{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QGNIFNWSPSHHOM35RCYSPCUR5J","short_pith_number":"pith:QGNIFNWS","schema_version":"1.0","canonical_sha256":"819a82b6d27c8e77337d88b1278a91ea79aff6bf8cb35a1fa97bb58fae84c190","source":{"kind":"arxiv","id":"2506.10011","version":1},"attestation_state":"computed","paper":{"title":"WDMIR: Wavelet-Driven Multimodal Intent Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","eess.SP"],"primary_cat":"cs.MM","authors_text":"Junyu Lu, Kai Zhang, Linbo Zhu, Qi Liu, Weiyin Gong, Xinjie Sun, Yanghai Zhang","submitted_at":"2025-05-27T03:32:45Z","abstract_excerpt":"Multimodal intent recognition (MIR) seeks to accurately interpret user intentions by integrating verbal and non-verbal information across video, audio and text modalities. While existing approaches prioritize text analysis, they often overlook the rich semantic content embedded in non-verbal cues. This paper presents a novel Wavelet-Driven Multimodal Intent Recognition(WDMIR) framework that enhances intent understanding through frequency-domain analysis of non-verbal information. To be more specific, we propose: (1) a wavelet-driven fusion module that performs synchronized decomposition and in"},"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":"2506.10011","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-27T03:32:45Z","cross_cats_sorted":["cs.AI","cs.CV","eess.SP"],"title_canon_sha256":"8de112846a2eb95abd58080d9dd417ed2f9cc1e51da03553660f5e76dcba59bc","abstract_canon_sha256":"ac6513de2fb55dee5c1a58c07b99219ab46d5c76a4d091e63a0d79fa24a71706"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:38.570788Z","signature_b64":"wxxHSezIHOupW26H9vM4AC/bbDpkJn0ag5Qj+ckkshn3cU3Q00ZDAfn2YXU1vnIk8zZUBVpK4/bbr34LYi4BBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"819a82b6d27c8e77337d88b1278a91ea79aff6bf8cb35a1fa97bb58fae84c190","last_reissued_at":"2026-07-05T11:20:38.570331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:38.570331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WDMIR: Wavelet-Driven Multimodal Intent Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","eess.SP"],"primary_cat":"cs.MM","authors_text":"Junyu Lu, Kai Zhang, Linbo Zhu, Qi Liu, Weiyin Gong, Xinjie Sun, Yanghai Zhang","submitted_at":"2025-05-27T03:32:45Z","abstract_excerpt":"Multimodal intent recognition (MIR) seeks to accurately interpret user intentions by integrating verbal and non-verbal information across video, audio and text modalities. While existing approaches prioritize text analysis, they often overlook the rich semantic content embedded in non-verbal cues. This paper presents a novel Wavelet-Driven Multimodal Intent Recognition(WDMIR) framework that enhances intent understanding through frequency-domain analysis of non-verbal information. To be more specific, we propose: (1) a wavelet-driven fusion module that performs synchronized decomposition and in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10011","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/2506.10011/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":"2506.10011","created_at":"2026-07-05T11:20:38.570388+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10011v1","created_at":"2026-07-05T11:20:38.570388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10011","created_at":"2026-07-05T11:20:38.570388+00:00"},{"alias_kind":"pith_short_12","alias_value":"QGNIFNWSPSHH","created_at":"2026-07-05T11:20:38.570388+00:00"},{"alias_kind":"pith_short_16","alias_value":"QGNIFNWSPSHHOM35","created_at":"2026-07-05T11:20:38.570388+00:00"},{"alias_kind":"pith_short_8","alias_value":"QGNIFNWS","created_at":"2026-07-05T11:20:38.570388+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/QGNIFNWSPSHHOM35RCYSPCUR5J","json":"https://pith.science/pith/QGNIFNWSPSHHOM35RCYSPCUR5J.json","graph_json":"https://pith.science/api/pith-number/QGNIFNWSPSHHOM35RCYSPCUR5J/graph.json","events_json":"https://pith.science/api/pith-number/QGNIFNWSPSHHOM35RCYSPCUR5J/events.json","paper":"https://pith.science/paper/QGNIFNWS"},"agent_actions":{"view_html":"https://pith.science/pith/QGNIFNWSPSHHOM35RCYSPCUR5J","download_json":"https://pith.science/pith/QGNIFNWSPSHHOM35RCYSPCUR5J.json","view_paper":"https://pith.science/paper/QGNIFNWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10011&json=true","fetch_graph":"https://pith.science/api/pith-number/QGNIFNWSPSHHOM35RCYSPCUR5J/graph.json","fetch_events":"https://pith.science/api/pith-number/QGNIFNWSPSHHOM35RCYSPCUR5J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QGNIFNWSPSHHOM35RCYSPCUR5J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QGNIFNWSPSHHOM35RCYSPCUR5J/action/storage_attestation","attest_author":"https://pith.science/pith/QGNIFNWSPSHHOM35RCYSPCUR5J/action/author_attestation","sign_citation":"https://pith.science/pith/QGNIFNWSPSHHOM35RCYSPCUR5J/action/citation_signature","submit_replication":"https://pith.science/pith/QGNIFNWSPSHHOM35RCYSPCUR5J/action/replication_record"}},"created_at":"2026-07-05T11:20:38.570388+00:00","updated_at":"2026-07-05T11:20:38.570388+00:00"}