{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QGLE5D7GQKP7X5TXJV3H5HSC2G","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"768da22fe26a7453a360f6d6954c1ce348f554511eae66af51e6946300046154","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-27T08:22:54Z","title_canon_sha256":"c5af70ead643b53f2d3395d1f1894b4bd4792c401c250617f3ac378631ea0cf3"},"schema_version":"1.0","source":{"id":"1908.10072","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.10072","created_at":"2026-07-04T23:59:53Z"},{"alias_kind":"arxiv_version","alias_value":"1908.10072v1","created_at":"2026-07-04T23:59:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.10072","created_at":"2026-07-04T23:59:53Z"},{"alias_kind":"pith_short_12","alias_value":"QGLE5D7GQKP7","created_at":"2026-07-04T23:59:53Z"},{"alias_kind":"pith_short_16","alias_value":"QGLE5D7GQKP7X5TX","created_at":"2026-07-04T23:59:53Z"},{"alias_kind":"pith_short_8","alias_value":"QGLE5D7G","created_at":"2026-07-04T23:59:53Z"}],"graph_snapshots":[{"event_id":"sha256:46afd8c83cee3de254728d5daea5ef44cef327f0942afb4462785a7188b7f6ff","target":"graph","created_at":"2026-07-04T23:59:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.10072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose to guide the video caption generation with Part-of-Speech (POS) information, based on a gated fusion of multiple representations of input videos. We construct a novel gated fusion network, with one particularly designed cross-gating (CG) block, to effectively encode and fuse different types of representations, e.g., the motion and content features of an input video. One POS sequence generator relies on this fused representation to predict the global syntactic structure, which is thereafter leveraged to guide the video captioning generation and control the syntax of th","authors_text":"Bairui Wang, Jingwen Wang, Lin Ma, Wei Liu, Wei Zhang, Wenhao Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-27T08:22:54Z","title":"Controllable Video Captioning with POS Sequence Guidance Based on Gated Fusion Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.10072","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7be0943500006e328b23745179c7f58d7038d66b95cec7cd55074ca32df346b6","target":"record","created_at":"2026-07-04T23:59:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"768da22fe26a7453a360f6d6954c1ce348f554511eae66af51e6946300046154","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-27T08:22:54Z","title_canon_sha256":"c5af70ead643b53f2d3395d1f1894b4bd4792c401c250617f3ac378631ea0cf3"},"schema_version":"1.0","source":{"id":"1908.10072","kind":"arxiv","version":1}},"canonical_sha256":"81964e8fe6829ffbf6774d767e9e42d1a7d60d5e1f7029da2edd91e88183dcca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81964e8fe6829ffbf6774d767e9e42d1a7d60d5e1f7029da2edd91e88183dcca","first_computed_at":"2026-07-04T23:59:53.593187Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:59:53.593187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WkssZI28hwVJrT6islVWszeVwFBwQEEm3meckh4tSEi7CxdUnHreigDeEJvEjIlRWyobhIPc6wkfD8StjkdXBQ==","signature_status":"signed_v1","signed_at":"2026-07-04T23:59:53.593645Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.10072","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7be0943500006e328b23745179c7f58d7038d66b95cec7cd55074ca32df346b6","sha256:46afd8c83cee3de254728d5daea5ef44cef327f0942afb4462785a7188b7f6ff"],"state_sha256":"31976509acf7be9b03ad9e9987be93db4b660bad426256f96de89f341af43762"}