{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CJNKUUYLALAPC2VH7D5LODUP3G","short_pith_number":"pith:CJNKUUYL","schema_version":"1.0","canonical_sha256":"125aaa530b02c0f16aa7f8fab70e8fd992f719753885a7efebe95f65d0f4593e","source":{"kind":"arxiv","id":"2405.10690","version":4},"attestation_state":"computed","paper":{"title":"CoLeaF: A Contrastive-Collaborative Learning Framework for Weakly Supervised Audio-Visual Video Parsing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrian Hilton, Armin Mustafa, Faegheh Sardari, Philip J. B. Jackson","submitted_at":"2024-05-17T10:51:15Z","abstract_excerpt":"Weakly supervised audio-visual video parsing (AVVP) methods aim to detect audible-only, visible-only, and audible-visible events using only video-level labels. Existing approaches tackle this by leveraging unimodal and cross-modal contexts. However, we argue that while cross-modal learning is beneficial for detecting audible-visible events, in the weakly supervised scenario, it negatively impacts unaligned audible or visible events by introducing irrelevant modality information. In this paper, we propose CoLeaF, a novel learning framework that optimizes the integration of cross-modal context i"},"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":"2405.10690","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-17T10:51:15Z","cross_cats_sorted":[],"title_canon_sha256":"41259537c5d64e489c362356e1d56536362173580e4905a6d7492ecab360197c","abstract_canon_sha256":"e043704ec4336c0e989282d540fba33154217dd5639543131c96bb92f4c88eed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:55.920994Z","signature_b64":"b2aL6tDWIb4axYJnc1zPYWSH6/gMj80Qh8uS+OsoEYheBYY9KCGcQ6kKPewCu4f2wDmClec4NP4kQJTiX7WjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"125aaa530b02c0f16aa7f8fab70e8fd992f719753885a7efebe95f65d0f4593e","last_reissued_at":"2026-07-05T08:43:55.920595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:55.920595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoLeaF: A Contrastive-Collaborative Learning Framework for Weakly Supervised Audio-Visual Video Parsing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrian Hilton, Armin Mustafa, Faegheh Sardari, Philip J. B. Jackson","submitted_at":"2024-05-17T10:51:15Z","abstract_excerpt":"Weakly supervised audio-visual video parsing (AVVP) methods aim to detect audible-only, visible-only, and audible-visible events using only video-level labels. Existing approaches tackle this by leveraging unimodal and cross-modal contexts. However, we argue that while cross-modal learning is beneficial for detecting audible-visible events, in the weakly supervised scenario, it negatively impacts unaligned audible or visible events by introducing irrelevant modality information. In this paper, we propose CoLeaF, a novel learning framework that optimizes the integration of cross-modal context i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10690","kind":"arxiv","version":4},"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/2405.10690/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":"2405.10690","created_at":"2026-07-05T08:43:55.920656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10690v4","created_at":"2026-07-05T08:43:55.920656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10690","created_at":"2026-07-05T08:43:55.920656+00:00"},{"alias_kind":"pith_short_12","alias_value":"CJNKUUYLALAP","created_at":"2026-07-05T08:43:55.920656+00:00"},{"alias_kind":"pith_short_16","alias_value":"CJNKUUYLALAPC2VH","created_at":"2026-07-05T08:43:55.920656+00:00"},{"alias_kind":"pith_short_8","alias_value":"CJNKUUYL","created_at":"2026-07-05T08:43:55.920656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.20872","citing_title":"LINK: Adaptive Modality Interaction for Audio-Visual Video Parsing","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CJNKUUYLALAPC2VH7D5LODUP3G","json":"https://pith.science/pith/CJNKUUYLALAPC2VH7D5LODUP3G.json","graph_json":"https://pith.science/api/pith-number/CJNKUUYLALAPC2VH7D5LODUP3G/graph.json","events_json":"https://pith.science/api/pith-number/CJNKUUYLALAPC2VH7D5LODUP3G/events.json","paper":"https://pith.science/paper/CJNKUUYL"},"agent_actions":{"view_html":"https://pith.science/pith/CJNKUUYLALAPC2VH7D5LODUP3G","download_json":"https://pith.science/pith/CJNKUUYLALAPC2VH7D5LODUP3G.json","view_paper":"https://pith.science/paper/CJNKUUYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10690&json=true","fetch_graph":"https://pith.science/api/pith-number/CJNKUUYLALAPC2VH7D5LODUP3G/graph.json","fetch_events":"https://pith.science/api/pith-number/CJNKUUYLALAPC2VH7D5LODUP3G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CJNKUUYLALAPC2VH7D5LODUP3G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CJNKUUYLALAPC2VH7D5LODUP3G/action/storage_attestation","attest_author":"https://pith.science/pith/CJNKUUYLALAPC2VH7D5LODUP3G/action/author_attestation","sign_citation":"https://pith.science/pith/CJNKUUYLALAPC2VH7D5LODUP3G/action/citation_signature","submit_replication":"https://pith.science/pith/CJNKUUYLALAPC2VH7D5LODUP3G/action/replication_record"}},"created_at":"2026-07-05T08:43:55.920656+00:00","updated_at":"2026-07-05T08:43:55.920656+00:00"}