{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:STIS3YUTHH3BRKAOGXLN5YQE5W","short_pith_number":"pith:STIS3YUT","schema_version":"1.0","canonical_sha256":"94d12de29339f618a80e35d6dee204ed89581d52db46c97a5d3c61efc2d81b66","source":{"kind":"arxiv","id":"1803.08842","version":1},"attestation_state":"computed","paper":{"title":"Audio-Visual Event Localization in Unconstrained Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bochen Li, Chenliang Xu, Jing Shi, Yapeng Tian, Zhiyao Duan","submitted_at":"2018-03-23T15:34:03Z","abstract_excerpt":"In this paper, we introduce a novel problem of audio-visual event localization in unconstrained videos. We define an audio-visual event as an event that is both visible and audible in a video segment. We collect an Audio-Visual Event(AVE) dataset to systemically investigate three temporal localization tasks: supervised and weakly-supervised audio-visual event localization, and cross-modality localization. We develop an audio-guided visual attention mechanism to explore audio-visual correlations, propose a dual multimodal residual network (DMRN) to fuse information over the two modalities, and "},"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":"1803.08842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-23T15:34:03Z","cross_cats_sorted":[],"title_canon_sha256":"ead55faa2ad5e8d035ecdb486c1ae4ad939acc2b37268f1d177069ef3a4df064","abstract_canon_sha256":"25d7b0698ffa0bc9cbf82ee5e59d26605050d1fb58f17ccb1d49c7b29c97fc52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:18.417706Z","signature_b64":"kFJfn87IzfdZ8GQbc9cb1Bf9rs75jj74v1kDllAcmUerfd6icfCrqDNWZZmuuLvK31Ev+8JPWf7CzryQRlqqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94d12de29339f618a80e35d6dee204ed89581d52db46c97a5d3c61efc2d81b66","last_reissued_at":"2026-05-18T00:20:18.417032Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:18.417032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Visual Event Localization in Unconstrained Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bochen Li, Chenliang Xu, Jing Shi, Yapeng Tian, Zhiyao Duan","submitted_at":"2018-03-23T15:34:03Z","abstract_excerpt":"In this paper, we introduce a novel problem of audio-visual event localization in unconstrained videos. We define an audio-visual event as an event that is both visible and audible in a video segment. We collect an Audio-Visual Event(AVE) dataset to systemically investigate three temporal localization tasks: supervised and weakly-supervised audio-visual event localization, and cross-modality localization. We develop an audio-guided visual attention mechanism to explore audio-visual correlations, propose a dual multimodal residual network (DMRN) to fuse information over the two modalities, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.08842","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":""},"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":"1803.08842","created_at":"2026-05-18T00:20:18.417169+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.08842v1","created_at":"2026-05-18T00:20:18.417169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.08842","created_at":"2026-05-18T00:20:18.417169+00:00"},{"alias_kind":"pith_short_12","alias_value":"STIS3YUTHH3B","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"STIS3YUTHH3BRKAO","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"STIS3YUT","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23321","citing_title":"MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding Models","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/STIS3YUTHH3BRKAOGXLN5YQE5W","json":"https://pith.science/pith/STIS3YUTHH3BRKAOGXLN5YQE5W.json","graph_json":"https://pith.science/api/pith-number/STIS3YUTHH3BRKAOGXLN5YQE5W/graph.json","events_json":"https://pith.science/api/pith-number/STIS3YUTHH3BRKAOGXLN5YQE5W/events.json","paper":"https://pith.science/paper/STIS3YUT"},"agent_actions":{"view_html":"https://pith.science/pith/STIS3YUTHH3BRKAOGXLN5YQE5W","download_json":"https://pith.science/pith/STIS3YUTHH3BRKAOGXLN5YQE5W.json","view_paper":"https://pith.science/paper/STIS3YUT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.08842&json=true","fetch_graph":"https://pith.science/api/pith-number/STIS3YUTHH3BRKAOGXLN5YQE5W/graph.json","fetch_events":"https://pith.science/api/pith-number/STIS3YUTHH3BRKAOGXLN5YQE5W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STIS3YUTHH3BRKAOGXLN5YQE5W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STIS3YUTHH3BRKAOGXLN5YQE5W/action/storage_attestation","attest_author":"https://pith.science/pith/STIS3YUTHH3BRKAOGXLN5YQE5W/action/author_attestation","sign_citation":"https://pith.science/pith/STIS3YUTHH3BRKAOGXLN5YQE5W/action/citation_signature","submit_replication":"https://pith.science/pith/STIS3YUTHH3BRKAOGXLN5YQE5W/action/replication_record"}},"created_at":"2026-05-18T00:20:18.417169+00:00","updated_at":"2026-05-18T00:20:18.417169+00:00"}