{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4Y73VZRGPRWP7WA4NPJZIFFK2M","short_pith_number":"pith:4Y73VZRG","schema_version":"1.0","canonical_sha256":"e63fbae6267c6cffd81c6bd39414aad310206955229d29c0b812283d506f7e15","source":{"kind":"arxiv","id":"2408.05075","version":3},"attestation_state":"computed","paper":{"title":"DeepInteraction++: Multi-Modality Interaction for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Li Zhang, Nan Song, Philip H.S. Torr, Wei Li, Xiatian Zhu, Zeyu Yang","submitted_at":"2024-08-09T14:04:21Z","abstract_excerpt":"Existing top-performance autonomous driving systems typically rely on the multi-modal fusion strategy for reliable scene understanding. This design is however fundamentally restricted due to overlooking the modality-specific strengths and finally hampering the model performance. To address this limitation, in this work, we introduce a novel modality interaction strategy that allows individual per-modality representations to be learned and maintained throughout, enabling their unique characteristics to be exploited during the whole perception pipeline. To demonstrate the effectiveness of the pr"},"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":"2408.05075","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-09T14:04:21Z","cross_cats_sorted":[],"title_canon_sha256":"225543fee000a6c4143529359fa594e23267639a40720fc9c9ee85401865b29c","abstract_canon_sha256":"65a581db34ae253336e2cedf6f764d586641ed0ee0bb397094de2007928a5c7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:48.837269Z","signature_b64":"ZPUMS02D4CIubPVK0N0b27TgtQJjxwLvgOR+H5xzN1whipmajffOMFQW5PLZpAVo0uK45miMAqO+Zk3pdZB7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e63fbae6267c6cffd81c6bd39414aad310206955229d29c0b812283d506f7e15","last_reissued_at":"2026-07-05T10:17:48.836804Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:48.836804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepInteraction++: Multi-Modality Interaction for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Li Zhang, Nan Song, Philip H.S. Torr, Wei Li, Xiatian Zhu, Zeyu Yang","submitted_at":"2024-08-09T14:04:21Z","abstract_excerpt":"Existing top-performance autonomous driving systems typically rely on the multi-modal fusion strategy for reliable scene understanding. This design is however fundamentally restricted due to overlooking the modality-specific strengths and finally hampering the model performance. To address this limitation, in this work, we introduce a novel modality interaction strategy that allows individual per-modality representations to be learned and maintained throughout, enabling their unique characteristics to be exploited during the whole perception pipeline. To demonstrate the effectiveness of the pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05075","kind":"arxiv","version":3},"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/2408.05075/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":"2408.05075","created_at":"2026-07-05T10:17:48.836871+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.05075v3","created_at":"2026-07-05T10:17:48.836871+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05075","created_at":"2026-07-05T10:17:48.836871+00:00"},{"alias_kind":"pith_short_12","alias_value":"4Y73VZRGPRWP","created_at":"2026-07-05T10:17:48.836871+00:00"},{"alias_kind":"pith_short_16","alias_value":"4Y73VZRGPRWP7WA4","created_at":"2026-07-05T10:17:48.836871+00:00"},{"alias_kind":"pith_short_8","alias_value":"4Y73VZRG","created_at":"2026-07-05T10:17:48.836871+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06786","citing_title":"Federated Foundation Models over Vehicular Networks","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4Y73VZRGPRWP7WA4NPJZIFFK2M","json":"https://pith.science/pith/4Y73VZRGPRWP7WA4NPJZIFFK2M.json","graph_json":"https://pith.science/api/pith-number/4Y73VZRGPRWP7WA4NPJZIFFK2M/graph.json","events_json":"https://pith.science/api/pith-number/4Y73VZRGPRWP7WA4NPJZIFFK2M/events.json","paper":"https://pith.science/paper/4Y73VZRG"},"agent_actions":{"view_html":"https://pith.science/pith/4Y73VZRGPRWP7WA4NPJZIFFK2M","download_json":"https://pith.science/pith/4Y73VZRGPRWP7WA4NPJZIFFK2M.json","view_paper":"https://pith.science/paper/4Y73VZRG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.05075&json=true","fetch_graph":"https://pith.science/api/pith-number/4Y73VZRGPRWP7WA4NPJZIFFK2M/graph.json","fetch_events":"https://pith.science/api/pith-number/4Y73VZRGPRWP7WA4NPJZIFFK2M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4Y73VZRGPRWP7WA4NPJZIFFK2M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4Y73VZRGPRWP7WA4NPJZIFFK2M/action/storage_attestation","attest_author":"https://pith.science/pith/4Y73VZRGPRWP7WA4NPJZIFFK2M/action/author_attestation","sign_citation":"https://pith.science/pith/4Y73VZRGPRWP7WA4NPJZIFFK2M/action/citation_signature","submit_replication":"https://pith.science/pith/4Y73VZRGPRWP7WA4NPJZIFFK2M/action/replication_record"}},"created_at":"2026-07-05T10:17:48.836871+00:00","updated_at":"2026-07-05T10:17:48.836871+00:00"}