{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HTNRBRJ3VSYF2MV6S64CSDXYOV","short_pith_number":"pith:HTNRBRJ3","schema_version":"1.0","canonical_sha256":"3cdb10c53bacb05d32be97b8290ef87544f1a38fb432e56371eaf46000cff5f7","source":{"kind":"arxiv","id":"1707.00683","version":3},"attestation_state":"computed","paper":{"title":"Modulating early visual processing by language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aaron Courville, Florian Strub, Harm de Vries, Hugo Larochelle, J\\'er\\'emie Mary, Olivier Pietquin","submitted_at":"2017-07-02T04:06:01Z","abstract_excerpt":"It is commonly assumed that language refers to high-level visual concepts while leaving low-level visual processing unaffected. This view dominates the current literature in computational models for language-vision tasks, where visual and linguistic input are mostly processed independently before being fused into a single representation. In this paper, we deviate from this classic pipeline and propose to modulate the \\emph{entire visual processing} by linguistic input. Specifically, we condition the batch normalization parameters of a pretrained residual network (ResNet) on a language embeddin"},"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":"1707.00683","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-02T04:06:01Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"36543fb6c793ef8030bb9cfcef506329513fcd3f888a1c45cc7276f1059a092d","abstract_canon_sha256":"4c432d2a908ffc98cf8cdb51b909ffc9d3811953587a66c7727f25e2b98f2570"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:46.324183Z","signature_b64":"TYRAmBqVGojOSyQhrYq9eC6Fpig8Uq5NCoJmkPkCARz/YZMXbhqH6NIp2FqjozvcCafQAu5fTNDBoJjzu+ApAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cdb10c53bacb05d32be97b8290ef87544f1a38fb432e56371eaf46000cff5f7","last_reissued_at":"2026-05-18T00:27:46.323747Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:46.323747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modulating early visual processing by language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aaron Courville, Florian Strub, Harm de Vries, Hugo Larochelle, J\\'er\\'emie Mary, Olivier Pietquin","submitted_at":"2017-07-02T04:06:01Z","abstract_excerpt":"It is commonly assumed that language refers to high-level visual concepts while leaving low-level visual processing unaffected. This view dominates the current literature in computational models for language-vision tasks, where visual and linguistic input are mostly processed independently before being fused into a single representation. In this paper, we deviate from this classic pipeline and propose to modulate the \\emph{entire visual processing} by linguistic input. Specifically, we condition the batch normalization parameters of a pretrained residual network (ResNet) on a language embeddin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.00683","kind":"arxiv","version":3},"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":"1707.00683","created_at":"2026-05-18T00:27:46.323812+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.00683v3","created_at":"2026-05-18T00:27:46.323812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.00683","created_at":"2026-05-18T00:27:46.323812+00:00"},{"alias_kind":"pith_short_12","alias_value":"HTNRBRJ3VSYF","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"HTNRBRJ3VSYF2MV6","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"HTNRBRJ3","created_at":"2026-05-18T12:31:18.294218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.11080","citing_title":"AGAN: Towards Automated Design of Generative Adversarial Networks","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2105.05233","citing_title":"Diffusion Models Beat GANs on Image Synthesis","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HTNRBRJ3VSYF2MV6S64CSDXYOV","json":"https://pith.science/pith/HTNRBRJ3VSYF2MV6S64CSDXYOV.json","graph_json":"https://pith.science/api/pith-number/HTNRBRJ3VSYF2MV6S64CSDXYOV/graph.json","events_json":"https://pith.science/api/pith-number/HTNRBRJ3VSYF2MV6S64CSDXYOV/events.json","paper":"https://pith.science/paper/HTNRBRJ3"},"agent_actions":{"view_html":"https://pith.science/pith/HTNRBRJ3VSYF2MV6S64CSDXYOV","download_json":"https://pith.science/pith/HTNRBRJ3VSYF2MV6S64CSDXYOV.json","view_paper":"https://pith.science/paper/HTNRBRJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.00683&json=true","fetch_graph":"https://pith.science/api/pith-number/HTNRBRJ3VSYF2MV6S64CSDXYOV/graph.json","fetch_events":"https://pith.science/api/pith-number/HTNRBRJ3VSYF2MV6S64CSDXYOV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HTNRBRJ3VSYF2MV6S64CSDXYOV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HTNRBRJ3VSYF2MV6S64CSDXYOV/action/storage_attestation","attest_author":"https://pith.science/pith/HTNRBRJ3VSYF2MV6S64CSDXYOV/action/author_attestation","sign_citation":"https://pith.science/pith/HTNRBRJ3VSYF2MV6S64CSDXYOV/action/citation_signature","submit_replication":"https://pith.science/pith/HTNRBRJ3VSYF2MV6S64CSDXYOV/action/replication_record"}},"created_at":"2026-05-18T00:27:46.323812+00:00","updated_at":"2026-05-18T00:27:46.323812+00:00"}