{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:IHR6SA634HMTU4KV7KLOGICU7G","short_pith_number":"pith:IHR6SA63","schema_version":"1.0","canonical_sha256":"41e3e903dbe1d93a7155fa96e32054f997e57cac55c8df2b0e1a3dfa6ab2e604","source":{"kind":"arxiv","id":"1704.06485","version":2},"attestation_state":"computed","paper":{"title":"Attend to You: Personalized Image Captioning with Context Sequence Memory Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Byeongchang Kim, Cesc Chunseong Park, Gunhee Kim","submitted_at":"2017-04-21T11:29:07Z","abstract_excerpt":"We address personalization issues of image captioning, which have not been discussed yet in previous research. For a query image, we aim to generate a descriptive sentence, accounting for prior knowledge such as the user's active vocabularies in previous documents. As applications of personalized image captioning, we tackle two post automation tasks: hashtag prediction and post generation, on our newly collected Instagram dataset, consisting of 1.1M posts from 6.3K users. We propose a novel captioning model named Context Sequence Memory Network (CSMN). Its unique updates over previous memory n"},"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":"1704.06485","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-21T11:29:07Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"97613d2926c6f96f8e9479329f21ad29d587903f6b78695d58e2d6ae9edca03b","abstract_canon_sha256":"1e1eab50f528a035963c61e209d6079ba0304f401a9ec94be6bbc3646ad3231f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:31.876789Z","signature_b64":"R+sPDWRN/OYSkuiGghJet1qJR0PtV9U2e7xOQzgljfhYuWOZ06CeHZbrM2/h8lkq5/ZiksBam8gWY1HCE+rzAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41e3e903dbe1d93a7155fa96e32054f997e57cac55c8df2b0e1a3dfa6ab2e604","last_reissued_at":"2026-05-18T00:45:31.876336Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:31.876336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attend to You: Personalized Image Captioning with Context Sequence Memory Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Byeongchang Kim, Cesc Chunseong Park, Gunhee Kim","submitted_at":"2017-04-21T11:29:07Z","abstract_excerpt":"We address personalization issues of image captioning, which have not been discussed yet in previous research. For a query image, we aim to generate a descriptive sentence, accounting for prior knowledge such as the user's active vocabularies in previous documents. As applications of personalized image captioning, we tackle two post automation tasks: hashtag prediction and post generation, on our newly collected Instagram dataset, consisting of 1.1M posts from 6.3K users. We propose a novel captioning model named Context Sequence Memory Network (CSMN). Its unique updates over previous memory n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06485","kind":"arxiv","version":2},"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":"1704.06485","created_at":"2026-05-18T00:45:31.876412+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.06485v2","created_at":"2026-05-18T00:45:31.876412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06485","created_at":"2026-05-18T00:45:31.876412+00:00"},{"alias_kind":"pith_short_12","alias_value":"IHR6SA634HMT","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"IHR6SA634HMTU4KV","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"IHR6SA63","created_at":"2026-05-18T12:31:21.493067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.12188","citing_title":"A Deep Decoder Structure Based on WordEmbedding Regression for An Encoder-Decoder Based Model for Image Captioning","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IHR6SA634HMTU4KV7KLOGICU7G","json":"https://pith.science/pith/IHR6SA634HMTU4KV7KLOGICU7G.json","graph_json":"https://pith.science/api/pith-number/IHR6SA634HMTU4KV7KLOGICU7G/graph.json","events_json":"https://pith.science/api/pith-number/IHR6SA634HMTU4KV7KLOGICU7G/events.json","paper":"https://pith.science/paper/IHR6SA63"},"agent_actions":{"view_html":"https://pith.science/pith/IHR6SA634HMTU4KV7KLOGICU7G","download_json":"https://pith.science/pith/IHR6SA634HMTU4KV7KLOGICU7G.json","view_paper":"https://pith.science/paper/IHR6SA63","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.06485&json=true","fetch_graph":"https://pith.science/api/pith-number/IHR6SA634HMTU4KV7KLOGICU7G/graph.json","fetch_events":"https://pith.science/api/pith-number/IHR6SA634HMTU4KV7KLOGICU7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IHR6SA634HMTU4KV7KLOGICU7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IHR6SA634HMTU4KV7KLOGICU7G/action/storage_attestation","attest_author":"https://pith.science/pith/IHR6SA634HMTU4KV7KLOGICU7G/action/author_attestation","sign_citation":"https://pith.science/pith/IHR6SA634HMTU4KV7KLOGICU7G/action/citation_signature","submit_replication":"https://pith.science/pith/IHR6SA634HMTU4KV7KLOGICU7G/action/replication_record"}},"created_at":"2026-05-18T00:45:31.876412+00:00","updated_at":"2026-05-18T00:45:31.876412+00:00"}