{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:P4XSLRPSVELXSL3XEYGR3RYHVY","short_pith_number":"pith:P4XSLRPS","schema_version":"1.0","canonical_sha256":"7f2f25c5f2a917792f77260d1dc707ae1bf223c8ca38a420ee8a1ba22438dcc6","source":{"kind":"arxiv","id":"1705.08631","version":1},"attestation_state":"computed","paper":{"title":"Self-supervised learning of visual features through embedding images into text topic spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"C.V. Jawahar, Dimosthenis Karatzas, Lluis Gomez, Mar\\c{c}al Rusi\\~nol, Yash Patel","submitted_at":"2017-05-24T06:59:30Z","abstract_excerpt":"End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible. In this paper we present a method that is able to take advantage of freely available multi-modal content to train computer vision algorithms without human supervision. We put forward the idea of performing self-supervised learning of visual features by mining a large scale corpus of multi-modal (text and image) documents. We show that discriminative visual features can be learnt efficiently by training a CNN to predict the seman"},"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":"1705.08631","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-24T06:59:30Z","cross_cats_sorted":[],"title_canon_sha256":"a8160deb93f602e55793a8117093f65bd3dfbecb648917388dee3ef18a80d7e5","abstract_canon_sha256":"5b2f074943a8277b86ddb54d80d97881e8f167655271cd4131e8bb455b0a4628"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:44.715455Z","signature_b64":"I12Bc2Gtnm+nm40S2/weBt3nkUFxsbsexu0mnYRh7qCOT1LcWinNnVNtM4rvmNPZMuIPi/mOuZSnPnwSW/djAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f2f25c5f2a917792f77260d1dc707ae1bf223c8ca38a420ee8a1ba22438dcc6","last_reissued_at":"2026-05-18T00:43:44.714758Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:44.714758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised learning of visual features through embedding images into text topic spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"C.V. Jawahar, Dimosthenis Karatzas, Lluis Gomez, Mar\\c{c}al Rusi\\~nol, Yash Patel","submitted_at":"2017-05-24T06:59:30Z","abstract_excerpt":"End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible. In this paper we present a method that is able to take advantage of freely available multi-modal content to train computer vision algorithms without human supervision. We put forward the idea of performing self-supervised learning of visual features by mining a large scale corpus of multi-modal (text and image) documents. We show that discriminative visual features can be learnt efficiently by training a CNN to predict the seman"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08631","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":"1705.08631","created_at":"2026-05-18T00:43:44.714885+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.08631v1","created_at":"2026-05-18T00:43:44.714885+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08631","created_at":"2026-05-18T00:43:44.714885+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4XSLRPSVELX","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4XSLRPSVELXSL3X","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4XSLRPS","created_at":"2026-05-18T12:31:37.085036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.11879","citing_title":"Multi-task Self-Supervised Learning for Human Activity Detection","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P4XSLRPSVELXSL3XEYGR3RYHVY","json":"https://pith.science/pith/P4XSLRPSVELXSL3XEYGR3RYHVY.json","graph_json":"https://pith.science/api/pith-number/P4XSLRPSVELXSL3XEYGR3RYHVY/graph.json","events_json":"https://pith.science/api/pith-number/P4XSLRPSVELXSL3XEYGR3RYHVY/events.json","paper":"https://pith.science/paper/P4XSLRPS"},"agent_actions":{"view_html":"https://pith.science/pith/P4XSLRPSVELXSL3XEYGR3RYHVY","download_json":"https://pith.science/pith/P4XSLRPSVELXSL3XEYGR3RYHVY.json","view_paper":"https://pith.science/paper/P4XSLRPS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.08631&json=true","fetch_graph":"https://pith.science/api/pith-number/P4XSLRPSVELXSL3XEYGR3RYHVY/graph.json","fetch_events":"https://pith.science/api/pith-number/P4XSLRPSVELXSL3XEYGR3RYHVY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4XSLRPSVELXSL3XEYGR3RYHVY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4XSLRPSVELXSL3XEYGR3RYHVY/action/storage_attestation","attest_author":"https://pith.science/pith/P4XSLRPSVELXSL3XEYGR3RYHVY/action/author_attestation","sign_citation":"https://pith.science/pith/P4XSLRPSVELXSL3XEYGR3RYHVY/action/citation_signature","submit_replication":"https://pith.science/pith/P4XSLRPSVELXSL3XEYGR3RYHVY/action/replication_record"}},"created_at":"2026-05-18T00:43:44.714885+00:00","updated_at":"2026-05-18T00:43:44.714885+00:00"}