{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q22ILDXWASF5CRX7GYWFHSNPWI","short_pith_number":"pith:Q22ILDXW","schema_version":"1.0","canonical_sha256":"86b4858ef6048bd146ff362c53c9afb232c26bd6934a1657c8087d585b51c1c6","source":{"kind":"arxiv","id":"2403.11074","version":1},"attestation_state":"computed","paper":{"title":"Audio-Visual Segmentation via Unlabeled Frame Exploitation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Chen Ju, Fei Zhang, Jinxiang Liu, Yanfeng Wang, Ya Zhang, Yikun Liu","submitted_at":"2024-03-17T03:45:14Z","abstract_excerpt":"Audio-visual segmentation (AVS) aims to segment the sounding objects in video frames. Although great progress has been witnessed, we experimentally reveal that current methods reach marginal performance gain within the use of the unlabeled frames, leading to the underutilization issue. To fully explore the potential of the unlabeled frames for AVS, we explicitly divide them into two categories based on their temporal characteristics, i.e., neighboring frame (NF) and distant frame (DF). NFs, temporally adjacent to the labeled frame, often contain rich motion information that assists in the accu"},"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":"2403.11074","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-17T03:45:14Z","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"05e9c317d74f75a99564f640305e0205e3a150df99c37a5cf66aace1f108ede6","abstract_canon_sha256":"b164d881721b14ef24ff0ee8db0ffce33862a5f0aabd654c2793dbec8484dd1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:10.946354Z","signature_b64":"D+LYxIog+X2N/k+Xi06AFOJ+jX3BprJvbeez1Q3nZCuHHY9xTE2DlSiWJCKX/5HZwFnrb0cwTVo0/HtSiSj9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86b4858ef6048bd146ff362c53c9afb232c26bd6934a1657c8087d585b51c1c6","last_reissued_at":"2026-07-05T07:57:10.945977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:10.945977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Visual Segmentation via Unlabeled Frame Exploitation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Chen Ju, Fei Zhang, Jinxiang Liu, Yanfeng Wang, Ya Zhang, Yikun Liu","submitted_at":"2024-03-17T03:45:14Z","abstract_excerpt":"Audio-visual segmentation (AVS) aims to segment the sounding objects in video frames. Although great progress has been witnessed, we experimentally reveal that current methods reach marginal performance gain within the use of the unlabeled frames, leading to the underutilization issue. To fully explore the potential of the unlabeled frames for AVS, we explicitly divide them into two categories based on their temporal characteristics, i.e., neighboring frame (NF) and distant frame (DF). NFs, temporally adjacent to the labeled frame, often contain rich motion information that assists in the accu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11074","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/2403.11074/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":"2403.11074","created_at":"2026-07-05T07:57:10.946036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11074v1","created_at":"2026-07-05T07:57:10.946036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11074","created_at":"2026-07-05T07:57:10.946036+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q22ILDXWASF5","created_at":"2026-07-05T07:57:10.946036+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q22ILDXWASF5CRX7","created_at":"2026-07-05T07:57:10.946036+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q22ILDXW","created_at":"2026-07-05T07:57:10.946036+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/Q22ILDXWASF5CRX7GYWFHSNPWI","json":"https://pith.science/pith/Q22ILDXWASF5CRX7GYWFHSNPWI.json","graph_json":"https://pith.science/api/pith-number/Q22ILDXWASF5CRX7GYWFHSNPWI/graph.json","events_json":"https://pith.science/api/pith-number/Q22ILDXWASF5CRX7GYWFHSNPWI/events.json","paper":"https://pith.science/paper/Q22ILDXW"},"agent_actions":{"view_html":"https://pith.science/pith/Q22ILDXWASF5CRX7GYWFHSNPWI","download_json":"https://pith.science/pith/Q22ILDXWASF5CRX7GYWFHSNPWI.json","view_paper":"https://pith.science/paper/Q22ILDXW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11074&json=true","fetch_graph":"https://pith.science/api/pith-number/Q22ILDXWASF5CRX7GYWFHSNPWI/graph.json","fetch_events":"https://pith.science/api/pith-number/Q22ILDXWASF5CRX7GYWFHSNPWI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q22ILDXWASF5CRX7GYWFHSNPWI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q22ILDXWASF5CRX7GYWFHSNPWI/action/storage_attestation","attest_author":"https://pith.science/pith/Q22ILDXWASF5CRX7GYWFHSNPWI/action/author_attestation","sign_citation":"https://pith.science/pith/Q22ILDXWASF5CRX7GYWFHSNPWI/action/citation_signature","submit_replication":"https://pith.science/pith/Q22ILDXWASF5CRX7GYWFHSNPWI/action/replication_record"}},"created_at":"2026-07-05T07:57:10.946036+00:00","updated_at":"2026-07-05T07:57:10.946036+00:00"}