{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GEW2PGJTQRCWRSHEMZPV75BDOM","short_pith_number":"pith:GEW2PGJT","schema_version":"1.0","canonical_sha256":"312da79933844568c8e4665f5ff4237327a278402f6400f4458665a8db97e02b","source":{"kind":"arxiv","id":"2409.11729","version":1},"attestation_state":"computed","paper":{"title":"DETECLAP: Enhancing Audio-Visual Representation Learning with Object Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Hokuto Munakata, Masayoshi Kondo, Shota Nakada, Taichi Nishimura, Tatsuya Komatsu","submitted_at":"2024-09-18T06:38:48Z","abstract_excerpt":"Current audio-visual representation learning can capture rough object categories (e.g., ``animals'' and ``instruments''), but it lacks the ability to recognize fine-grained details, such as specific categories like ``dogs'' and ``flutes'' within animals and instruments. To address this issue, we introduce DETECLAP, a method to enhance audio-visual representation learning with object information. Our key idea is to introduce an audio-visual label prediction loss to the existing Contrastive Audio-Visual Masked AutoEncoder to enhance its object awareness. To avoid costly manual annotations, we 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":"2409.11729","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-09-18T06:38:48Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"93145486d00cf5bb25f3c434dee02441ccef1c447a4c7a55bc5ab10b710a4385","abstract_canon_sha256":"4d27993b800fd1646807712c381144db75c3c13d2cf5b5383890f9e239f2273f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:36.734373Z","signature_b64":"rW30akGp7fepbsr89R0qDAgseNaHIP3OjVPzDrJpIDt42Q44S14qzkPp0UBbOcnWx+LZHCp/KbVxKf2xlJJQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"312da79933844568c8e4665f5ff4237327a278402f6400f4458665a8db97e02b","last_reissued_at":"2026-07-05T09:08:36.733863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:36.733863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DETECLAP: Enhancing Audio-Visual Representation Learning with Object Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Hokuto Munakata, Masayoshi Kondo, Shota Nakada, Taichi Nishimura, Tatsuya Komatsu","submitted_at":"2024-09-18T06:38:48Z","abstract_excerpt":"Current audio-visual representation learning can capture rough object categories (e.g., ``animals'' and ``instruments''), but it lacks the ability to recognize fine-grained details, such as specific categories like ``dogs'' and ``flutes'' within animals and instruments. To address this issue, we introduce DETECLAP, a method to enhance audio-visual representation learning with object information. Our key idea is to introduce an audio-visual label prediction loss to the existing Contrastive Audio-Visual Masked AutoEncoder to enhance its object awareness. To avoid costly manual annotations, we pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11729","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/2409.11729/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":"2409.11729","created_at":"2026-07-05T09:08:36.733925+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11729v1","created_at":"2026-07-05T09:08:36.733925+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11729","created_at":"2026-07-05T09:08:36.733925+00:00"},{"alias_kind":"pith_short_12","alias_value":"GEW2PGJTQRCW","created_at":"2026-07-05T09:08:36.733925+00:00"},{"alias_kind":"pith_short_16","alias_value":"GEW2PGJTQRCWRSHE","created_at":"2026-07-05T09:08:36.733925+00:00"},{"alias_kind":"pith_short_8","alias_value":"GEW2PGJT","created_at":"2026-07-05T09:08:36.733925+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.11967","citing_title":"Language-Guided Contrastive Audio-Visual Masked Autoencoder with Automatically Generated Audio-Visual-Text Triplets from Videos","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GEW2PGJTQRCWRSHEMZPV75BDOM","json":"https://pith.science/pith/GEW2PGJTQRCWRSHEMZPV75BDOM.json","graph_json":"https://pith.science/api/pith-number/GEW2PGJTQRCWRSHEMZPV75BDOM/graph.json","events_json":"https://pith.science/api/pith-number/GEW2PGJTQRCWRSHEMZPV75BDOM/events.json","paper":"https://pith.science/paper/GEW2PGJT"},"agent_actions":{"view_html":"https://pith.science/pith/GEW2PGJTQRCWRSHEMZPV75BDOM","download_json":"https://pith.science/pith/GEW2PGJTQRCWRSHEMZPV75BDOM.json","view_paper":"https://pith.science/paper/GEW2PGJT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11729&json=true","fetch_graph":"https://pith.science/api/pith-number/GEW2PGJTQRCWRSHEMZPV75BDOM/graph.json","fetch_events":"https://pith.science/api/pith-number/GEW2PGJTQRCWRSHEMZPV75BDOM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GEW2PGJTQRCWRSHEMZPV75BDOM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GEW2PGJTQRCWRSHEMZPV75BDOM/action/storage_attestation","attest_author":"https://pith.science/pith/GEW2PGJTQRCWRSHEMZPV75BDOM/action/author_attestation","sign_citation":"https://pith.science/pith/GEW2PGJTQRCWRSHEMZPV75BDOM/action/citation_signature","submit_replication":"https://pith.science/pith/GEW2PGJTQRCWRSHEMZPV75BDOM/action/replication_record"}},"created_at":"2026-07-05T09:08:36.733925+00:00","updated_at":"2026-07-05T09:08:36.733925+00:00"}