{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GJ4PHVIFOQYNDYJLGQOPYHOWU2","short_pith_number":"pith:GJ4PHVIF","schema_version":"1.0","canonical_sha256":"3278f3d5057430d1e12b341cfc1dd6a698d22e726444853c4a3dbb47b3f09e66","source":{"kind":"arxiv","id":"1903.02930","version":1},"attestation_state":"computed","paper":{"title":"Neural Language Modeling with Visual Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antonios Anastasopoulos, Hank Liao, Shankar Kumar","submitted_at":"2019-03-07T14:20:01Z","abstract_excerpt":"Multimodal language models attempt to incorporate non-linguistic features for the language modeling task. In this work, we extend a standard recurrent neural network (RNN) language model with features derived from videos. We train our models on data that is two orders-of-magnitude bigger than datasets used in prior work. We perform a thorough exploration of model architectures for combining visual and text features. Our experiments on two corpora (YouCookII and 20bn-something-something-v2) show that the best performing architecture consists of middle fusion of visual and text features, yieldin"},"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":"1903.02930","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-07T14:20:01Z","cross_cats_sorted":[],"title_canon_sha256":"4353531b7b5d4c541e254b401525e7e55644f27d51720f627e40edc00c01ec43","abstract_canon_sha256":"82bae6067f23542825aeaa7fb4aa7a4bcd0d4fc9a685abffdeee57ce70cd974a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:50.707877Z","signature_b64":"gyEOJ7UaD2SHDOYiscw0i+uJhBDgeA3QUT0DOGwMsJDMGxFTzlSu3ChDoZaxq/c1j3PL+GSVAmWBxl2A66qfDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3278f3d5057430d1e12b341cfc1dd6a698d22e726444853c4a3dbb47b3f09e66","last_reissued_at":"2026-05-17T23:51:50.707162Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:50.707162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Language Modeling with Visual Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antonios Anastasopoulos, Hank Liao, Shankar Kumar","submitted_at":"2019-03-07T14:20:01Z","abstract_excerpt":"Multimodal language models attempt to incorporate non-linguistic features for the language modeling task. In this work, we extend a standard recurrent neural network (RNN) language model with features derived from videos. We train our models on data that is two orders-of-magnitude bigger than datasets used in prior work. We perform a thorough exploration of model architectures for combining visual and text features. Our experiments on two corpora (YouCookII and 20bn-something-something-v2) show that the best performing architecture consists of middle fusion of visual and text features, yieldin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.02930","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":"1903.02930","created_at":"2026-05-17T23:51:50.707275+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.02930v1","created_at":"2026-05-17T23:51:50.707275+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.02930","created_at":"2026-05-17T23:51:50.707275+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJ4PHVIFOQYN","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJ4PHVIFOQYNDYJL","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJ4PHVIF","created_at":"2026-05-18T12:33:18.533446+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/GJ4PHVIFOQYNDYJLGQOPYHOWU2","json":"https://pith.science/pith/GJ4PHVIFOQYNDYJLGQOPYHOWU2.json","graph_json":"https://pith.science/api/pith-number/GJ4PHVIFOQYNDYJLGQOPYHOWU2/graph.json","events_json":"https://pith.science/api/pith-number/GJ4PHVIFOQYNDYJLGQOPYHOWU2/events.json","paper":"https://pith.science/paper/GJ4PHVIF"},"agent_actions":{"view_html":"https://pith.science/pith/GJ4PHVIFOQYNDYJLGQOPYHOWU2","download_json":"https://pith.science/pith/GJ4PHVIFOQYNDYJLGQOPYHOWU2.json","view_paper":"https://pith.science/paper/GJ4PHVIF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.02930&json=true","fetch_graph":"https://pith.science/api/pith-number/GJ4PHVIFOQYNDYJLGQOPYHOWU2/graph.json","fetch_events":"https://pith.science/api/pith-number/GJ4PHVIFOQYNDYJLGQOPYHOWU2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJ4PHVIFOQYNDYJLGQOPYHOWU2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJ4PHVIFOQYNDYJLGQOPYHOWU2/action/storage_attestation","attest_author":"https://pith.science/pith/GJ4PHVIFOQYNDYJLGQOPYHOWU2/action/author_attestation","sign_citation":"https://pith.science/pith/GJ4PHVIFOQYNDYJLGQOPYHOWU2/action/citation_signature","submit_replication":"https://pith.science/pith/GJ4PHVIFOQYNDYJLGQOPYHOWU2/action/replication_record"}},"created_at":"2026-05-17T23:51:50.707275+00:00","updated_at":"2026-05-17T23:51:50.707275+00:00"}