{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Q3KHO5XOTSAW7YKNHQ7XT5PRNZ","short_pith_number":"pith:Q3KHO5XO","schema_version":"1.0","canonical_sha256":"86d47776ee9c816fe14d3c3f79f5f16e7696606f24dc7fcb16ed553b0dc8f710","source":{"kind":"arxiv","id":"2309.09501","version":1},"attestation_state":"computed","paper":{"title":"Discovering Sounding Objects by Audio Queries for Audio Visual Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Li, Hongji Zhu, Jiao Dai, Jizhong Han, Shaofei Huang, Si Liu, Wenge Rong, Yuqing Wang","submitted_at":"2023-09-18T05:58:06Z","abstract_excerpt":"Audio visual segmentation (AVS) aims to segment the sounding objects for each frame of a given video. To distinguish the sounding objects from silent ones, both audio-visual semantic correspondence and temporal interaction are required. The previous method applies multi-frame cross-modal attention to conduct pixel-level interactions between audio features and visual features of multiple frames simultaneously, which is both redundant and implicit. In this paper, we propose an Audio-Queried Transformer architecture, AQFormer, where we define a set of object queries conditioned on audio informati"},"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":"2309.09501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-18T05:58:06Z","cross_cats_sorted":[],"title_canon_sha256":"f0886ef3013ff0ad8dbcd07ef1224a4659d6232813a8947f87491f1039f01074","abstract_canon_sha256":"bff1e87cc851dc52a3af76033bd1480b7a8c239df855e4bba11ee28850438732"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:40.300008Z","signature_b64":"LIF07YzwnWdgS06GdsYrdwVfGOdsyOyoSU3b4ClPcS7+Nl4wYqMXVmKpoyHbE9KMrFZryIf3iY8H1YzbTLMmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86d47776ee9c816fe14d3c3f79f5f16e7696606f24dc7fcb16ed553b0dc8f710","last_reissued_at":"2026-07-05T06:51:40.299464Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:40.299464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discovering Sounding Objects by Audio Queries for Audio Visual Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Li, Hongji Zhu, Jiao Dai, Jizhong Han, Shaofei Huang, Si Liu, Wenge Rong, Yuqing Wang","submitted_at":"2023-09-18T05:58:06Z","abstract_excerpt":"Audio visual segmentation (AVS) aims to segment the sounding objects for each frame of a given video. To distinguish the sounding objects from silent ones, both audio-visual semantic correspondence and temporal interaction are required. The previous method applies multi-frame cross-modal attention to conduct pixel-level interactions between audio features and visual features of multiple frames simultaneously, which is both redundant and implicit. In this paper, we propose an Audio-Queried Transformer architecture, AQFormer, where we define a set of object queries conditioned on audio informati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09501","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/2309.09501/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":"2309.09501","created_at":"2026-07-05T06:51:40.299527+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09501v1","created_at":"2026-07-05T06:51:40.299527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09501","created_at":"2026-07-05T06:51:40.299527+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3KHO5XOTSAW","created_at":"2026-07-05T06:51:40.299527+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3KHO5XOTSAW7YKN","created_at":"2026-07-05T06:51:40.299527+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3KHO5XO","created_at":"2026-07-05T06:51:40.299527+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":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q3KHO5XOTSAW7YKNHQ7XT5PRNZ","json":"https://pith.science/pith/Q3KHO5XOTSAW7YKNHQ7XT5PRNZ.json","graph_json":"https://pith.science/api/pith-number/Q3KHO5XOTSAW7YKNHQ7XT5PRNZ/graph.json","events_json":"https://pith.science/api/pith-number/Q3KHO5XOTSAW7YKNHQ7XT5PRNZ/events.json","paper":"https://pith.science/paper/Q3KHO5XO"},"agent_actions":{"view_html":"https://pith.science/pith/Q3KHO5XOTSAW7YKNHQ7XT5PRNZ","download_json":"https://pith.science/pith/Q3KHO5XOTSAW7YKNHQ7XT5PRNZ.json","view_paper":"https://pith.science/paper/Q3KHO5XO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09501&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3KHO5XOTSAW7YKNHQ7XT5PRNZ/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3KHO5XOTSAW7YKNHQ7XT5PRNZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3KHO5XOTSAW7YKNHQ7XT5PRNZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3KHO5XOTSAW7YKNHQ7XT5PRNZ/action/storage_attestation","attest_author":"https://pith.science/pith/Q3KHO5XOTSAW7YKNHQ7XT5PRNZ/action/author_attestation","sign_citation":"https://pith.science/pith/Q3KHO5XOTSAW7YKNHQ7XT5PRNZ/action/citation_signature","submit_replication":"https://pith.science/pith/Q3KHO5XOTSAW7YKNHQ7XT5PRNZ/action/replication_record"}},"created_at":"2026-07-05T06:51:40.299527+00:00","updated_at":"2026-07-05T06:51:40.299527+00:00"}