{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZFDBQJYK6LGDD3A4BC7BPNNCDH","short_pith_number":"pith:ZFDBQJYK","schema_version":"1.0","canonical_sha256":"c94618270af2cc31ec1c08be17b5a219dcce918f4b1d4b7588762b3734e9abf5","source":{"kind":"arxiv","id":"2407.08130","version":1},"attestation_state":"computed","paper":{"title":"Spiking Tucker Fusion Transformer for Audio-Visual Zero-Shot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Penghong Wang, Ruiqin Xiong, Wenrui Li, Xiaopeng Fan","submitted_at":"2024-07-11T02:01:26Z","abstract_excerpt":"The spiking neural networks (SNNs) that efficiently encode temporal sequences have shown great potential in extracting audio-visual joint feature representations. However, coupling SNNs (binary spike sequences) with transformers (float-point sequences) to jointly explore the temporal-semantic information still facing challenges. In this paper, we introduce a novel Spiking Tucker Fusion Transformer (STFT) for audio-visual zero-shot learning (ZSL). The STFT leverage the temporal and semantic information from different time steps to generate robust representations. The time-step factor (TSF) is i"},"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":"2407.08130","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-07-11T02:01:26Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"9fcf02fdf58e267c8a3b020d17de71ad34703921e1bf25d0e6be365b5d3cf12b","abstract_canon_sha256":"f8f239ef015a9abfa7b2137cef2df5da217b3ce37f97193c3790fe4ff2d00063"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:43.616835Z","signature_b64":"qMhYQc1w4txNfSMKX8nB4dJ25Z1BfLnLdXypMcyDkhWZZAL0/CyDtrKdMt3HGe7vFloLslx+avmMpFbscUfeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c94618270af2cc31ec1c08be17b5a219dcce918f4b1d4b7588762b3734e9abf5","last_reissued_at":"2026-07-05T08:42:43.616297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:43.616297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spiking Tucker Fusion Transformer for Audio-Visual Zero-Shot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Penghong Wang, Ruiqin Xiong, Wenrui Li, Xiaopeng Fan","submitted_at":"2024-07-11T02:01:26Z","abstract_excerpt":"The spiking neural networks (SNNs) that efficiently encode temporal sequences have shown great potential in extracting audio-visual joint feature representations. However, coupling SNNs (binary spike sequences) with transformers (float-point sequences) to jointly explore the temporal-semantic information still facing challenges. In this paper, we introduce a novel Spiking Tucker Fusion Transformer (STFT) for audio-visual zero-shot learning (ZSL). The STFT leverage the temporal and semantic information from different time steps to generate robust representations. The time-step factor (TSF) is i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08130","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/2407.08130/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":"2407.08130","created_at":"2026-07-05T08:42:43.616387+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.08130v1","created_at":"2026-07-05T08:42:43.616387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08130","created_at":"2026-07-05T08:42:43.616387+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZFDBQJYK6LGD","created_at":"2026-07-05T08:42:43.616387+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZFDBQJYK6LGDD3A4","created_at":"2026-07-05T08:42:43.616387+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZFDBQJYK","created_at":"2026-07-05T08:42:43.616387+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/ZFDBQJYK6LGDD3A4BC7BPNNCDH","json":"https://pith.science/pith/ZFDBQJYK6LGDD3A4BC7BPNNCDH.json","graph_json":"https://pith.science/api/pith-number/ZFDBQJYK6LGDD3A4BC7BPNNCDH/graph.json","events_json":"https://pith.science/api/pith-number/ZFDBQJYK6LGDD3A4BC7BPNNCDH/events.json","paper":"https://pith.science/paper/ZFDBQJYK"},"agent_actions":{"view_html":"https://pith.science/pith/ZFDBQJYK6LGDD3A4BC7BPNNCDH","download_json":"https://pith.science/pith/ZFDBQJYK6LGDD3A4BC7BPNNCDH.json","view_paper":"https://pith.science/paper/ZFDBQJYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.08130&json=true","fetch_graph":"https://pith.science/api/pith-number/ZFDBQJYK6LGDD3A4BC7BPNNCDH/graph.json","fetch_events":"https://pith.science/api/pith-number/ZFDBQJYK6LGDD3A4BC7BPNNCDH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZFDBQJYK6LGDD3A4BC7BPNNCDH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZFDBQJYK6LGDD3A4BC7BPNNCDH/action/storage_attestation","attest_author":"https://pith.science/pith/ZFDBQJYK6LGDD3A4BC7BPNNCDH/action/author_attestation","sign_citation":"https://pith.science/pith/ZFDBQJYK6LGDD3A4BC7BPNNCDH/action/citation_signature","submit_replication":"https://pith.science/pith/ZFDBQJYK6LGDD3A4BC7BPNNCDH/action/replication_record"}},"created_at":"2026-07-05T08:42:43.616387+00:00","updated_at":"2026-07-05T08:42:43.616387+00:00"}