{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NMKE4R75IPT2GP47LWKPGTYTAT","short_pith_number":"pith:NMKE4R75","schema_version":"1.0","canonical_sha256":"6b144e47fd43e7a33f9f5d94f34f1304ddc12829941f4e591a4fca2fd8128dc5","source":{"kind":"arxiv","id":"1905.03966","version":1},"attestation_state":"computed","paper":{"title":"Memory-Attended Recurrent Network for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiyuan Zhang, Lei Ke, Wenjie Pei, Xiangrong Wang, Xiaoyong Shen, Yu-Wing Tai","submitted_at":"2019-05-10T06:47:57Z","abstract_excerpt":"Typical techniques for video captioning follow the encoder-decoder framework, which can only focus on one source video being processed. A potential disadvantage of such design is that it cannot capture the multiple visual context information of a word appearing in more than one relevant videos in training data. To tackle this limitation, we propose the Memory-Attended Recurrent Network (MARN) for video captioning, in which a memory structure is designed to explore the full-spectrum correspondence between a word and its various similar visual contexts across videos in training data. Thus, our m"},"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":"1905.03966","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-10T06:47:57Z","cross_cats_sorted":[],"title_canon_sha256":"dc569e8f4e3fc5e4a25e296a2c7f6b7f2142351acba21b69ccbfa8f1a280d018","abstract_canon_sha256":"879391471e601c7fe417656927fcaea299cabded102e992d95ffe067f140f794"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:35.022850Z","signature_b64":"hb++ltZbm/j4H9o+Ef1pOfPGz2JKxmpr+REIx92/ZKxFvihZS+FMqqdiqJBKyMvFEd4IKTbrZYUS0SPSVDgpBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b144e47fd43e7a33f9f5d94f34f1304ddc12829941f4e591a4fca2fd8128dc5","last_reissued_at":"2026-05-17T23:46:35.022291Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:35.022291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory-Attended Recurrent Network for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiyuan Zhang, Lei Ke, Wenjie Pei, Xiangrong Wang, Xiaoyong Shen, Yu-Wing Tai","submitted_at":"2019-05-10T06:47:57Z","abstract_excerpt":"Typical techniques for video captioning follow the encoder-decoder framework, which can only focus on one source video being processed. A potential disadvantage of such design is that it cannot capture the multiple visual context information of a word appearing in more than one relevant videos in training data. To tackle this limitation, we propose the Memory-Attended Recurrent Network (MARN) for video captioning, in which a memory structure is designed to explore the full-spectrum correspondence between a word and its various similar visual contexts across videos in training data. Thus, our m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.03966","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":"1905.03966","created_at":"2026-05-17T23:46:35.022389+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.03966v1","created_at":"2026-05-17T23:46:35.022389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.03966","created_at":"2026-05-17T23:46:35.022389+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMKE4R75IPT2","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMKE4R75IPT2GP47","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMKE4R75","created_at":"2026-05-18T12:33:24.271573+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/NMKE4R75IPT2GP47LWKPGTYTAT","json":"https://pith.science/pith/NMKE4R75IPT2GP47LWKPGTYTAT.json","graph_json":"https://pith.science/api/pith-number/NMKE4R75IPT2GP47LWKPGTYTAT/graph.json","events_json":"https://pith.science/api/pith-number/NMKE4R75IPT2GP47LWKPGTYTAT/events.json","paper":"https://pith.science/paper/NMKE4R75"},"agent_actions":{"view_html":"https://pith.science/pith/NMKE4R75IPT2GP47LWKPGTYTAT","download_json":"https://pith.science/pith/NMKE4R75IPT2GP47LWKPGTYTAT.json","view_paper":"https://pith.science/paper/NMKE4R75","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.03966&json=true","fetch_graph":"https://pith.science/api/pith-number/NMKE4R75IPT2GP47LWKPGTYTAT/graph.json","fetch_events":"https://pith.science/api/pith-number/NMKE4R75IPT2GP47LWKPGTYTAT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMKE4R75IPT2GP47LWKPGTYTAT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMKE4R75IPT2GP47LWKPGTYTAT/action/storage_attestation","attest_author":"https://pith.science/pith/NMKE4R75IPT2GP47LWKPGTYTAT/action/author_attestation","sign_citation":"https://pith.science/pith/NMKE4R75IPT2GP47LWKPGTYTAT/action/citation_signature","submit_replication":"https://pith.science/pith/NMKE4R75IPT2GP47LWKPGTYTAT/action/replication_record"}},"created_at":"2026-05-17T23:46:35.022389+00:00","updated_at":"2026-05-17T23:46:35.022389+00:00"}