{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EAQ6AXMEGEKSP3SPK2XHHWBW6X","short_pith_number":"pith:EAQ6AXME","schema_version":"1.0","canonical_sha256":"2021e05d84311527ee4f56ae73d836f5c0ee00595554dbe96ae533dbc0336b84","source":{"kind":"arxiv","id":"2310.08303","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Variational Auto-encoder based Audio-Visual Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Jing Zhang, Mochu Xiang, Yiran Zhong, Yuchao Dai, Yuxin Mao","submitted_at":"2023-10-12T13:09:40Z","abstract_excerpt":"We propose an Explicit Conditional Multimodal Variational Auto-Encoder (ECMVAE) for audio-visual segmentation (AVS), aiming to segment sound sources in the video sequence. Existing AVS methods focus on implicit feature fusion strategies, where models are trained to fit the discrete samples in the dataset. With a limited and less diverse dataset, the resulting performance is usually unsatisfactory. In contrast, we address this problem from an effective representation learning perspective, aiming to model the contribution of each modality explicitly. Specifically, we find that audio contains cri"},"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":"2310.08303","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-12T13:09:40Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"8cfa86e1d61a4039720ea16266bb90505dfc0b296d35700df38b1da2bfb6a632","abstract_canon_sha256":"7292d13189af895644110c8ba30a9ca9b42d43d08c1a3e34aed1bde2d275b4e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:13.717106Z","signature_b64":"GYqvcpYqWIdeLtNjNz9VLoXlOELwEFaWEmB84HXy4kPXRvio/ALrbrh/r7zPyqBOVeF4r13k/Uf8QwUJDlcYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2021e05d84311527ee4f56ae73d836f5c0ee00595554dbe96ae533dbc0336b84","last_reissued_at":"2026-07-05T07:00:13.716681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:13.716681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Variational Auto-encoder based Audio-Visual Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Jing Zhang, Mochu Xiang, Yiran Zhong, Yuchao Dai, Yuxin Mao","submitted_at":"2023-10-12T13:09:40Z","abstract_excerpt":"We propose an Explicit Conditional Multimodal Variational Auto-Encoder (ECMVAE) for audio-visual segmentation (AVS), aiming to segment sound sources in the video sequence. Existing AVS methods focus on implicit feature fusion strategies, where models are trained to fit the discrete samples in the dataset. With a limited and less diverse dataset, the resulting performance is usually unsatisfactory. In contrast, we address this problem from an effective representation learning perspective, aiming to model the contribution of each modality explicitly. Specifically, we find that audio contains cri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08303","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/2310.08303/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":"2310.08303","created_at":"2026-07-05T07:00:13.716740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08303v1","created_at":"2026-07-05T07:00:13.716740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08303","created_at":"2026-07-05T07:00:13.716740+00:00"},{"alias_kind":"pith_short_12","alias_value":"EAQ6AXMEGEKS","created_at":"2026-07-05T07:00:13.716740+00:00"},{"alias_kind":"pith_short_16","alias_value":"EAQ6AXMEGEKSP3SP","created_at":"2026-07-05T07:00:13.716740+00:00"},{"alias_kind":"pith_short_8","alias_value":"EAQ6AXME","created_at":"2026-07-05T07:00:13.716740+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/EAQ6AXMEGEKSP3SPK2XHHWBW6X","json":"https://pith.science/pith/EAQ6AXMEGEKSP3SPK2XHHWBW6X.json","graph_json":"https://pith.science/api/pith-number/EAQ6AXMEGEKSP3SPK2XHHWBW6X/graph.json","events_json":"https://pith.science/api/pith-number/EAQ6AXMEGEKSP3SPK2XHHWBW6X/events.json","paper":"https://pith.science/paper/EAQ6AXME"},"agent_actions":{"view_html":"https://pith.science/pith/EAQ6AXMEGEKSP3SPK2XHHWBW6X","download_json":"https://pith.science/pith/EAQ6AXMEGEKSP3SPK2XHHWBW6X.json","view_paper":"https://pith.science/paper/EAQ6AXME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08303&json=true","fetch_graph":"https://pith.science/api/pith-number/EAQ6AXMEGEKSP3SPK2XHHWBW6X/graph.json","fetch_events":"https://pith.science/api/pith-number/EAQ6AXMEGEKSP3SPK2XHHWBW6X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EAQ6AXMEGEKSP3SPK2XHHWBW6X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EAQ6AXMEGEKSP3SPK2XHHWBW6X/action/storage_attestation","attest_author":"https://pith.science/pith/EAQ6AXMEGEKSP3SPK2XHHWBW6X/action/author_attestation","sign_citation":"https://pith.science/pith/EAQ6AXMEGEKSP3SPK2XHHWBW6X/action/citation_signature","submit_replication":"https://pith.science/pith/EAQ6AXMEGEKSP3SPK2XHHWBW6X/action/replication_record"}},"created_at":"2026-07-05T07:00:13.716740+00:00","updated_at":"2026-07-05T07:00:13.716740+00:00"}