{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:U2YSPGRZWWJUWKKCUCXQJ5ITWC","short_pith_number":"pith:U2YSPGRZ","schema_version":"1.0","canonical_sha256":"a6b1279a39b5934b2942a0af04f513b0999a9ac96e3132a45c4a5c8fa1babb10","source":{"kind":"arxiv","id":"1902.10322","version":2},"attestation_state":"computed","paper":{"title":"Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ajmal Mian, Naveed Akhtar, Nayyer Aafaq, Syed Zulqarnain Gilani, Wei Liu","submitted_at":"2019-02-27T03:52:08Z","abstract_excerpt":"Automatic generation of video captions is a fundamental challenge in computer vision. Recent techniques typically employ a combination of Convolutional Neural Networks (CNNs) and Recursive Neural Networks (RNNs) for video captioning. These methods mainly focus on tailoring sequence learning through RNNs for better caption generation, whereas off-the-shelf visual features are borrowed from CNNs. We argue that careful designing of visual features for this task is equally important, and present a visual feature encoding technique to generate semantically rich captions using Gated Recurrent Units "},"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":"1902.10322","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-27T03:52:08Z","cross_cats_sorted":[],"title_canon_sha256":"9727db43912d063721b93ccf1f26f1e3e2a86b2be82451d5f57464103a2e9498","abstract_canon_sha256":"2d0f8d19754188cbf03093e7fe481e52a359fad13d9e5687719324b905de51bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:35.717420Z","signature_b64":"7rx9FnaW9dRlCxIbpmCFDLaaktWTsJ7cZf9ZsANQfddObwK3w5YdNkxebQjTIyTbb/Ve+fsyyGqEdSBbX9GsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6b1279a39b5934b2942a0af04f513b0999a9ac96e3132a45c4a5c8fa1babb10","last_reissued_at":"2026-05-17T23:47:35.716952Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:35.716952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ajmal Mian, Naveed Akhtar, Nayyer Aafaq, Syed Zulqarnain Gilani, Wei Liu","submitted_at":"2019-02-27T03:52:08Z","abstract_excerpt":"Automatic generation of video captions is a fundamental challenge in computer vision. Recent techniques typically employ a combination of Convolutional Neural Networks (CNNs) and Recursive Neural Networks (RNNs) for video captioning. These methods mainly focus on tailoring sequence learning through RNNs for better caption generation, whereas off-the-shelf visual features are borrowed from CNNs. We argue that careful designing of visual features for this task is equally important, and present a visual feature encoding technique to generate semantically rich captions using Gated Recurrent Units "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10322","kind":"arxiv","version":2},"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":"1902.10322","created_at":"2026-05-17T23:47:35.717019+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.10322v2","created_at":"2026-05-17T23:47:35.717019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10322","created_at":"2026-05-17T23:47:35.717019+00:00"},{"alias_kind":"pith_short_12","alias_value":"U2YSPGRZWWJU","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"U2YSPGRZWWJUWKKC","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"U2YSPGRZ","created_at":"2026-05-18T12:33:30.264802+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/U2YSPGRZWWJUWKKCUCXQJ5ITWC","json":"https://pith.science/pith/U2YSPGRZWWJUWKKCUCXQJ5ITWC.json","graph_json":"https://pith.science/api/pith-number/U2YSPGRZWWJUWKKCUCXQJ5ITWC/graph.json","events_json":"https://pith.science/api/pith-number/U2YSPGRZWWJUWKKCUCXQJ5ITWC/events.json","paper":"https://pith.science/paper/U2YSPGRZ"},"agent_actions":{"view_html":"https://pith.science/pith/U2YSPGRZWWJUWKKCUCXQJ5ITWC","download_json":"https://pith.science/pith/U2YSPGRZWWJUWKKCUCXQJ5ITWC.json","view_paper":"https://pith.science/paper/U2YSPGRZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.10322&json=true","fetch_graph":"https://pith.science/api/pith-number/U2YSPGRZWWJUWKKCUCXQJ5ITWC/graph.json","fetch_events":"https://pith.science/api/pith-number/U2YSPGRZWWJUWKKCUCXQJ5ITWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U2YSPGRZWWJUWKKCUCXQJ5ITWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U2YSPGRZWWJUWKKCUCXQJ5ITWC/action/storage_attestation","attest_author":"https://pith.science/pith/U2YSPGRZWWJUWKKCUCXQJ5ITWC/action/author_attestation","sign_citation":"https://pith.science/pith/U2YSPGRZWWJUWKKCUCXQJ5ITWC/action/citation_signature","submit_replication":"https://pith.science/pith/U2YSPGRZWWJUWKKCUCXQJ5ITWC/action/replication_record"}},"created_at":"2026-05-17T23:47:35.717019+00:00","updated_at":"2026-05-17T23:47:35.717019+00:00"}