{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SBRJRHTX573HUOLIHSZGLHSVIW","short_pith_number":"pith:SBRJRHTX","schema_version":"1.0","canonical_sha256":"9062989e77eff67a39683cb2659e55459f6460a0b6833647d0544f7de1208389","source":{"kind":"arxiv","id":"2311.10170","version":1},"attestation_state":"computed","paper":{"title":"Improving Unimodal Inference with Multimodal Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexandros Iosifidis, Kateryna Chumachenko, Moncef Gabbouj","submitted_at":"2023-11-16T19:53:35Z","abstract_excerpt":"This paper proposes an approach for improving performance of unimodal models with multimodal training. Our approach involves a multi-branch architecture that incorporates unimodal models with a multimodal transformer-based branch. By co-training these branches, the stronger multimodal branch can transfer its knowledge to the weaker unimodal branches through a multi-task objective, thereby improving the performance of the resulting unimodal models. We evaluate our approach on tasks of dynamic hand gesture recognition based on RGB and Depth, audiovisual emotion recognition based on speech and fa"},"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":"2311.10170","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-16T19:53:35Z","cross_cats_sorted":[],"title_canon_sha256":"86c926377352b942e6c8633c17ec6ff5314e501cb7cd1b60c6f08af90719905e","abstract_canon_sha256":"a1b289b2ed9fac17705a5517dece8bb72825f2c837e39765f96f904206b10571"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:47.832880Z","signature_b64":"7C1CmXtOTGNKkB4euGbarcMkdsenNYPJk/sH4Q8+xa6KXipWPNTxR+8TRu4WQjHRvqAveNa7pPxqNUjxYyTACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9062989e77eff67a39683cb2659e55459f6460a0b6833647d0544f7de1208389","last_reissued_at":"2026-07-05T07:13:47.832438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:47.832438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Unimodal Inference with Multimodal Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexandros Iosifidis, Kateryna Chumachenko, Moncef Gabbouj","submitted_at":"2023-11-16T19:53:35Z","abstract_excerpt":"This paper proposes an approach for improving performance of unimodal models with multimodal training. Our approach involves a multi-branch architecture that incorporates unimodal models with a multimodal transformer-based branch. By co-training these branches, the stronger multimodal branch can transfer its knowledge to the weaker unimodal branches through a multi-task objective, thereby improving the performance of the resulting unimodal models. We evaluate our approach on tasks of dynamic hand gesture recognition based on RGB and Depth, audiovisual emotion recognition based on speech and fa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10170","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/2311.10170/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":"2311.10170","created_at":"2026-07-05T07:13:47.832491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.10170v1","created_at":"2026-07-05T07:13:47.832491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10170","created_at":"2026-07-05T07:13:47.832491+00:00"},{"alias_kind":"pith_short_12","alias_value":"SBRJRHTX573H","created_at":"2026-07-05T07:13:47.832491+00:00"},{"alias_kind":"pith_short_16","alias_value":"SBRJRHTX573HUOLI","created_at":"2026-07-05T07:13:47.832491+00:00"},{"alias_kind":"pith_short_8","alias_value":"SBRJRHTX","created_at":"2026-07-05T07:13:47.832491+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/SBRJRHTX573HUOLIHSZGLHSVIW","json":"https://pith.science/pith/SBRJRHTX573HUOLIHSZGLHSVIW.json","graph_json":"https://pith.science/api/pith-number/SBRJRHTX573HUOLIHSZGLHSVIW/graph.json","events_json":"https://pith.science/api/pith-number/SBRJRHTX573HUOLIHSZGLHSVIW/events.json","paper":"https://pith.science/paper/SBRJRHTX"},"agent_actions":{"view_html":"https://pith.science/pith/SBRJRHTX573HUOLIHSZGLHSVIW","download_json":"https://pith.science/pith/SBRJRHTX573HUOLIHSZGLHSVIW.json","view_paper":"https://pith.science/paper/SBRJRHTX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.10170&json=true","fetch_graph":"https://pith.science/api/pith-number/SBRJRHTX573HUOLIHSZGLHSVIW/graph.json","fetch_events":"https://pith.science/api/pith-number/SBRJRHTX573HUOLIHSZGLHSVIW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SBRJRHTX573HUOLIHSZGLHSVIW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SBRJRHTX573HUOLIHSZGLHSVIW/action/storage_attestation","attest_author":"https://pith.science/pith/SBRJRHTX573HUOLIHSZGLHSVIW/action/author_attestation","sign_citation":"https://pith.science/pith/SBRJRHTX573HUOLIHSZGLHSVIW/action/citation_signature","submit_replication":"https://pith.science/pith/SBRJRHTX573HUOLIHSZGLHSVIW/action/replication_record"}},"created_at":"2026-07-05T07:13:47.832491+00:00","updated_at":"2026-07-05T07:13:47.832491+00:00"}