{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PJT3ZOTLY5KVMU24IQ232EEQ3G","short_pith_number":"pith:PJT3ZOTL","schema_version":"1.0","canonical_sha256":"7a67bcba6bc75556535c4435bd1090d98277fdc6a32e1f7ebec978fbfd8ba6c4","source":{"kind":"arxiv","id":"2407.11820","version":3},"attestation_state":"computed","paper":{"title":"Stepping Stones: A Progressive Training Strategy for Audio-Visual Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Di Hu, Juncheng Ma, Peiwen Sun, Yaoting Wang","submitted_at":"2024-07-16T15:08:30Z","abstract_excerpt":"Audio-Visual Segmentation (AVS) aims to achieve pixel-level localization of sound sources in videos, while Audio-Visual Semantic Segmentation (AVSS), as an extension of AVS, further pursues semantic understanding of audio-visual scenes. However, since the AVSS task requires the establishment of audio-visual correspondence and semantic understanding simultaneously, we observe that previous methods have struggled to handle this mashup of objectives in end-to-end training, resulting in insufficient learning and sub-optimization. Therefore, we propose a two-stage training strategy called \\textit{S"},"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":"2407.11820","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T15:08:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"436c1a598905d0fc0854c58264d530aa4e25d4ffce95ddc5d59df3526874bede","abstract_canon_sha256":"c0662de7c7cb1043210c7c0cab7e713ceb6cdae89797e3e7433f1597b439a0f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:07.225807Z","signature_b64":"iPvGsHB9PJn10a/h4G/pRj3vQrL9SrwcCoqoPX65tuHvVPFvUtroZQ5+t53VTUd8y9raRV5MOUI7LtG5e5/mCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a67bcba6bc75556535c4435bd1090d98277fdc6a32e1f7ebec978fbfd8ba6c4","last_reissued_at":"2026-07-05T09:06:07.225326Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:07.225326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stepping Stones: A Progressive Training Strategy for Audio-Visual Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Di Hu, Juncheng Ma, Peiwen Sun, Yaoting Wang","submitted_at":"2024-07-16T15:08:30Z","abstract_excerpt":"Audio-Visual Segmentation (AVS) aims to achieve pixel-level localization of sound sources in videos, while Audio-Visual Semantic Segmentation (AVSS), as an extension of AVS, further pursues semantic understanding of audio-visual scenes. However, since the AVSS task requires the establishment of audio-visual correspondence and semantic understanding simultaneously, we observe that previous methods have struggled to handle this mashup of objectives in end-to-end training, resulting in insufficient learning and sub-optimization. Therefore, we propose a two-stage training strategy called \\textit{S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11820","kind":"arxiv","version":3},"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/2407.11820/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":"2407.11820","created_at":"2026-07-05T09:06:07.225385+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11820v3","created_at":"2026-07-05T09:06:07.225385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11820","created_at":"2026-07-05T09:06:07.225385+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJT3ZOTLY5KV","created_at":"2026-07-05T09:06:07.225385+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJT3ZOTLY5KVMU24","created_at":"2026-07-05T09:06:07.225385+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJT3ZOTL","created_at":"2026-07-05T09:06:07.225385+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00358","citing_title":"Do Audio-Visual Segmentation Models Truly Segment Sounding Objects?","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJT3ZOTLY5KVMU24IQ232EEQ3G","json":"https://pith.science/pith/PJT3ZOTLY5KVMU24IQ232EEQ3G.json","graph_json":"https://pith.science/api/pith-number/PJT3ZOTLY5KVMU24IQ232EEQ3G/graph.json","events_json":"https://pith.science/api/pith-number/PJT3ZOTLY5KVMU24IQ232EEQ3G/events.json","paper":"https://pith.science/paper/PJT3ZOTL"},"agent_actions":{"view_html":"https://pith.science/pith/PJT3ZOTLY5KVMU24IQ232EEQ3G","download_json":"https://pith.science/pith/PJT3ZOTLY5KVMU24IQ232EEQ3G.json","view_paper":"https://pith.science/paper/PJT3ZOTL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11820&json=true","fetch_graph":"https://pith.science/api/pith-number/PJT3ZOTLY5KVMU24IQ232EEQ3G/graph.json","fetch_events":"https://pith.science/api/pith-number/PJT3ZOTLY5KVMU24IQ232EEQ3G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJT3ZOTLY5KVMU24IQ232EEQ3G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJT3ZOTLY5KVMU24IQ232EEQ3G/action/storage_attestation","attest_author":"https://pith.science/pith/PJT3ZOTLY5KVMU24IQ232EEQ3G/action/author_attestation","sign_citation":"https://pith.science/pith/PJT3ZOTLY5KVMU24IQ232EEQ3G/action/citation_signature","submit_replication":"https://pith.science/pith/PJT3ZOTLY5KVMU24IQ232EEQ3G/action/replication_record"}},"created_at":"2026-07-05T09:06:07.225385+00:00","updated_at":"2026-07-05T09:06:07.225385+00:00"}