{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2YPC2YZJ76Q7XFHRD4XPV7MPUJ","short_pith_number":"pith:2YPC2YZJ","schema_version":"1.0","canonical_sha256":"d61e2d6329ffa1fb94f11f2efafd8fa27629315e3f76ffd913b98c6b0b1aa9ff","source":{"kind":"arxiv","id":"2001.09414","version":1},"attestation_state":"computed","paper":{"title":"Curriculum Audiovisual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dejing Dou, Di Hu, Dong Wang, Feiping Nie, Haoyi Xiong, Zheng Wang","submitted_at":"2020-01-26T07:08:47Z","abstract_excerpt":"Associating sound and its producer in complex audiovisual scene is a challenging task, especially when we are lack of annotated training data. In this paper, we present a flexible audiovisual model that introduces a soft-clustering module as the audio and visual content detector, and regards the pervasive property of audiovisual concurrency as the latent supervision for inferring the correlation among detected contents. To ease the difficulty of audiovisual learning, we propose a novel curriculum learning strategy that trains the model from simple to complex scene. We show that such ordered le"},"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":"2001.09414","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-26T07:08:47Z","cross_cats_sorted":[],"title_canon_sha256":"9a15e40bb9e80f1077b270523071962a8690ab01104649b7fa44dc0aaac9648b","abstract_canon_sha256":"0ccdf07c459abcbaf57f173e8f0ad60c42d70a9eacf278d70a093223c3ce4386"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:59.372887Z","signature_b64":"hoD1WqvqF3/rnq57FaXmpMKmP3v570wqyd50XRHCIERT47tLoeUFmwwK8zEfFqNjdwBpAdClk+kdyVsIDeopAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d61e2d6329ffa1fb94f11f2efafd8fa27629315e3f76ffd913b98c6b0b1aa9ff","last_reissued_at":"2026-07-05T00:35:59.372351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:59.372351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curriculum Audiovisual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dejing Dou, Di Hu, Dong Wang, Feiping Nie, Haoyi Xiong, Zheng Wang","submitted_at":"2020-01-26T07:08:47Z","abstract_excerpt":"Associating sound and its producer in complex audiovisual scene is a challenging task, especially when we are lack of annotated training data. In this paper, we present a flexible audiovisual model that introduces a soft-clustering module as the audio and visual content detector, and regards the pervasive property of audiovisual concurrency as the latent supervision for inferring the correlation among detected contents. To ease the difficulty of audiovisual learning, we propose a novel curriculum learning strategy that trains the model from simple to complex scene. We show that such ordered le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.09414","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/2001.09414/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":"2001.09414","created_at":"2026-07-05T00:35:59.372404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.09414v1","created_at":"2026-07-05T00:35:59.372404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.09414","created_at":"2026-07-05T00:35:59.372404+00:00"},{"alias_kind":"pith_short_12","alias_value":"2YPC2YZJ76Q7","created_at":"2026-07-05T00:35:59.372404+00:00"},{"alias_kind":"pith_short_16","alias_value":"2YPC2YZJ76Q7XFHR","created_at":"2026-07-05T00:35:59.372404+00:00"},{"alias_kind":"pith_short_8","alias_value":"2YPC2YZJ","created_at":"2026-07-05T00:35:59.372404+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/2YPC2YZJ76Q7XFHRD4XPV7MPUJ","json":"https://pith.science/pith/2YPC2YZJ76Q7XFHRD4XPV7MPUJ.json","graph_json":"https://pith.science/api/pith-number/2YPC2YZJ76Q7XFHRD4XPV7MPUJ/graph.json","events_json":"https://pith.science/api/pith-number/2YPC2YZJ76Q7XFHRD4XPV7MPUJ/events.json","paper":"https://pith.science/paper/2YPC2YZJ"},"agent_actions":{"view_html":"https://pith.science/pith/2YPC2YZJ76Q7XFHRD4XPV7MPUJ","download_json":"https://pith.science/pith/2YPC2YZJ76Q7XFHRD4XPV7MPUJ.json","view_paper":"https://pith.science/paper/2YPC2YZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.09414&json=true","fetch_graph":"https://pith.science/api/pith-number/2YPC2YZJ76Q7XFHRD4XPV7MPUJ/graph.json","fetch_events":"https://pith.science/api/pith-number/2YPC2YZJ76Q7XFHRD4XPV7MPUJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2YPC2YZJ76Q7XFHRD4XPV7MPUJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2YPC2YZJ76Q7XFHRD4XPV7MPUJ/action/storage_attestation","attest_author":"https://pith.science/pith/2YPC2YZJ76Q7XFHRD4XPV7MPUJ/action/author_attestation","sign_citation":"https://pith.science/pith/2YPC2YZJ76Q7XFHRD4XPV7MPUJ/action/citation_signature","submit_replication":"https://pith.science/pith/2YPC2YZJ76Q7XFHRD4XPV7MPUJ/action/replication_record"}},"created_at":"2026-07-05T00:35:59.372404+00:00","updated_at":"2026-07-05T00:35:59.372404+00:00"}