{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:UAWP3UNZM4MCDQ6KHH7LRFGTBF","short_pith_number":"pith:UAWP3UNZ","schema_version":"1.0","canonical_sha256":"a02cfdd1b9671821c3ca39feb894d309548665cd313766573d2ff6e64125fc40","source":{"kind":"arxiv","id":"1612.08354","version":1},"attestation_state":"computed","paper":{"title":"Image-Text Multi-Modal Representation Learning by Adversarial Backpropagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gwangbeen Park, Woobin Im","submitted_at":"2016-12-26T09:51:18Z","abstract_excerpt":"We present novel method for image-text multi-modal representation learning. In our knowledge, this work is the first approach of applying adversarial learning concept to multi-modal learning and not exploiting image-text pair information to learn multi-modal feature. We only use category information in contrast with most previous methods using image-text pair information for multi-modal embedding. In this paper, we show that multi-modal feature can be achieved without image-text pair information and our method makes more similar distribution with image and text in multi-modal feature space tha"},"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":"1612.08354","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-26T09:51:18Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"0fb69c2237e490096e00946e5f1f15f4eb73fa3439b14b286a445146727dbc19","abstract_canon_sha256":"23a22b0e270ef8a8e0aeb6cd0574158d1e057a6b15ef3fe8ba867c014b250e98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:53:56.845168Z","signature_b64":"mfFCchbY8jKrD15rBhV6I7TApIt+zcmvIIJONOd110ZdnvYJzTewMvpi8/YvuWt8hC1hdnjy3EQDp5jywP3QAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a02cfdd1b9671821c3ca39feb894d309548665cd313766573d2ff6e64125fc40","last_reissued_at":"2026-05-18T00:53:56.844729Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:53:56.844729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image-Text Multi-Modal Representation Learning by Adversarial Backpropagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gwangbeen Park, Woobin Im","submitted_at":"2016-12-26T09:51:18Z","abstract_excerpt":"We present novel method for image-text multi-modal representation learning. In our knowledge, this work is the first approach of applying adversarial learning concept to multi-modal learning and not exploiting image-text pair information to learn multi-modal feature. We only use category information in contrast with most previous methods using image-text pair information for multi-modal embedding. In this paper, we show that multi-modal feature can be achieved without image-text pair information and our method makes more similar distribution with image and text in multi-modal feature space tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.08354","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":"1612.08354","created_at":"2026-05-18T00:53:56.844799+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.08354v1","created_at":"2026-05-18T00:53:56.844799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.08354","created_at":"2026-05-18T00:53:56.844799+00:00"},{"alias_kind":"pith_short_12","alias_value":"UAWP3UNZM4MC","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_16","alias_value":"UAWP3UNZM4MCDQ6K","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_8","alias_value":"UAWP3UNZ","created_at":"2026-05-18T12:30:46.583412+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.01976","citing_title":"Do Cross Modal Systems Leverage Semantic Relationships?","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UAWP3UNZM4MCDQ6KHH7LRFGTBF","json":"https://pith.science/pith/UAWP3UNZM4MCDQ6KHH7LRFGTBF.json","graph_json":"https://pith.science/api/pith-number/UAWP3UNZM4MCDQ6KHH7LRFGTBF/graph.json","events_json":"https://pith.science/api/pith-number/UAWP3UNZM4MCDQ6KHH7LRFGTBF/events.json","paper":"https://pith.science/paper/UAWP3UNZ"},"agent_actions":{"view_html":"https://pith.science/pith/UAWP3UNZM4MCDQ6KHH7LRFGTBF","download_json":"https://pith.science/pith/UAWP3UNZM4MCDQ6KHH7LRFGTBF.json","view_paper":"https://pith.science/paper/UAWP3UNZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.08354&json=true","fetch_graph":"https://pith.science/api/pith-number/UAWP3UNZM4MCDQ6KHH7LRFGTBF/graph.json","fetch_events":"https://pith.science/api/pith-number/UAWP3UNZM4MCDQ6KHH7LRFGTBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UAWP3UNZM4MCDQ6KHH7LRFGTBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UAWP3UNZM4MCDQ6KHH7LRFGTBF/action/storage_attestation","attest_author":"https://pith.science/pith/UAWP3UNZM4MCDQ6KHH7LRFGTBF/action/author_attestation","sign_citation":"https://pith.science/pith/UAWP3UNZM4MCDQ6KHH7LRFGTBF/action/citation_signature","submit_replication":"https://pith.science/pith/UAWP3UNZM4MCDQ6KHH7LRFGTBF/action/replication_record"}},"created_at":"2026-05-18T00:53:56.844799+00:00","updated_at":"2026-05-18T00:53:56.844799+00:00"}