sha256":"bab1906712482e45cdf2fc56be75faf8ec3116928849a8c24dac1692f169d2b7","abstract_canon_sha256":"ee75eccab21d1a0da30f29882c3881eb9508e430b2426717afa3087702c7767d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:49.241601Z","signature_b64":"G7PTsZj/ywe5ARs4HTrIrFC7x6Q0KSdz0Hh3ntzV+dmCvUap249l7B8W7HOE8yfkVOad2VaSUZTcZddPwUqOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"131cc0ed5f70edd11dadfa8340aafae60c693b0f1a45456ce50dc8555147204d","last_reissued_at":"2026-07-05T10:40:49.241044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:49.241044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-modal Knowledge Distillation-based Human Trajectory Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daehee Park, Giwon Lee, Jaewoo Jeong, Kuk-Jin Yoon, Seohee Lee","submitted_at":"2025-03-28T07:32:51Z","abstract_excerpt":"Pedestrian trajectory forecasting is crucial in various applications such as autonomous driving and mobile robot navigation. In such applications, camera-based perception enables the extraction of additional modalities (human pose, text) to enhance prediction accuracy. Indeed, we find that textual descriptions play a crucial role in integrating additional modalities into a unified understanding. However, online extraction of text requires the use of VLM, which may not be feasible for resource-constrained systems. To address this challenge, we propose a multi-modal knowledge distillation framew"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22201","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/2503.22201/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":"2503.22201","created_at":"2026-07-05T10:40:49.241138+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.22201v1","created_at":"2026-07-05T10:40:49.241138+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22201","created_at":"2026-07-05T10:40:49.241138+00:00"},{"alias_kind":"pith_short_12","alias_value":"CMOMB3K7ODW5","created_at":"2026-07-05T10:40:49.241138+00:00"},{"alias_kind":"pith_short_16","alias_value":"CMOMB3K7ODW5CHNN","created_at":"2026-07-05T10:40:49.241138+00:00"},{"alias_kind":"pith_short_8","alias_value":"CMOMB3K7","created_at":"2026-07-05T10:40:49.241138+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/CMOMB3K7ODW5CHNN7KBUBKX24Y","json":"https://pith.science/pith/CMOMB3K7ODW5CHNN7KBUBKX24Y.json","graph_json":"https://pith.science/api/pith-number/CMOMB3K7ODW5CHNN7KBUBKX24Y/graph.json","events_json":"https://pith.science/api/pith-number/CMOMB3K7ODW5CHNN7KBUBKX24Y/events.json","paper":"https://pith.science/paper/CMOMB3K7"},"agent_actions":{"view_html":"https://pith.science/pith/CMOMB3K7ODW5CHNN7KBUBKX24Y","download_json":"https://pith.science/pith/CMOMB3K7ODW5CHNN7KBUBKX24Y.json","view_paper":"https://pith.science/paper/CMOMB3K7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.22201&json=true","fetch_graph":"https://pith.science/api/pith-number/CMOMB3K7ODW5CHNN7KBUBKX24Y/graph.json","fetch_events":"https://pith.science/api/pith-number/CMOMB3K7ODW5CHNN7KBUBKX24Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CMOMB3K7ODW5CHNN7KBUBKX24Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CMOMB3K7ODW5CHNN7KBUBKX24Y/action/storage_attestation","attest_author":"https://pith.science/pith/CMOMB3K7ODW5CHNN7KBUBKX24Y/action/author_attestation","sign_citation":"https://pith.science/pith/CMOMB3K7ODW5CHNN7KBUBKX24Y/action/citation_signature","submit_replication":"https://pith.science/pith/CMOMB3K7ODW5CHNN7KBUBKX24Y/action/replication_record"}},"created_at":"2026-07-05T10:40:49.241138+00:00","updated_at":"2026-07-05T10:40:49.241138+00:00"}