{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SACDP7U7DLVQRLILFZRPPNFLJH","short_pith_number":"pith:SACDP7U7","schema_version":"1.0","canonical_sha256":"900437fe9f1aeb08ad0b2e62f7b4ab49e16aaab2ecffb429df4fafdf99481496","source":{"kind":"arxiv","id":"2309.06728","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Foundation models for Unsupervised Audio-Visual Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Diptesh Kanojia, Haosen Yang, Swapnil Bhosale, Xiatian Zhu","submitted_at":"2023-09-13T05:05:47Z","abstract_excerpt":"Audio-Visual Segmentation (AVS) aims to precisely outline audible objects in a visual scene at the pixel level. Existing AVS methods require fine-grained annotations of audio-mask pairs in supervised learning fashion. This limits their scalability since it is time consuming and tedious to acquire such cross-modality pixel level labels. To overcome this obstacle, in this work we introduce unsupervised audio-visual segmentation with no need for task-specific data annotations and model training. For tackling this newly proposed problem, we formulate a novel Cross-Modality Semantic Filtering (CMSF"},"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":"2309.06728","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-13T05:05:47Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"cba5b60f6cdaaa94134f9d9e47bf555f8dd461d53a50f513fc885de2b226637e","abstract_canon_sha256":"589e7de9585099074a62d6b062eac5714dd1e40540d3543941e975e97b4e026e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:21.796509Z","signature_b64":"QZRgE4wklzoawrEl52BVxljQ4lHrWsR8LKlMjlUVuNrbNi2pmCcrZLCfEeKhGEkna1tkOPPZgUKWdeZ26/f7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"900437fe9f1aeb08ad0b2e62f7b4ab49e16aaab2ecffb429df4fafdf99481496","last_reissued_at":"2026-07-05T06:50:21.796092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:21.796092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Foundation models for Unsupervised Audio-Visual Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Diptesh Kanojia, Haosen Yang, Swapnil Bhosale, Xiatian Zhu","submitted_at":"2023-09-13T05:05:47Z","abstract_excerpt":"Audio-Visual Segmentation (AVS) aims to precisely outline audible objects in a visual scene at the pixel level. Existing AVS methods require fine-grained annotations of audio-mask pairs in supervised learning fashion. This limits their scalability since it is time consuming and tedious to acquire such cross-modality pixel level labels. To overcome this obstacle, in this work we introduce unsupervised audio-visual segmentation with no need for task-specific data annotations and model training. For tackling this newly proposed problem, we formulate a novel Cross-Modality Semantic Filtering (CMSF"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06728","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/2309.06728/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":"2309.06728","created_at":"2026-07-05T06:50:21.796151+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.06728v1","created_at":"2026-07-05T06:50:21.796151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06728","created_at":"2026-07-05T06:50:21.796151+00:00"},{"alias_kind":"pith_short_12","alias_value":"SACDP7U7DLVQ","created_at":"2026-07-05T06:50:21.796151+00:00"},{"alias_kind":"pith_short_16","alias_value":"SACDP7U7DLVQRLIL","created_at":"2026-07-05T06:50:21.796151+00:00"},{"alias_kind":"pith_short_8","alias_value":"SACDP7U7","created_at":"2026-07-05T06:50:21.796151+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/SACDP7U7DLVQRLILFZRPPNFLJH","json":"https://pith.science/pith/SACDP7U7DLVQRLILFZRPPNFLJH.json","graph_json":"https://pith.science/api/pith-number/SACDP7U7DLVQRLILFZRPPNFLJH/graph.json","events_json":"https://pith.science/api/pith-number/SACDP7U7DLVQRLILFZRPPNFLJH/events.json","paper":"https://pith.science/paper/SACDP7U7"},"agent_actions":{"view_html":"https://pith.science/pith/SACDP7U7DLVQRLILFZRPPNFLJH","download_json":"https://pith.science/pith/SACDP7U7DLVQRLILFZRPPNFLJH.json","view_paper":"https://pith.science/paper/SACDP7U7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.06728&json=true","fetch_graph":"https://pith.science/api/pith-number/SACDP7U7DLVQRLILFZRPPNFLJH/graph.json","fetch_events":"https://pith.science/api/pith-number/SACDP7U7DLVQRLILFZRPPNFLJH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SACDP7U7DLVQRLILFZRPPNFLJH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SACDP7U7DLVQRLILFZRPPNFLJH/action/storage_attestation","attest_author":"https://pith.science/pith/SACDP7U7DLVQRLILFZRPPNFLJH/action/author_attestation","sign_citation":"https://pith.science/pith/SACDP7U7DLVQRLILFZRPPNFLJH/action/citation_signature","submit_replication":"https://pith.science/pith/SACDP7U7DLVQRLILFZRPPNFLJH/action/replication_record"}},"created_at":"2026-07-05T06:50:21.796151+00:00","updated_at":"2026-07-05T06:50:21.796151+00:00"}