{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:V4NX6F676TLCS4SCBCGRJNC6RF","short_pith_number":"pith:V4NX6F67","schema_version":"1.0","canonical_sha256":"af1b7f17dff4d6297242088d14b45e89741102d4a813c16154a62cd2636d108e","source":{"kind":"arxiv","id":"1808.07793","version":1},"attestation_state":"computed","paper":{"title":"Webly Supervised Joint Embedding for Cross-Modal Image-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.IR"],"primary_cat":"cs.MM","authors_text":"Amit K. Roy-Chowdhury, Evangelos E. Papalexakis, Niluthpol Chowdhury Mithun, Rameswar Panda","submitted_at":"2018-08-23T15:07:52Z","abstract_excerpt":"Cross-modal retrieval between visual data and natural language description remains a long-standing challenge in multimedia. While recent image-text retrieval methods offer great promise by learning deep representations aligned across modalities, most of these methods are plagued by the issue of training with small-scale datasets covering a limited number of images with ground-truth sentences. Moreover, it is extremely expensive to create a larger dataset by annotating millions of images with sentences and may lead to a biased model. Inspired by the recent success of webly supervised learning i"},"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":"1808.07793","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2018-08-23T15:07:52Z","cross_cats_sorted":["cs.CV","cs.IR"],"title_canon_sha256":"77643385dc77675ddeb9ee549e6b20864858070bc1fb44933c03fef16aad0cb2","abstract_canon_sha256":"8992287b00fbc96b29a612c830fcc7dce002daaaf38e8939b2916fef088417d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:24.290644Z","signature_b64":"xYgcDBt5XMALEjOpIoE6qyvkCtEsn0KmJS1jQccexIBAbzIH0ieHjGxH7DH2kMwwHtoMtqxlWyVQSeaJHxTRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af1b7f17dff4d6297242088d14b45e89741102d4a813c16154a62cd2636d108e","last_reissued_at":"2026-05-18T00:07:24.290190Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:24.290190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Webly Supervised Joint Embedding for Cross-Modal Image-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.IR"],"primary_cat":"cs.MM","authors_text":"Amit K. Roy-Chowdhury, Evangelos E. Papalexakis, Niluthpol Chowdhury Mithun, Rameswar Panda","submitted_at":"2018-08-23T15:07:52Z","abstract_excerpt":"Cross-modal retrieval between visual data and natural language description remains a long-standing challenge in multimedia. While recent image-text retrieval methods offer great promise by learning deep representations aligned across modalities, most of these methods are plagued by the issue of training with small-scale datasets covering a limited number of images with ground-truth sentences. Moreover, it is extremely expensive to create a larger dataset by annotating millions of images with sentences and may lead to a biased model. Inspired by the recent success of webly supervised learning i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.07793","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":"1808.07793","created_at":"2026-05-18T00:07:24.290262+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.07793v1","created_at":"2026-05-18T00:07:24.290262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.07793","created_at":"2026-05-18T00:07:24.290262+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4NX6F676TLC","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4NX6F676TLCS4SC","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4NX6F67","created_at":"2026-05-18T12:32:56.356000+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/V4NX6F676TLCS4SCBCGRJNC6RF","json":"https://pith.science/pith/V4NX6F676TLCS4SCBCGRJNC6RF.json","graph_json":"https://pith.science/api/pith-number/V4NX6F676TLCS4SCBCGRJNC6RF/graph.json","events_json":"https://pith.science/api/pith-number/V4NX6F676TLCS4SCBCGRJNC6RF/events.json","paper":"https://pith.science/paper/V4NX6F67"},"agent_actions":{"view_html":"https://pith.science/pith/V4NX6F676TLCS4SCBCGRJNC6RF","download_json":"https://pith.science/pith/V4NX6F676TLCS4SCBCGRJNC6RF.json","view_paper":"https://pith.science/paper/V4NX6F67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.07793&json=true","fetch_graph":"https://pith.science/api/pith-number/V4NX6F676TLCS4SCBCGRJNC6RF/graph.json","fetch_events":"https://pith.science/api/pith-number/V4NX6F676TLCS4SCBCGRJNC6RF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4NX6F676TLCS4SCBCGRJNC6RF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4NX6F676TLCS4SCBCGRJNC6RF/action/storage_attestation","attest_author":"https://pith.science/pith/V4NX6F676TLCS4SCBCGRJNC6RF/action/author_attestation","sign_citation":"https://pith.science/pith/V4NX6F676TLCS4SCBCGRJNC6RF/action/citation_signature","submit_replication":"https://pith.science/pith/V4NX6F676TLCS4SCBCGRJNC6RF/action/replication_record"}},"created_at":"2026-05-18T00:07:24.290262+00:00","updated_at":"2026-05-18T00:07:24.290262+00:00"}