{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JTIM3MXPSQIMTPLSBS62ZGG6AH","short_pith_number":"pith:JTIM3MXP","schema_version":"1.0","canonical_sha256":"4cd0cdb2ef9410c9bd720cbdac98de01e8b67f004153fdbd5e00a13cadf090db","source":{"kind":"arxiv","id":"2407.04587","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Classification via Modal-Aware Interactive Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Qing-Yuan Jiang, Yang Yang, Zhouyang Chi","submitted_at":"2024-07-05T15:32:07Z","abstract_excerpt":"Due to the notorious modality imbalance problem, multimodal learning (MML) leads to the phenomenon of optimization imbalance, thus struggling to achieve satisfactory performance. Recently, some representative methods have been proposed to boost the performance, mainly focusing on adaptive adjusting the optimization of each modality to rebalance the learning speed of dominant and non-dominant modalities. To better facilitate the interaction of model information in multimodal learning, in this paper, we propose a novel multimodal learning method, called modal-aware interactive enhancement (MIE)."},"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":"2407.04587","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-05T15:32:07Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"86b9f4813dde509d691cf8e6e9f551d5b39edd9c536fe907eed68743dd05f6d8","abstract_canon_sha256":"3f9e2ee97c1505d3b12c0e66b2add2e9948489155fe1469bc23d6bf7a9cb44c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:35.990487Z","signature_b64":"h7DvDF2EflzKTBemnHCwQcNJiFIblSTn3eA1CmmiXNn6+61c/oJHk2BKl8LvM1DJppWtwySNwHMKxaUVofVoBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cd0cdb2ef9410c9bd720cbdac98de01e8b67f004153fdbd5e00a13cadf090db","last_reissued_at":"2026-07-05T08:40:35.989995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:35.989995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Classification via Modal-Aware Interactive Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Qing-Yuan Jiang, Yang Yang, Zhouyang Chi","submitted_at":"2024-07-05T15:32:07Z","abstract_excerpt":"Due to the notorious modality imbalance problem, multimodal learning (MML) leads to the phenomenon of optimization imbalance, thus struggling to achieve satisfactory performance. Recently, some representative methods have been proposed to boost the performance, mainly focusing on adaptive adjusting the optimization of each modality to rebalance the learning speed of dominant and non-dominant modalities. To better facilitate the interaction of model information in multimodal learning, in this paper, we propose a novel multimodal learning method, called modal-aware interactive enhancement (MIE)."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04587","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/2407.04587/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":"2407.04587","created_at":"2026-07-05T08:40:35.990049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.04587v1","created_at":"2026-07-05T08:40:35.990049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04587","created_at":"2026-07-05T08:40:35.990049+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTIM3MXPSQIM","created_at":"2026-07-05T08:40:35.990049+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTIM3MXPSQIMTPLS","created_at":"2026-07-05T08:40:35.990049+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTIM3MXP","created_at":"2026-07-05T08:40:35.990049+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.01470","citing_title":"Balance-aware Sequence Sampling Makes Multi-modal Learning Better","ref_index":2022,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JTIM3MXPSQIMTPLSBS62ZGG6AH","json":"https://pith.science/pith/JTIM3MXPSQIMTPLSBS62ZGG6AH.json","graph_json":"https://pith.science/api/pith-number/JTIM3MXPSQIMTPLSBS62ZGG6AH/graph.json","events_json":"https://pith.science/api/pith-number/JTIM3MXPSQIMTPLSBS62ZGG6AH/events.json","paper":"https://pith.science/paper/JTIM3MXP"},"agent_actions":{"view_html":"https://pith.science/pith/JTIM3MXPSQIMTPLSBS62ZGG6AH","download_json":"https://pith.science/pith/JTIM3MXPSQIMTPLSBS62ZGG6AH.json","view_paper":"https://pith.science/paper/JTIM3MXP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.04587&json=true","fetch_graph":"https://pith.science/api/pith-number/JTIM3MXPSQIMTPLSBS62ZGG6AH/graph.json","fetch_events":"https://pith.science/api/pith-number/JTIM3MXPSQIMTPLSBS62ZGG6AH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTIM3MXPSQIMTPLSBS62ZGG6AH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTIM3MXPSQIMTPLSBS62ZGG6AH/action/storage_attestation","attest_author":"https://pith.science/pith/JTIM3MXPSQIMTPLSBS62ZGG6AH/action/author_attestation","sign_citation":"https://pith.science/pith/JTIM3MXPSQIMTPLSBS62ZGG6AH/action/citation_signature","submit_replication":"https://pith.science/pith/JTIM3MXPSQIMTPLSBS62ZGG6AH/action/replication_record"}},"created_at":"2026-07-05T08:40:35.990049+00:00","updated_at":"2026-07-05T08:40:35.990049+00:00"}