{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:64H5YCYK3QNARIFUUSLDE7NQEO","short_pith_number":"pith:64H5YCYK","schema_version":"1.0","canonical_sha256":"f70fdc0b0adc1a08a0b4a496327db023b9223b05d1bce1e267e489f20b4423f2","source":{"kind":"arxiv","id":"2508.03724","version":1},"attestation_state":"computed","paper":{"title":"From Waveforms to Pixels: A Survey on Audio-Visual Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia Li, Yapeng Tian","submitted_at":"2025-07-29T22:20:51Z","abstract_excerpt":"Audio-Visual Segmentation (AVS) aims to identify and segment sound-producing objects in videos by leveraging both visual and audio modalities. It has emerged as a significant research area in multimodal perception, enabling fine-grained object-level understanding. In this survey, we present a comprehensive overview of the AVS field, covering its problem formulation, benchmark datasets, evaluation metrics, and the progression of methodologies. We analyze a wide range of approaches, including architectures for unimodal and multimodal encoding, key strategies for audio-visual fusion, and various "},"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":"2508.03724","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T22:20:51Z","cross_cats_sorted":[],"title_canon_sha256":"ed8ac4d3ef56156c3c3fccd34498e724ef7c40e2e7e5929b8abe83d14afb1af9","abstract_canon_sha256":"8441bd9e937df4736bd749b2ce3a332cdd64cdd4c720b0008919016a29293ccd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:13.673445Z","signature_b64":"UfCdlB2D/t2P2eVKwa1+z9pTNzXwHaGwI8M+ejCOr2rmf+dY25T/OvhDXV7YavXkoI54WHYzZ27LM7WAgp4ADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f70fdc0b0adc1a08a0b4a496327db023b9223b05d1bce1e267e489f20b4423f2","last_reissued_at":"2026-07-05T11:49:13.672888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:13.672888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Waveforms to Pixels: A Survey on Audio-Visual Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia Li, Yapeng Tian","submitted_at":"2025-07-29T22:20:51Z","abstract_excerpt":"Audio-Visual Segmentation (AVS) aims to identify and segment sound-producing objects in videos by leveraging both visual and audio modalities. It has emerged as a significant research area in multimodal perception, enabling fine-grained object-level understanding. In this survey, we present a comprehensive overview of the AVS field, covering its problem formulation, benchmark datasets, evaluation metrics, and the progression of methodologies. We analyze a wide range of approaches, including architectures for unimodal and multimodal encoding, key strategies for audio-visual fusion, and various "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03724","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/2508.03724/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":"2508.03724","created_at":"2026-07-05T11:49:13.672947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.03724v1","created_at":"2026-07-05T11:49:13.672947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03724","created_at":"2026-07-05T11:49:13.672947+00:00"},{"alias_kind":"pith_short_12","alias_value":"64H5YCYK3QNA","created_at":"2026-07-05T11:49:13.672947+00:00"},{"alias_kind":"pith_short_16","alias_value":"64H5YCYK3QNARIFU","created_at":"2026-07-05T11:49:13.672947+00:00"},{"alias_kind":"pith_short_8","alias_value":"64H5YCYK","created_at":"2026-07-05T11:49:13.672947+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/64H5YCYK3QNARIFUUSLDE7NQEO","json":"https://pith.science/pith/64H5YCYK3QNARIFUUSLDE7NQEO.json","graph_json":"https://pith.science/api/pith-number/64H5YCYK3QNARIFUUSLDE7NQEO/graph.json","events_json":"https://pith.science/api/pith-number/64H5YCYK3QNARIFUUSLDE7NQEO/events.json","paper":"https://pith.science/paper/64H5YCYK"},"agent_actions":{"view_html":"https://pith.science/pith/64H5YCYK3QNARIFUUSLDE7NQEO","download_json":"https://pith.science/pith/64H5YCYK3QNARIFUUSLDE7NQEO.json","view_paper":"https://pith.science/paper/64H5YCYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.03724&json=true","fetch_graph":"https://pith.science/api/pith-number/64H5YCYK3QNARIFUUSLDE7NQEO/graph.json","fetch_events":"https://pith.science/api/pith-number/64H5YCYK3QNARIFUUSLDE7NQEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/64H5YCYK3QNARIFUUSLDE7NQEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/64H5YCYK3QNARIFUUSLDE7NQEO/action/storage_attestation","attest_author":"https://pith.science/pith/64H5YCYK3QNARIFUUSLDE7NQEO/action/author_attestation","sign_citation":"https://pith.science/pith/64H5YCYK3QNARIFUUSLDE7NQEO/action/citation_signature","submit_replication":"https://pith.science/pith/64H5YCYK3QNARIFUUSLDE7NQEO/action/replication_record"}},"created_at":"2026-07-05T11:49:13.672947+00:00","updated_at":"2026-07-05T11:49:13.672947+00:00"}