{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:OXDSLXXSECWOTAXUOVOZVRM2HR","short_pith_number":"pith:OXDSLXXS","schema_version":"1.0","canonical_sha256":"75c725def220ace982f4755d9ac59a3c6fa7abcba2135246f96ae22feeea7130","source":{"kind":"arxiv","id":"2001.05614","version":3},"attestation_state":"computed","paper":{"title":"Delving Deeper into the Decoder for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Haoran Chen, Jianmin Li, Xiaolin Hu","submitted_at":"2020-01-16T02:18:27Z","abstract_excerpt":"Video captioning is an advanced multi-modal task which aims to describe a video clip using a natural language sentence. The encoder-decoder framework is the most popular paradigm for this task in recent years. However, there exist some problems in the decoder of a video captioning model. We make a thorough investigation into the decoder and adopt three techniques to improve the performance of the model. First of all, a combination of variational dropout and layer normalization is embedded into a recurrent unit to alleviate the problem of overfitting. Secondly, a new online method is proposed t"},"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":"2001.05614","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-16T02:18:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"3c15ac70bb3e128cb2e01a412f2448f23182d82fb6f0a83ee54677b46ac0d4b3","abstract_canon_sha256":"be06d0bfcc9f24fdca2b0b245979ccefe4d46dee070d10e1ae246d5778d3b4f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:40.934611Z","signature_b64":"fExGZELTom1iHt/8iWPFyxL2Gs4a43+mwdlSn/oAeQ6Zdv2hbIEgMiSBsyGL7yukcJzoHj81nC4ezGFKtcXVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75c725def220ace982f4755d9ac59a3c6fa7abcba2135246f96ae22feeea7130","last_reissued_at":"2026-07-05T02:14:40.934119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:40.934119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Delving Deeper into the Decoder for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Haoran Chen, Jianmin Li, Xiaolin Hu","submitted_at":"2020-01-16T02:18:27Z","abstract_excerpt":"Video captioning is an advanced multi-modal task which aims to describe a video clip using a natural language sentence. The encoder-decoder framework is the most popular paradigm for this task in recent years. However, there exist some problems in the decoder of a video captioning model. We make a thorough investigation into the decoder and adopt three techniques to improve the performance of the model. First of all, a combination of variational dropout and layer normalization is embedded into a recurrent unit to alleviate the problem of overfitting. Secondly, a new online method is proposed t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.05614","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2001.05614/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2001.05614","created_at":"2026-07-05T02:14:40.934177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.05614v3","created_at":"2026-07-05T02:14:40.934177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.05614","created_at":"2026-07-05T02:14:40.934177+00:00"},{"alias_kind":"pith_short_12","alias_value":"OXDSLXXSECWO","created_at":"2026-07-05T02:14:40.934177+00:00"},{"alias_kind":"pith_short_16","alias_value":"OXDSLXXSECWOTAXU","created_at":"2026-07-05T02:14:40.934177+00:00"},{"alias_kind":"pith_short_8","alias_value":"OXDSLXXS","created_at":"2026-07-05T02:14:40.934177+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.11013","citing_title":"Watching Synthetic Videos: Aligning Cross-modal Representations with Visual Synthesis for Zero-shot Video Captioning","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OXDSLXXSECWOTAXUOVOZVRM2HR","json":"https://pith.science/pith/OXDSLXXSECWOTAXUOVOZVRM2HR.json","graph_json":"https://pith.science/api/pith-number/OXDSLXXSECWOTAXUOVOZVRM2HR/graph.json","events_json":"https://pith.science/api/pith-number/OXDSLXXSECWOTAXUOVOZVRM2HR/events.json","paper":"https://pith.science/paper/OXDSLXXS"},"agent_actions":{"view_html":"https://pith.science/pith/OXDSLXXSECWOTAXUOVOZVRM2HR","download_json":"https://pith.science/pith/OXDSLXXSECWOTAXUOVOZVRM2HR.json","view_paper":"https://pith.science/paper/OXDSLXXS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.05614&json=true","fetch_graph":"https://pith.science/api/pith-number/OXDSLXXSECWOTAXUOVOZVRM2HR/graph.json","fetch_events":"https://pith.science/api/pith-number/OXDSLXXSECWOTAXUOVOZVRM2HR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OXDSLXXSECWOTAXUOVOZVRM2HR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OXDSLXXSECWOTAXUOVOZVRM2HR/action/storage_attestation","attest_author":"https://pith.science/pith/OXDSLXXSECWOTAXUOVOZVRM2HR/action/author_attestation","sign_citation":"https://pith.science/pith/OXDSLXXSECWOTAXUOVOZVRM2HR/action/citation_signature","submit_replication":"https://pith.science/pith/OXDSLXXSECWOTAXUOVOZVRM2HR/action/replication_record"}},"created_at":"2026-07-05T02:14:40.934177+00:00","updated_at":"2026-07-05T02:14:40.934177+00:00"}