{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:B4XTHMRVNCARYQSMX6ZRL5OYSQ","short_pith_number":"pith:B4XTHMRV","schema_version":"1.0","canonical_sha256":"0f2f33b23568811c424cbfb315f5d894179b0d96689ae1dab2b827137159eb95","source":{"kind":"arxiv","id":"2301.13190","version":1},"attestation_state":"computed","paper":{"title":"Audio-Visual Segmentation with Semantics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Guo, Jianyuan Wang, Jiayi Zhang, Jing Zhang, Jinxing Zhou, Lingpeng Kong, Meng Wang, Stan Birchfield, Weixuan Sun, Xuyang Shen, Yiran Zhong","submitted_at":"2023-01-30T18:53:32Z","abstract_excerpt":"We propose a new problem called audio-visual segmentation (AVS), in which the goal is to output a pixel-level map of the object(s) that produce sound at the time of the image frame. To facilitate this research, we construct the first audio-visual segmentation benchmark, i.e., AVSBench, providing pixel-wise annotations for sounding objects in audible videos. It contains three subsets: AVSBench-object (Single-source subset, Multi-sources subset) and AVSBench-semantic (Semantic-labels subset). Accordingly, three settings are studied: 1) semi-supervised audio-visual segmentation with a single soun"},"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":"2301.13190","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-30T18:53:32Z","cross_cats_sorted":[],"title_canon_sha256":"19ff4421b11fefa64999006542888d77cab37057e779933aacb82bc71dc5b9e0","abstract_canon_sha256":"95a464e7c0c304bfa9c2545119e6d28a9f9491c586a3127f21791720bca63e0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:37:01.738198Z","signature_b64":"CEcDpFLr7+FwGsuls3EoUXjNTFH3vCGvD7wg1wh2n82DudvzKHzUXSvK3BtjkjHBx1lmjmAAmTbPm9BjbwNGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f2f33b23568811c424cbfb315f5d894179b0d96689ae1dab2b827137159eb95","last_reissued_at":"2026-07-05T05:37:01.737699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:37:01.737699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Visual Segmentation with Semantics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Guo, Jianyuan Wang, Jiayi Zhang, Jing Zhang, Jinxing Zhou, Lingpeng Kong, Meng Wang, Stan Birchfield, Weixuan Sun, Xuyang Shen, Yiran Zhong","submitted_at":"2023-01-30T18:53:32Z","abstract_excerpt":"We propose a new problem called audio-visual segmentation (AVS), in which the goal is to output a pixel-level map of the object(s) that produce sound at the time of the image frame. To facilitate this research, we construct the first audio-visual segmentation benchmark, i.e., AVSBench, providing pixel-wise annotations for sounding objects in audible videos. It contains three subsets: AVSBench-object (Single-source subset, Multi-sources subset) and AVSBench-semantic (Semantic-labels subset). Accordingly, three settings are studied: 1) semi-supervised audio-visual segmentation with a single soun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13190","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/2301.13190/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":"2301.13190","created_at":"2026-07-05T05:37:01.737765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13190v1","created_at":"2026-07-05T05:37:01.737765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13190","created_at":"2026-07-05T05:37:01.737765+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4XTHMRVNCAR","created_at":"2026-07-05T05:37:01.737765+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4XTHMRVNCARYQSM","created_at":"2026-07-05T05:37:01.737765+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4XTHMRV","created_at":"2026-07-05T05:37:01.737765+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.01015","citing_title":"AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4XTHMRVNCARYQSMX6ZRL5OYSQ","json":"https://pith.science/pith/B4XTHMRVNCARYQSMX6ZRL5OYSQ.json","graph_json":"https://pith.science/api/pith-number/B4XTHMRVNCARYQSMX6ZRL5OYSQ/graph.json","events_json":"https://pith.science/api/pith-number/B4XTHMRVNCARYQSMX6ZRL5OYSQ/events.json","paper":"https://pith.science/paper/B4XTHMRV"},"agent_actions":{"view_html":"https://pith.science/pith/B4XTHMRVNCARYQSMX6ZRL5OYSQ","download_json":"https://pith.science/pith/B4XTHMRVNCARYQSMX6ZRL5OYSQ.json","view_paper":"https://pith.science/paper/B4XTHMRV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13190&json=true","fetch_graph":"https://pith.science/api/pith-number/B4XTHMRVNCARYQSMX6ZRL5OYSQ/graph.json","fetch_events":"https://pith.science/api/pith-number/B4XTHMRVNCARYQSMX6ZRL5OYSQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4XTHMRVNCARYQSMX6ZRL5OYSQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4XTHMRVNCARYQSMX6ZRL5OYSQ/action/storage_attestation","attest_author":"https://pith.science/pith/B4XTHMRVNCARYQSMX6ZRL5OYSQ/action/author_attestation","sign_citation":"https://pith.science/pith/B4XTHMRVNCARYQSMX6ZRL5OYSQ/action/citation_signature","submit_replication":"https://pith.science/pith/B4XTHMRVNCARYQSMX6ZRL5OYSQ/action/replication_record"}},"created_at":"2026-07-05T05:37:01.737765+00:00","updated_at":"2026-07-05T05:37:01.737765+00:00"}