{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UJUEFIXWCX66F5EUPLO2QMEFUN","short_pith_number":"pith:UJUEFIXW","schema_version":"1.0","canonical_sha256":"a26842a2f615fde2f4947adda83085a370b27e3064634014a67724e19599b6f2","source":{"kind":"arxiv","id":"2504.02264","version":1},"attestation_state":"computed","paper":{"title":"MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perception","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huaping Liu, Huiming Yang, Jiayin Zhu, Lening Wang, Pengfei Li, Qiannan Guo, Tiao Tan, Wenshuo Wang, Wenzhuo Liu, Yicheng Qiao, Zhiwei Li, Zilong Chen","submitted_at":"2025-04-03T04:23:27Z","abstract_excerpt":"Advanced driver assistance systems require a comprehensive understanding of the driver's mental/physical state and traffic context but existing works often neglect the potential benefits of joint learning between these tasks. This paper proposes MMTL-UniAD, a unified multi-modal multi-task learning framework that simultaneously recognizes driver behavior (e.g., looking around, talking), driver emotion (e.g., anxiety, happiness), vehicle behavior (e.g., parking, turning), and traffic context (e.g., traffic jam, traffic smooth). A key challenge is avoiding negative transfer between tasks, which "},"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":"2504.02264","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T04:23:27Z","cross_cats_sorted":[],"title_canon_sha256":"fe8ccc3952935bcfb82bc192e5b231e3c6b00455312ff6bebe4ce6b21d9afd74","abstract_canon_sha256":"e13686dd48ca1fc4d57ecf964b9e2d7e68429976224c8bed59ca99c8eff50489"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:53.798465Z","signature_b64":"CgztdhSX5tXu1CeJK72wsHVY+FXNpK0KgFTGPrDYucOvPi4CXV7R8MCD3WFBNrplTKy1hYu3MWmLHCNpA8E/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a26842a2f615fde2f4947adda83085a370b27e3064634014a67724e19599b6f2","last_reissued_at":"2026-07-05T10:43:53.797963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:53.797963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perception","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huaping Liu, Huiming Yang, Jiayin Zhu, Lening Wang, Pengfei Li, Qiannan Guo, Tiao Tan, Wenshuo Wang, Wenzhuo Liu, Yicheng Qiao, Zhiwei Li, Zilong Chen","submitted_at":"2025-04-03T04:23:27Z","abstract_excerpt":"Advanced driver assistance systems require a comprehensive understanding of the driver's mental/physical state and traffic context but existing works often neglect the potential benefits of joint learning between these tasks. This paper proposes MMTL-UniAD, a unified multi-modal multi-task learning framework that simultaneously recognizes driver behavior (e.g., looking around, talking), driver emotion (e.g., anxiety, happiness), vehicle behavior (e.g., parking, turning), and traffic context (e.g., traffic jam, traffic smooth). A key challenge is avoiding negative transfer between tasks, which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02264","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/2504.02264/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":"2504.02264","created_at":"2026-07-05T10:43:53.798027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02264v1","created_at":"2026-07-05T10:43:53.798027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02264","created_at":"2026-07-05T10:43:53.798027+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJUEFIXWCX66","created_at":"2026-07-05T10:43:53.798027+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJUEFIXWCX66F5EU","created_at":"2026-07-05T10:43:53.798027+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJUEFIXW","created_at":"2026-07-05T10:43:53.798027+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18220","citing_title":"EEG-Based Emergency Braking Intensity Prediction Using Blind Source Separation","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UJUEFIXWCX66F5EUPLO2QMEFUN","json":"https://pith.science/pith/UJUEFIXWCX66F5EUPLO2QMEFUN.json","graph_json":"https://pith.science/api/pith-number/UJUEFIXWCX66F5EUPLO2QMEFUN/graph.json","events_json":"https://pith.science/api/pith-number/UJUEFIXWCX66F5EUPLO2QMEFUN/events.json","paper":"https://pith.science/paper/UJUEFIXW"},"agent_actions":{"view_html":"https://pith.science/pith/UJUEFIXWCX66F5EUPLO2QMEFUN","download_json":"https://pith.science/pith/UJUEFIXWCX66F5EUPLO2QMEFUN.json","view_paper":"https://pith.science/paper/UJUEFIXW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02264&json=true","fetch_graph":"https://pith.science/api/pith-number/UJUEFIXWCX66F5EUPLO2QMEFUN/graph.json","fetch_events":"https://pith.science/api/pith-number/UJUEFIXWCX66F5EUPLO2QMEFUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJUEFIXWCX66F5EUPLO2QMEFUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJUEFIXWCX66F5EUPLO2QMEFUN/action/storage_attestation","attest_author":"https://pith.science/pith/UJUEFIXWCX66F5EUPLO2QMEFUN/action/author_attestation","sign_citation":"https://pith.science/pith/UJUEFIXWCX66F5EUPLO2QMEFUN/action/citation_signature","submit_replication":"https://pith.science/pith/UJUEFIXWCX66F5EUPLO2QMEFUN/action/replication_record"}},"created_at":"2026-07-05T10:43:53.798027+00:00","updated_at":"2026-07-05T10:43:53.798027+00:00"}