{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CKG4VAYO6C4PBIV7NW7CKQ2HEI","short_pith_number":"pith:CKG4VAYO","schema_version":"1.0","canonical_sha256":"128dca830ef0b8f0a2bf6dbe25434722253fbc2449c6536da52b22d7ff71f021","source":{"kind":"arxiv","id":"1905.02963","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Semantic Attention Network for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Li, Chunfeng Yuan, Liang Sun, Weiming Hu, Zhengjun Zha","submitted_at":"2019-05-08T08:51:12Z","abstract_excerpt":"Inspired by the fact that different modalities in videos carry complementary information, we propose a Multimodal Semantic Attention Network(MSAN), which is a new encoder-decoder framework incorporating multimodal semantic attributes for video captioning. In the encoding phase, we detect and generate multimodal semantic attributes by formulating it as a multi-label classification problem. Moreover, we add auxiliary classification loss to our model that can obtain more effective visual features and high-level multimodal semantic attribute distributions for sufficient video encoding. In the deco"},"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":"1905.02963","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-08T08:51:12Z","cross_cats_sorted":[],"title_canon_sha256":"5f7271a61cf69867f0e2465c4bcdb0bbefa4691bbb35e1d918cbd0f012168cb4","abstract_canon_sha256":"5303b6056ddf46bdd940918552990b17533521e87d535e19a151c9a93d9cd335"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:43.265134Z","signature_b64":"C6NOV5A+q2znNtf4AsXS/Eg6I6rtgZ0GFUz8ojDyTiC3i8Wzyx0k7axh27FXdEzNChFZ4CrVbi2es2vmDHztCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"128dca830ef0b8f0a2bf6dbe25434722253fbc2449c6536da52b22d7ff71f021","last_reissued_at":"2026-05-17T23:46:43.264689Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:43.264689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Semantic Attention Network for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Li, Chunfeng Yuan, Liang Sun, Weiming Hu, Zhengjun Zha","submitted_at":"2019-05-08T08:51:12Z","abstract_excerpt":"Inspired by the fact that different modalities in videos carry complementary information, we propose a Multimodal Semantic Attention Network(MSAN), which is a new encoder-decoder framework incorporating multimodal semantic attributes for video captioning. In the encoding phase, we detect and generate multimodal semantic attributes by formulating it as a multi-label classification problem. Moreover, we add auxiliary classification loss to our model that can obtain more effective visual features and high-level multimodal semantic attribute distributions for sufficient video encoding. In the deco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.02963","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":"1905.02963","created_at":"2026-05-17T23:46:43.264756+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.02963v1","created_at":"2026-05-17T23:46:43.264756+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.02963","created_at":"2026-05-17T23:46:43.264756+00:00"},{"alias_kind":"pith_short_12","alias_value":"CKG4VAYO6C4P","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"CKG4VAYO6C4PBIV7","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"CKG4VAYO","created_at":"2026-05-18T12:33:15.570797+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/CKG4VAYO6C4PBIV7NW7CKQ2HEI","json":"https://pith.science/pith/CKG4VAYO6C4PBIV7NW7CKQ2HEI.json","graph_json":"https://pith.science/api/pith-number/CKG4VAYO6C4PBIV7NW7CKQ2HEI/graph.json","events_json":"https://pith.science/api/pith-number/CKG4VAYO6C4PBIV7NW7CKQ2HEI/events.json","paper":"https://pith.science/paper/CKG4VAYO"},"agent_actions":{"view_html":"https://pith.science/pith/CKG4VAYO6C4PBIV7NW7CKQ2HEI","download_json":"https://pith.science/pith/CKG4VAYO6C4PBIV7NW7CKQ2HEI.json","view_paper":"https://pith.science/paper/CKG4VAYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.02963&json=true","fetch_graph":"https://pith.science/api/pith-number/CKG4VAYO6C4PBIV7NW7CKQ2HEI/graph.json","fetch_events":"https://pith.science/api/pith-number/CKG4VAYO6C4PBIV7NW7CKQ2HEI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CKG4VAYO6C4PBIV7NW7CKQ2HEI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CKG4VAYO6C4PBIV7NW7CKQ2HEI/action/storage_attestation","attest_author":"https://pith.science/pith/CKG4VAYO6C4PBIV7NW7CKQ2HEI/action/author_attestation","sign_citation":"https://pith.science/pith/CKG4VAYO6C4PBIV7NW7CKQ2HEI/action/citation_signature","submit_replication":"https://pith.science/pith/CKG4VAYO6C4PBIV7NW7CKQ2HEI/action/replication_record"}},"created_at":"2026-05-17T23:46:43.264756+00:00","updated_at":"2026-05-17T23:46:43.264756+00:00"}