{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V5PTIYMVHPFATLEEJRQANBX5NL","short_pith_number":"pith:V5PTIYMV","schema_version":"1.0","canonical_sha256":"af5f3461953bca09ac844c600686fd6ae2ebb0ecea47f66b1ddd4b0addc6dac5","source":{"kind":"arxiv","id":"2409.18046","version":1},"attestation_state":"computed","paper":{"title":"IFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dong-Jin Kim, Si-Woo Kim, Soeun Lee, Taewhan Kim","submitted_at":"2024-09-26T16:47:32Z","abstract_excerpt":"Recent advancements in image captioning have explored text-only training methods to overcome the limitations of paired image-text data. However, existing text-only training methods often overlook the modality gap between using text data during training and employing images during inference. To address this issue, we propose a novel approach called Image-like Retrieval, which aligns text features with visually relevant features to mitigate the modality gap. Our method further enhances the accuracy of generated captions by designing a Fusion Module that integrates retrieved captions with input f"},"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":"2409.18046","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-26T16:47:32Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"ed589b8b88ec15aae02064d53bc62b91001cc3d5a24ed458add025257f23b0a8","abstract_canon_sha256":"c32493794ae921ca2e57ab64f73f3af039a49379ed0e9bbd2a8993f66025e00e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:19.780036Z","signature_b64":"R90L14MRfEjk9YPW7R1FlJiCEVJ5ja/fA+riRubh6nI9PWM/VpPJRbu6kNHSV4lsAL+8KthKqXpvLNqAmnpMBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af5f3461953bca09ac844c600686fd6ae2ebb0ecea47f66b1ddd4b0addc6dac5","last_reissued_at":"2026-07-05T09:12:19.779451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:19.779451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dong-Jin Kim, Si-Woo Kim, Soeun Lee, Taewhan Kim","submitted_at":"2024-09-26T16:47:32Z","abstract_excerpt":"Recent advancements in image captioning have explored text-only training methods to overcome the limitations of paired image-text data. However, existing text-only training methods often overlook the modality gap between using text data during training and employing images during inference. To address this issue, we propose a novel approach called Image-like Retrieval, which aligns text features with visually relevant features to mitigate the modality gap. Our method further enhances the accuracy of generated captions by designing a Fusion Module that integrates retrieved captions with input f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18046","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.18046/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2409.18046","created_at":"2026-07-05T09:12:19.779517+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18046v1","created_at":"2026-07-05T09:12:19.779517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18046","created_at":"2026-07-05T09:12:19.779517+00:00"},{"alias_kind":"pith_short_12","alias_value":"V5PTIYMVHPFA","created_at":"2026-07-05T09:12:19.779517+00:00"},{"alias_kind":"pith_short_16","alias_value":"V5PTIYMVHPFATLEE","created_at":"2026-07-05T09:12:19.779517+00:00"},{"alias_kind":"pith_short_8","alias_value":"V5PTIYMV","created_at":"2026-07-05T09:12:19.779517+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.11013","citing_title":"Watching Synthetic Videos: Aligning Cross-modal Representations with Visual Synthesis for Zero-shot Video Captioning","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V5PTIYMVHPFATLEEJRQANBX5NL","json":"https://pith.science/pith/V5PTIYMVHPFATLEEJRQANBX5NL.json","graph_json":"https://pith.science/api/pith-number/V5PTIYMVHPFATLEEJRQANBX5NL/graph.json","events_json":"https://pith.science/api/pith-number/V5PTIYMVHPFATLEEJRQANBX5NL/events.json","paper":"https://pith.science/paper/V5PTIYMV"},"agent_actions":{"view_html":"https://pith.science/pith/V5PTIYMVHPFATLEEJRQANBX5NL","download_json":"https://pith.science/pith/V5PTIYMVHPFATLEEJRQANBX5NL.json","view_paper":"https://pith.science/paper/V5PTIYMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18046&json=true","fetch_graph":"https://pith.science/api/pith-number/V5PTIYMVHPFATLEEJRQANBX5NL/graph.json","fetch_events":"https://pith.science/api/pith-number/V5PTIYMVHPFATLEEJRQANBX5NL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V5PTIYMVHPFATLEEJRQANBX5NL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V5PTIYMVHPFATLEEJRQANBX5NL/action/storage_attestation","attest_author":"https://pith.science/pith/V5PTIYMVHPFATLEEJRQANBX5NL/action/author_attestation","sign_citation":"https://pith.science/pith/V5PTIYMVHPFATLEEJRQANBX5NL/action/citation_signature","submit_replication":"https://pith.science/pith/V5PTIYMVHPFATLEEJRQANBX5NL/action/replication_record"}},"created_at":"2026-07-05T09:12:19.779517+00:00","updated_at":"2026-07-05T09:12:19.779517+00:00"}