{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O4LRIQTEA4KG2Q2UENLAY7D3ID","short_pith_number":"pith:O4LRIQTE","schema_version":"1.0","canonical_sha256":"771714426407146d435423560c7c7b40f3670f0a20f760dd149cf7a5c30dc7df","source":{"kind":"arxiv","id":"2408.07445","version":1},"attestation_state":"computed","paper":{"title":"Modality Invariant Multimodal Learning to Handle Missing Modalities: A Single-Branch Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hassan Sajjad, Karthik Nandakumar, Markus Schedl, Muhammad Haris Khan, Muhammad Haroon Yousaf, Muhammad Saad Saeed, Muhammad Zaigham Zaheer, Shah Nawaz, Tom De Schepper","submitted_at":"2024-08-14T10:32:16Z","abstract_excerpt":"Multimodal networks have demonstrated remarkable performance improvements over their unimodal counterparts. Existing multimodal networks are designed in a multi-branch fashion that, due to the reliance on fusion strategies, exhibit deteriorated performance if one or more modalities are missing. In this work, we propose a modality invariant multimodal learning method, which is less susceptible to the impact of missing modalities. It consists of a single-branch network sharing weights across multiple modalities to learn inter-modality representations to maximize performance as well as robustness"},"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":"2408.07445","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-14T10:32:16Z","cross_cats_sorted":[],"title_canon_sha256":"fddc55407b939ef41bffc67ee6d1081d31949b6456228e50bb5d078da91b138e","abstract_canon_sha256":"12e526aca5a918dc6d379bcf22db38e0053fb07567ca2773274e027fb00f6d77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:25.432674Z","signature_b64":"SwCslbvnJfbsKELB8dAmm2AU9K88aZRbeZcEFrtPF6XCS3HCL+fSWfk0vniItbN/tTSsxryy6aZIa2D/zy+kBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"771714426407146d435423560c7c7b40f3670f0a20f760dd149cf7a5c30dc7df","last_reissued_at":"2026-07-05T08:55:25.432126Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:25.432126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modality Invariant Multimodal Learning to Handle Missing Modalities: A Single-Branch Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hassan Sajjad, Karthik Nandakumar, Markus Schedl, Muhammad Haris Khan, Muhammad Haroon Yousaf, Muhammad Saad Saeed, Muhammad Zaigham Zaheer, Shah Nawaz, Tom De Schepper","submitted_at":"2024-08-14T10:32:16Z","abstract_excerpt":"Multimodal networks have demonstrated remarkable performance improvements over their unimodal counterparts. Existing multimodal networks are designed in a multi-branch fashion that, due to the reliance on fusion strategies, exhibit deteriorated performance if one or more modalities are missing. In this work, we propose a modality invariant multimodal learning method, which is less susceptible to the impact of missing modalities. It consists of a single-branch network sharing weights across multiple modalities to learn inter-modality representations to maximize performance as well as robustness"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07445","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/2408.07445/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":"2408.07445","created_at":"2026-07-05T08:55:25.432196+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.07445v1","created_at":"2026-07-05T08:55:25.432196+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07445","created_at":"2026-07-05T08:55:25.432196+00:00"},{"alias_kind":"pith_short_12","alias_value":"O4LRIQTEA4KG","created_at":"2026-07-05T08:55:25.432196+00:00"},{"alias_kind":"pith_short_16","alias_value":"O4LRIQTEA4KG2Q2U","created_at":"2026-07-05T08:55:25.432196+00:00"},{"alias_kind":"pith_short_8","alias_value":"O4LRIQTE","created_at":"2026-07-05T08:55:25.432196+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11799","citing_title":"SB-BEVFusion: Enhancing the Robustness against Sensor Malfunction and Corruptions","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O4LRIQTEA4KG2Q2UENLAY7D3ID","json":"https://pith.science/pith/O4LRIQTEA4KG2Q2UENLAY7D3ID.json","graph_json":"https://pith.science/api/pith-number/O4LRIQTEA4KG2Q2UENLAY7D3ID/graph.json","events_json":"https://pith.science/api/pith-number/O4LRIQTEA4KG2Q2UENLAY7D3ID/events.json","paper":"https://pith.science/paper/O4LRIQTE"},"agent_actions":{"view_html":"https://pith.science/pith/O4LRIQTEA4KG2Q2UENLAY7D3ID","download_json":"https://pith.science/pith/O4LRIQTEA4KG2Q2UENLAY7D3ID.json","view_paper":"https://pith.science/paper/O4LRIQTE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.07445&json=true","fetch_graph":"https://pith.science/api/pith-number/O4LRIQTEA4KG2Q2UENLAY7D3ID/graph.json","fetch_events":"https://pith.science/api/pith-number/O4LRIQTEA4KG2Q2UENLAY7D3ID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O4LRIQTEA4KG2Q2UENLAY7D3ID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O4LRIQTEA4KG2Q2UENLAY7D3ID/action/storage_attestation","attest_author":"https://pith.science/pith/O4LRIQTEA4KG2Q2UENLAY7D3ID/action/author_attestation","sign_citation":"https://pith.science/pith/O4LRIQTEA4KG2Q2UENLAY7D3ID/action/citation_signature","submit_replication":"https://pith.science/pith/O4LRIQTEA4KG2Q2UENLAY7D3ID/action/replication_record"}},"created_at":"2026-07-05T08:55:25.432196+00:00","updated_at":"2026-07-05T08:55:25.432196+00:00"}