{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KEN2BHHTH2CBXUTZEISEUPXAUZ","short_pith_number":"pith:KEN2BHHT","schema_version":"1.0","canonical_sha256":"511ba09cf33e841bd27922244a3ee0a66ff1924f912e0ab99a94dd9b42e2583b","source":{"kind":"arxiv","id":"1805.10973","version":3},"attestation_state":"computed","paper":{"title":"GLAC Net: GLocal Attention Cascading Networks for Multi-image Cued Story Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Byoung-Tak Zhang, Kyoung-Wha Park, Min-Oh Heo, Seonil Son, Taehyeong Kim","submitted_at":"2018-05-28T15:30:21Z","abstract_excerpt":"The task of multi-image cued story generation, such as visual storytelling dataset (VIST) challenge, is to compose multiple coherent sentences from a given sequence of images. The main difficulty is how to generate image-specific sentences within the context of overall images. Here we propose a deep learning network model, GLAC Net, that generates visual stories by combining global-local (glocal) attention and context cascading mechanisms. The model incorporates two levels of attention, i.e., overall encoding level and image feature level, to construct image-dependent sentences. While standard"},"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":"1805.10973","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-28T15:30:21Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1cf4d2cba37fe8284bf1578e2867e70bcef85c185655717ca6e7caca069f4d85","abstract_canon_sha256":"5e127b8757bcea941f01971ffc620d11278e08c92483ebcccb73d5a3c9339791"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:07.290942Z","signature_b64":"DI5lt24/DjRfTd0NDzX0zuncqK2NsJM6Z4REAdoyqEvykmjw3ZUAo/PILcnn/2LBRVNxyxfXT3VIRQdlcufBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"511ba09cf33e841bd27922244a3ee0a66ff1924f912e0ab99a94dd9b42e2583b","last_reissued_at":"2026-05-17T23:54:07.290449Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:07.290449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GLAC Net: GLocal Attention Cascading Networks for Multi-image Cued Story Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Byoung-Tak Zhang, Kyoung-Wha Park, Min-Oh Heo, Seonil Son, Taehyeong Kim","submitted_at":"2018-05-28T15:30:21Z","abstract_excerpt":"The task of multi-image cued story generation, such as visual storytelling dataset (VIST) challenge, is to compose multiple coherent sentences from a given sequence of images. The main difficulty is how to generate image-specific sentences within the context of overall images. Here we propose a deep learning network model, GLAC Net, that generates visual stories by combining global-local (glocal) attention and context cascading mechanisms. The model incorporates two levels of attention, i.e., overall encoding level and image feature level, to construct image-dependent sentences. While standard"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10973","kind":"arxiv","version":3},"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":"1805.10973","created_at":"2026-05-17T23:54:07.290518+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.10973v3","created_at":"2026-05-17T23:54:07.290518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10973","created_at":"2026-05-17T23:54:07.290518+00:00"},{"alias_kind":"pith_short_12","alias_value":"KEN2BHHTH2CB","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KEN2BHHTH2CBXUTZ","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KEN2BHHT","created_at":"2026-05-18T12:32:33.847187+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/KEN2BHHTH2CBXUTZEISEUPXAUZ","json":"https://pith.science/pith/KEN2BHHTH2CBXUTZEISEUPXAUZ.json","graph_json":"https://pith.science/api/pith-number/KEN2BHHTH2CBXUTZEISEUPXAUZ/graph.json","events_json":"https://pith.science/api/pith-number/KEN2BHHTH2CBXUTZEISEUPXAUZ/events.json","paper":"https://pith.science/paper/KEN2BHHT"},"agent_actions":{"view_html":"https://pith.science/pith/KEN2BHHTH2CBXUTZEISEUPXAUZ","download_json":"https://pith.science/pith/KEN2BHHTH2CBXUTZEISEUPXAUZ.json","view_paper":"https://pith.science/paper/KEN2BHHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.10973&json=true","fetch_graph":"https://pith.science/api/pith-number/KEN2BHHTH2CBXUTZEISEUPXAUZ/graph.json","fetch_events":"https://pith.science/api/pith-number/KEN2BHHTH2CBXUTZEISEUPXAUZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KEN2BHHTH2CBXUTZEISEUPXAUZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KEN2BHHTH2CBXUTZEISEUPXAUZ/action/storage_attestation","attest_author":"https://pith.science/pith/KEN2BHHTH2CBXUTZEISEUPXAUZ/action/author_attestation","sign_citation":"https://pith.science/pith/KEN2BHHTH2CBXUTZEISEUPXAUZ/action/citation_signature","submit_replication":"https://pith.science/pith/KEN2BHHTH2CBXUTZEISEUPXAUZ/action/replication_record"}},"created_at":"2026-05-17T23:54:07.290518+00:00","updated_at":"2026-05-17T23:54:07.290518+00:00"}