{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:B66MMGQL2QFUPT4NV6YEA2WNUN","short_pith_number":"pith:B66MMGQL","schema_version":"1.0","canonical_sha256":"0fbcc61a0bd40b47cf8dafb0406acda34f508309bc0a1a54c44162d6e2dd507a","source":{"kind":"arxiv","id":"1702.01992","version":1},"attestation_state":"computed","paper":{"title":"Gated Multimodal Units for Information Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Fabio A. Gonz\\'alez, John Arevalo, Manuel Montes-y-G\\'omez, Thamar Solorio","submitted_at":"2017-02-07T13:05:19Z","abstract_excerpt":"This paper presents a novel model for multimodal learning based on gated neural networks. The Gated Multimodal Unit (GMU) model is intended to be used as an internal unit in a neural network architecture whose purpose is to find an intermediate representation based on a combination of data from different modalities. The GMU learns to decide how modalities influence the activation of the unit using multiplicative gates. It was evaluated on a multilabel scenario for genre classification of movies using the plot and the poster. The GMU improved the macro f-score performance of single-modality app"},"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":"1702.01992","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-02-07T13:05:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d0005e056ffeccce20c1ecfaac771d3ae40f692f9d159dc586ff8f5ff8832966","abstract_canon_sha256":"41ed86112e7210f61116d908901632e17391b78b3fa4c821b98226062503cf5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:10.674207Z","signature_b64":"/QOc/RMRYfq98XY0qe3BdugY4UAs1xHZNQSl3daHpoqk8v1PrVqv/ohsl0pSJ3MPMeigCH5S71P0sF7ld72bCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fbcc61a0bd40b47cf8dafb0406acda34f508309bc0a1a54c44162d6e2dd507a","last_reissued_at":"2026-05-18T00:51:10.673448Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:10.673448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gated Multimodal Units for Information Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Fabio A. Gonz\\'alez, John Arevalo, Manuel Montes-y-G\\'omez, Thamar Solorio","submitted_at":"2017-02-07T13:05:19Z","abstract_excerpt":"This paper presents a novel model for multimodal learning based on gated neural networks. The Gated Multimodal Unit (GMU) model is intended to be used as an internal unit in a neural network architecture whose purpose is to find an intermediate representation based on a combination of data from different modalities. The GMU learns to decide how modalities influence the activation of the unit using multiplicative gates. It was evaluated on a multilabel scenario for genre classification of movies using the plot and the poster. The GMU improved the macro f-score performance of single-modality app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.01992","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":""},"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":"1702.01992","created_at":"2026-05-18T00:51:10.673596+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.01992v1","created_at":"2026-05-18T00:51:10.673596+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.01992","created_at":"2026-05-18T00:51:10.673596+00:00"},{"alias_kind":"pith_short_12","alias_value":"B66MMGQL2QFU","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"B66MMGQL2QFUPT4N","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"B66MMGQL","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":11,"sample":[{"citing_arxiv_id":"1906.10198","citing_title":"Multimodal and Multi-view Models for Emotion Recognition","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"1906.11604","citing_title":"Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2502.03484","citing_title":"Dementia classification from spontaneous speech using wrapper-based feature selection","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21600","citing_title":"ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning","ref_index":204,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21610","citing_title":"AgForce Enables Antigen-conditioned Generative Antibody Design","ref_index":204,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21485","citing_title":"EvoStruct: Bridging Evolutionary and Structural Priors for Antibody CDR Design via Protein Language Model Adaptation","ref_index":204,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16889","citing_title":"Controlling Decision Drift in Multimodal Sentiment Analysis with Missing Modalities","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2511.01831","citing_title":"Routing-Based Continual Learning for Multimodal Large Language Models","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2602.03151","citing_title":"Enhancing Foundation VLM Robustness to Missing Modality: Scalable Diffusion for Bi-directional Feature Restoration","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2603.12221","citing_title":"A Two-Stage Dual-Modality Model for Facial Emotional Expression Recognition","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2603.23916","citing_title":"DecepGPT: Schema-Driven Deception Detection with Multicultural Datasets and Robust Multimodal Learning","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16411","citing_title":"CGCMA: Conditionally-Gated Cross-Modal Attention for Event-Conditioned Asynchronous Fusion","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05950","citing_title":"Lightweight Stylistic Consistency Profiling: Robust Detection of LLM-Generated Textual Content for Multimedia Moderation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01238","citing_title":"EduGage: Methods and Dataset for Sensor-Based Momentary Assessment of Engagement in Self-Guided Video Learning","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07175","citing_title":"Learning Multi-Relational Graph Representations for DNA Methylation-Based Biological Age Estimation","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B66MMGQL2QFUPT4NV6YEA2WNUN","json":"https://pith.science/pith/B66MMGQL2QFUPT4NV6YEA2WNUN.json","graph_json":"https://pith.science/api/pith-number/B66MMGQL2QFUPT4NV6YEA2WNUN/graph.json","events_json":"https://pith.science/api/pith-number/B66MMGQL2QFUPT4NV6YEA2WNUN/events.json","paper":"https://pith.science/paper/B66MMGQL"},"agent_actions":{"view_html":"https://pith.science/pith/B66MMGQL2QFUPT4NV6YEA2WNUN","download_json":"https://pith.science/pith/B66MMGQL2QFUPT4NV6YEA2WNUN.json","view_paper":"https://pith.science/paper/B66MMGQL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.01992&json=true","fetch_graph":"https://pith.science/api/pith-number/B66MMGQL2QFUPT4NV6YEA2WNUN/graph.json","fetch_events":"https://pith.science/api/pith-number/B66MMGQL2QFUPT4NV6YEA2WNUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B66MMGQL2QFUPT4NV6YEA2WNUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B66MMGQL2QFUPT4NV6YEA2WNUN/action/storage_attestation","attest_author":"https://pith.science/pith/B66MMGQL2QFUPT4NV6YEA2WNUN/action/author_attestation","sign_citation":"https://pith.science/pith/B66MMGQL2QFUPT4NV6YEA2WNUN/action/citation_signature","submit_replication":"https://pith.science/pith/B66MMGQL2QFUPT4NV6YEA2WNUN/action/replication_record"}},"created_at":"2026-05-18T00:51:10.673596+00:00","updated_at":"2026-05-18T00:51:10.673596+00:00"}