{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:P4XSLRPSVELXSL3XEYGR3RYHVY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5b2f074943a8277b86ddb54d80d97881e8f167655271cd4131e8bb455b0a4628","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-24T06:59:30Z","title_canon_sha256":"a8160deb93f602e55793a8117093f65bd3dfbecb648917388dee3ef18a80d7e5"},"schema_version":"1.0","source":{"id":"1705.08631","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08631","created_at":"2026-05-18T00:43:44Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08631v1","created_at":"2026-05-18T00:43:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08631","created_at":"2026-05-18T00:43:44Z"},{"alias_kind":"pith_short_12","alias_value":"P4XSLRPSVELX","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"P4XSLRPSVELXSL3X","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"P4XSLRPS","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:6d9a166fb12b3dccd6b9c79dda4a466bbd9428b4b112fb72aac26f9385e7443d","target":"graph","created_at":"2026-05-18T00:43:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"C.V. Jawahar, Dimosthenis Karatzas, Lluis Gomez, Mar\\c{c}al Rusi\\~nol, Yash Patel","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-24T06:59:30Z","title":"Self-supervised learning of visual features through embedding images into text topic spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08631","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d3daf39a5dbc4719deaac4368385be4f466dbfdf1719383e25fb673728acd5db","target":"record","created_at":"2026-05-18T00:43:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5b2f074943a8277b86ddb54d80d97881e8f167655271cd4131e8bb455b0a4628","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-24T06:59:30Z","title_canon_sha256":"a8160deb93f602e55793a8117093f65bd3dfbecb648917388dee3ef18a80d7e5"},"schema_version":"1.0","source":{"id":"1705.08631","kind":"arxiv","version":1}},"canonical_sha256":"7f2f25c5f2a917792f77260d1dc707ae1bf223c8ca38a420ee8a1ba22438dcc6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f2f25c5f2a917792f77260d1dc707ae1bf223c8ca38a420ee8a1ba22438dcc6","first_computed_at":"2026-05-18T00:43:44.714758Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:44.714758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I12Bc2Gtnm+nm40S2/weBt3nkUFxsbsexu0mnYRh7qCOT1LcWinNnVNtM4rvmNPZMuIPi/mOuZSnPnwSW/djAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:44.715455Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.08631","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3daf39a5dbc4719deaac4368385be4f466dbfdf1719383e25fb673728acd5db","sha256:6d9a166fb12b3dccd6b9c79dda4a466bbd9428b4b112fb72aac26f9385e7443d"],"state_sha256":"b77d2690fbe376242d0725ad1d9c311423e8945f30500864c7fb0e33ea1148ca"}