{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7B2553RIRI3UJ7VSPZOIY7WLK5","short_pith_number":"pith:7B2553RI","schema_version":"1.0","canonical_sha256":"f875deee288a3744feb27e5c8c7ecb5758854e36d75e5ff086b4b2b3527e5491","source":{"kind":"arxiv","id":"1812.11004","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical LSTMs with Adaptive Attention for Visual Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heng Tao Shen, Jingkuan Song, Lianli Gao, Xiangpeng Li","submitted_at":"2018-12-26T09:51:58Z","abstract_excerpt":"Recent progress has been made in using attention based encoder-decoder framework for image and video captioning. Most existing decoders apply the attention mechanism to every generated word including both visual words (e.g., \"gun\" and \"shooting\") and non-visual words (e.g. \"the\", \"a\"). However, these non-visual words can be easily predicted using natural language model without considering visual signals or attention. Imposing attention mechanism on non-visual words could mislead and decrease the overall performance of visual captioning. Furthermore, the hierarchy of LSTMs enables more complex "},"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":"1812.11004","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-26T09:51:58Z","cross_cats_sorted":[],"title_canon_sha256":"3b071ae608ff751cfe3b81a8224b33b11e04eafad500dcbb0af5683fae697aba","abstract_canon_sha256":"f31bcd5a32d11c217015d57daeff83be2fa4949d4dd4521933568270f6192115"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:16.583186Z","signature_b64":"Hnd3zr7bZeQfRWkDSDldozp2/zZNPhQ4r4ZBpW5RNuXCqzij/VXSWr4lgPel27NuwqRIuA45a5Wp48PNIclwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f875deee288a3744feb27e5c8c7ecb5758854e36d75e5ff086b4b2b3527e5491","last_reissued_at":"2026-05-17T23:57:16.582748Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:16.582748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical LSTMs with Adaptive Attention for Visual Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heng Tao Shen, Jingkuan Song, Lianli Gao, Xiangpeng Li","submitted_at":"2018-12-26T09:51:58Z","abstract_excerpt":"Recent progress has been made in using attention based encoder-decoder framework for image and video captioning. Most existing decoders apply the attention mechanism to every generated word including both visual words (e.g., \"gun\" and \"shooting\") and non-visual words (e.g. \"the\", \"a\"). However, these non-visual words can be easily predicted using natural language model without considering visual signals or attention. Imposing attention mechanism on non-visual words could mislead and decrease the overall performance of visual captioning. Furthermore, the hierarchy of LSTMs enables more complex "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.11004","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":"1812.11004","created_at":"2026-05-17T23:57:16.582831+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.11004v1","created_at":"2026-05-17T23:57:16.582831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.11004","created_at":"2026-05-17T23:57:16.582831+00:00"},{"alias_kind":"pith_short_12","alias_value":"7B2553RIRI3U","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7B2553RIRI3UJ7VS","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7B2553RI","created_at":"2026-05-18T12:32:11.075285+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/7B2553RIRI3UJ7VSPZOIY7WLK5","json":"https://pith.science/pith/7B2553RIRI3UJ7VSPZOIY7WLK5.json","graph_json":"https://pith.science/api/pith-number/7B2553RIRI3UJ7VSPZOIY7WLK5/graph.json","events_json":"https://pith.science/api/pith-number/7B2553RIRI3UJ7VSPZOIY7WLK5/events.json","paper":"https://pith.science/paper/7B2553RI"},"agent_actions":{"view_html":"https://pith.science/pith/7B2553RIRI3UJ7VSPZOIY7WLK5","download_json":"https://pith.science/pith/7B2553RIRI3UJ7VSPZOIY7WLK5.json","view_paper":"https://pith.science/paper/7B2553RI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.11004&json=true","fetch_graph":"https://pith.science/api/pith-number/7B2553RIRI3UJ7VSPZOIY7WLK5/graph.json","fetch_events":"https://pith.science/api/pith-number/7B2553RIRI3UJ7VSPZOIY7WLK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7B2553RIRI3UJ7VSPZOIY7WLK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7B2553RIRI3UJ7VSPZOIY7WLK5/action/storage_attestation","attest_author":"https://pith.science/pith/7B2553RIRI3UJ7VSPZOIY7WLK5/action/author_attestation","sign_citation":"https://pith.science/pith/7B2553RIRI3UJ7VSPZOIY7WLK5/action/citation_signature","submit_replication":"https://pith.science/pith/7B2553RIRI3UJ7VSPZOIY7WLK5/action/replication_record"}},"created_at":"2026-05-17T23:57:16.582831+00:00","updated_at":"2026-05-17T23:57:16.582831+00:00"}