{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5B2ZSG6DLZQSFV72ZSPWJYLXCL","short_pith_number":"pith:5B2ZSG6D","schema_version":"1.0","canonical_sha256":"e875991bc35e6122d7facc9f64e17712dc4d8e5a4723c73b5e0344f61ac02437","source":{"kind":"arxiv","id":"2412.16928","version":1},"attestation_state":"computed","paper":{"title":"AV-DTEC: Self-Supervised Audio-Visual Fusion for Drone Trajectory Estimation and Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Guili Xu, Shenghai Yuan, Xianglong Zeng, Yizhuo Yang, Zhenyuan Xiao","submitted_at":"2024-12-22T08:58:15Z","abstract_excerpt":"The increasing use of compact UAVs has created significant threats to public safety, while traditional drone detection systems are often bulky and costly. To address these challenges, we propose AV-DTEC, a lightweight self-supervised audio-visual fusion-based anti-UAV system. AV-DTEC is trained using self-supervised learning with labels generated by LiDAR, and it simultaneously learns audio and visual features through a parallel selective state-space model. With the learned features, a specially designed plug-and-play primary-auxiliary feature enhancement module integrates visual features into"},"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":"2412.16928","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-22T08:58:15Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"b6bf56800329954ad7f29dcba8f0919ae87ef3c09927e80418e3886826ce9f3f","abstract_canon_sha256":"6672b0e5ceda70131bbf347bca8ad3cd5f9965b1f8ef076ccd6d9251c3f1d24e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:14.885244Z","signature_b64":"uCe8Pm27OxxgbE7SeZkk2g4DiC6wXw5NSls7fZ+hBagWvpnlzl1lL1e4vA3+WwOtprA+Edu/LCYWfkXOmtEbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e875991bc35e6122d7facc9f64e17712dc4d8e5a4723c73b5e0344f61ac02437","last_reissued_at":"2026-07-05T09:53:14.884870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:14.884870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AV-DTEC: Self-Supervised Audio-Visual Fusion for Drone Trajectory Estimation and Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Guili Xu, Shenghai Yuan, Xianglong Zeng, Yizhuo Yang, Zhenyuan Xiao","submitted_at":"2024-12-22T08:58:15Z","abstract_excerpt":"The increasing use of compact UAVs has created significant threats to public safety, while traditional drone detection systems are often bulky and costly. To address these challenges, we propose AV-DTEC, a lightweight self-supervised audio-visual fusion-based anti-UAV system. AV-DTEC is trained using self-supervised learning with labels generated by LiDAR, and it simultaneously learns audio and visual features through a parallel selective state-space model. With the learned features, a specially designed plug-and-play primary-auxiliary feature enhancement module integrates visual features into"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16928","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/2412.16928/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":"2412.16928","created_at":"2026-07-05T09:53:14.884919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16928v1","created_at":"2026-07-05T09:53:14.884919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16928","created_at":"2026-07-05T09:53:14.884919+00:00"},{"alias_kind":"pith_short_12","alias_value":"5B2ZSG6DLZQS","created_at":"2026-07-05T09:53:14.884919+00:00"},{"alias_kind":"pith_short_16","alias_value":"5B2ZSG6DLZQSFV72","created_at":"2026-07-05T09:53:14.884919+00:00"},{"alias_kind":"pith_short_8","alias_value":"5B2ZSG6D","created_at":"2026-07-05T09:53:14.884919+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.13106","citing_title":"Autonomous 3D Moving Target Encirclement and Interception with Range measurement","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5B2ZSG6DLZQSFV72ZSPWJYLXCL","json":"https://pith.science/pith/5B2ZSG6DLZQSFV72ZSPWJYLXCL.json","graph_json":"https://pith.science/api/pith-number/5B2ZSG6DLZQSFV72ZSPWJYLXCL/graph.json","events_json":"https://pith.science/api/pith-number/5B2ZSG6DLZQSFV72ZSPWJYLXCL/events.json","paper":"https://pith.science/paper/5B2ZSG6D"},"agent_actions":{"view_html":"https://pith.science/pith/5B2ZSG6DLZQSFV72ZSPWJYLXCL","download_json":"https://pith.science/pith/5B2ZSG6DLZQSFV72ZSPWJYLXCL.json","view_paper":"https://pith.science/paper/5B2ZSG6D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16928&json=true","fetch_graph":"https://pith.science/api/pith-number/5B2ZSG6DLZQSFV72ZSPWJYLXCL/graph.json","fetch_events":"https://pith.science/api/pith-number/5B2ZSG6DLZQSFV72ZSPWJYLXCL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5B2ZSG6DLZQSFV72ZSPWJYLXCL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5B2ZSG6DLZQSFV72ZSPWJYLXCL/action/storage_attestation","attest_author":"https://pith.science/pith/5B2ZSG6DLZQSFV72ZSPWJYLXCL/action/author_attestation","sign_citation":"https://pith.science/pith/5B2ZSG6DLZQSFV72ZSPWJYLXCL/action/citation_signature","submit_replication":"https://pith.science/pith/5B2ZSG6DLZQSFV72ZSPWJYLXCL/action/replication_record"}},"created_at":"2026-07-05T09:53:14.884919+00:00","updated_at":"2026-07-05T09:53:14.884919+00:00"}