{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NQGD7KDQ2K3VYPYKC6OZGFUOEP","short_pith_number":"pith:NQGD7KDQ","schema_version":"1.0","canonical_sha256":"6c0c3fa870d2b75c3f0a179d93168e23dcc1d419af3c6155d00d135bce86f731","source":{"kind":"arxiv","id":"2312.14667","version":2},"attestation_state":"computed","paper":{"title":"Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MM","authors_text":"Hanlei Zhang, Hao Li, Hua Xu, Kai Gao, Qianrui Zhou, Xiaohan Zhang, Yifan Wang","submitted_at":"2023-12-22T13:03:23Z","abstract_excerpt":"Multimodal intent recognition aims to leverage diverse modalities such as expressions, body movements and tone of speech to comprehend user's intent, constituting a critical task for understanding human language and behavior in real-world multimodal scenarios. Nevertheless, the majority of existing methods ignore potential correlations among different modalities and own limitations in effectively learning semantic features from nonverbal modalities. In this paper, we introduce a token-level contrastive learning method with modality-aware prompting (TCL-MAP) to address the above challenges. To "},"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":"2312.14667","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2023-12-22T13:03:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"222724cea167602cdda366c1516b6af11e3262eaac491a1f24ac9f2151247bcd","abstract_canon_sha256":"0fde443b6ab0089ab86cd78f1c3196da76523b309b1fa037ffcfa8a1df85d1bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:04.475876Z","signature_b64":"TMc87+3r+z0LeDbL3gsPGLX/3fdNUwHjhwu47JCauzysGFcTQN1QSYgtiO2b8KPyda9IsMAwD+lcRjQwkOorCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c0c3fa870d2b75c3f0a179d93168e23dcc1d419af3c6155d00d135bce86f731","last_reissued_at":"2026-07-05T08:28:04.475484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:04.475484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MM","authors_text":"Hanlei Zhang, Hao Li, Hua Xu, Kai Gao, Qianrui Zhou, Xiaohan Zhang, Yifan Wang","submitted_at":"2023-12-22T13:03:23Z","abstract_excerpt":"Multimodal intent recognition aims to leverage diverse modalities such as expressions, body movements and tone of speech to comprehend user's intent, constituting a critical task for understanding human language and behavior in real-world multimodal scenarios. Nevertheless, the majority of existing methods ignore potential correlations among different modalities and own limitations in effectively learning semantic features from nonverbal modalities. In this paper, we introduce a token-level contrastive learning method with modality-aware prompting (TCL-MAP) to address the above challenges. To "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14667","kind":"arxiv","version":2},"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/2312.14667/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":"2312.14667","created_at":"2026-07-05T08:28:04.475537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.14667v2","created_at":"2026-07-05T08:28:04.475537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14667","created_at":"2026-07-05T08:28:04.475537+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQGD7KDQ2K3V","created_at":"2026-07-05T08:28:04.475537+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQGD7KDQ2K3VYPYK","created_at":"2026-07-05T08:28:04.475537+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQGD7KDQ","created_at":"2026-07-05T08:28:04.475537+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/NQGD7KDQ2K3VYPYKC6OZGFUOEP","json":"https://pith.science/pith/NQGD7KDQ2K3VYPYKC6OZGFUOEP.json","graph_json":"https://pith.science/api/pith-number/NQGD7KDQ2K3VYPYKC6OZGFUOEP/graph.json","events_json":"https://pith.science/api/pith-number/NQGD7KDQ2K3VYPYKC6OZGFUOEP/events.json","paper":"https://pith.science/paper/NQGD7KDQ"},"agent_actions":{"view_html":"https://pith.science/pith/NQGD7KDQ2K3VYPYKC6OZGFUOEP","download_json":"https://pith.science/pith/NQGD7KDQ2K3VYPYKC6OZGFUOEP.json","view_paper":"https://pith.science/paper/NQGD7KDQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.14667&json=true","fetch_graph":"https://pith.science/api/pith-number/NQGD7KDQ2K3VYPYKC6OZGFUOEP/graph.json","fetch_events":"https://pith.science/api/pith-number/NQGD7KDQ2K3VYPYKC6OZGFUOEP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQGD7KDQ2K3VYPYKC6OZGFUOEP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQGD7KDQ2K3VYPYKC6OZGFUOEP/action/storage_attestation","attest_author":"https://pith.science/pith/NQGD7KDQ2K3VYPYKC6OZGFUOEP/action/author_attestation","sign_citation":"https://pith.science/pith/NQGD7KDQ2K3VYPYKC6OZGFUOEP/action/citation_signature","submit_replication":"https://pith.science/pith/NQGD7KDQ2K3VYPYKC6OZGFUOEP/action/replication_record"}},"created_at":"2026-07-05T08:28:04.475537+00:00","updated_at":"2026-07-05T08:28:04.475537+00:00"}