{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NFL6YJM4IHCIWHBT4B2CPZFXPG","short_pith_number":"pith:NFL6YJM4","schema_version":"1.0","canonical_sha256":"6957ec259c41c48b1c33e07427e4b77982cf030b74afa34929f9574381773bcf","source":{"kind":"arxiv","id":"2307.13236","version":1},"attestation_state":"computed","paper":{"title":"Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chaofan Ma, Chen Ju, Jinxiang Liu, Yanfeng Wang, Ya Zhang, Yu Wang","submitted_at":"2023-07-25T03:59:04Z","abstract_excerpt":"The goal of the audio-visual segmentation (AVS) task is to segment the sounding objects in the video frames using audio cues. However, current fusion-based methods have the performance limitations due to the small receptive field of convolution and inadequate fusion of audio-visual features. To overcome these issues, we propose a novel \\textbf{Au}dio-aware query-enhanced \\textbf{TR}ansformer (AuTR) to tackle the task. Unlike existing methods, our approach introduces a multimodal transformer architecture that enables deep fusion and aggregation of audio-visual features. Furthermore, we devise a"},"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":"2307.13236","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-25T03:59:04Z","cross_cats_sorted":["cs.CV","cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"fac611864fb70cb13edb745b07385fefef7674759ce39028a0bbd2f41aa54254","abstract_canon_sha256":"937f9d18e537d8179121511bbc45809e31bb03b5cb7f1dd9bc56b2fca9e7e70f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:11.049303Z","signature_b64":"4CYC8WeBS6pS0654mqDHRinvnYXXC4M0iditq+IZZHxI+GjMRPsMyOQvhpwCfM6nMQ3FJCUfbjVhUK2lqxDRDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6957ec259c41c48b1c33e07427e4b77982cf030b74afa34929f9574381773bcf","last_reissued_at":"2026-07-05T06:34:11.048873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:11.048873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chaofan Ma, Chen Ju, Jinxiang Liu, Yanfeng Wang, Ya Zhang, Yu Wang","submitted_at":"2023-07-25T03:59:04Z","abstract_excerpt":"The goal of the audio-visual segmentation (AVS) task is to segment the sounding objects in the video frames using audio cues. However, current fusion-based methods have the performance limitations due to the small receptive field of convolution and inadequate fusion of audio-visual features. To overcome these issues, we propose a novel \\textbf{Au}dio-aware query-enhanced \\textbf{TR}ansformer (AuTR) to tackle the task. Unlike existing methods, our approach introduces a multimodal transformer architecture that enables deep fusion and aggregation of audio-visual features. Furthermore, we devise a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.13236","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/2307.13236/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":"2307.13236","created_at":"2026-07-05T06:34:11.048930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.13236v1","created_at":"2026-07-05T06:34:11.048930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.13236","created_at":"2026-07-05T06:34:11.048930+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFL6YJM4IHCI","created_at":"2026-07-05T06:34:11.048930+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFL6YJM4IHCIWHBT","created_at":"2026-07-05T06:34:11.048930+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFL6YJM4","created_at":"2026-07-05T06:34:11.048930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11683","citing_title":"Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08805","citing_title":"LightAVSeg: Lightweight Audio-Visual Segmentation","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NFL6YJM4IHCIWHBT4B2CPZFXPG","json":"https://pith.science/pith/NFL6YJM4IHCIWHBT4B2CPZFXPG.json","graph_json":"https://pith.science/api/pith-number/NFL6YJM4IHCIWHBT4B2CPZFXPG/graph.json","events_json":"https://pith.science/api/pith-number/NFL6YJM4IHCIWHBT4B2CPZFXPG/events.json","paper":"https://pith.science/paper/NFL6YJM4"},"agent_actions":{"view_html":"https://pith.science/pith/NFL6YJM4IHCIWHBT4B2CPZFXPG","download_json":"https://pith.science/pith/NFL6YJM4IHCIWHBT4B2CPZFXPG.json","view_paper":"https://pith.science/paper/NFL6YJM4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.13236&json=true","fetch_graph":"https://pith.science/api/pith-number/NFL6YJM4IHCIWHBT4B2CPZFXPG/graph.json","fetch_events":"https://pith.science/api/pith-number/NFL6YJM4IHCIWHBT4B2CPZFXPG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFL6YJM4IHCIWHBT4B2CPZFXPG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFL6YJM4IHCIWHBT4B2CPZFXPG/action/storage_attestation","attest_author":"https://pith.science/pith/NFL6YJM4IHCIWHBT4B2CPZFXPG/action/author_attestation","sign_citation":"https://pith.science/pith/NFL6YJM4IHCIWHBT4B2CPZFXPG/action/citation_signature","submit_replication":"https://pith.science/pith/NFL6YJM4IHCIWHBT4B2CPZFXPG/action/replication_record"}},"created_at":"2026-07-05T06:34:11.048930+00:00","updated_at":"2026-07-05T06:34:11.048930+00:00"}