{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:R3YCT4AUDP6S5IR7IX4VS6YBVK","short_pith_number":"pith:R3YCT4AU","schema_version":"1.0","canonical_sha256":"8ef029f0141bfd2ea23f45f9597b01aa9b54f97b397e74dc1480751d2f7598a5","source":{"kind":"arxiv","id":"2002.11886","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Memory Decoding for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aming Wu, Yahong Han","submitted_at":"2020-02-27T02:48:10Z","abstract_excerpt":"Recent advances of video captioning often employ a recurrent neural network (RNN) as the decoder. However, RNN is prone to diluting long-term information. Recent works have demonstrated memory network (MemNet) has the advantage of storing long-term information. However, as the decoder, it has not been well exploited for video captioning. The reason partially comes from the difficulty of sequence decoding with MemNet. Instead of the common practice, i.e., sequence decoding with RNN, in this paper, we devise a novel memory decoder for video captioning. Concretely, after obtaining representation "},"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":"2002.11886","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-27T02:48:10Z","cross_cats_sorted":[],"title_canon_sha256":"71564a4a62d3d47a63c93217df837175cb73ea3e78654de8ca7c1fb2592cad30","abstract_canon_sha256":"a0d1473f5ebc3b1095c7c08fb20b0d0f8abe9c1deac289e82a09e651c90bfec4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:09.959817Z","signature_b64":"NHRHeNdZa6GT9Mk89mZQpMVTU6wqll3PJqTvjXyiyFom7ZkXzbptlbKdavxYlAod8TMaPkd6kZwPXhLqkXsGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ef029f0141bfd2ea23f45f9597b01aa9b54f97b397e74dc1480751d2f7598a5","last_reissued_at":"2026-07-05T00:44:09.959400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:09.959400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Memory Decoding for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aming Wu, Yahong Han","submitted_at":"2020-02-27T02:48:10Z","abstract_excerpt":"Recent advances of video captioning often employ a recurrent neural network (RNN) as the decoder. However, RNN is prone to diluting long-term information. Recent works have demonstrated memory network (MemNet) has the advantage of storing long-term information. However, as the decoder, it has not been well exploited for video captioning. The reason partially comes from the difficulty of sequence decoding with MemNet. Instead of the common practice, i.e., sequence decoding with RNN, in this paper, we devise a novel memory decoder for video captioning. Concretely, after obtaining representation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.11886","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.11886/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":"2002.11886","created_at":"2026-07-05T00:44:09.959457+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.11886v1","created_at":"2026-07-05T00:44:09.959457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.11886","created_at":"2026-07-05T00:44:09.959457+00:00"},{"alias_kind":"pith_short_12","alias_value":"R3YCT4AUDP6S","created_at":"2026-07-05T00:44:09.959457+00:00"},{"alias_kind":"pith_short_16","alias_value":"R3YCT4AUDP6S5IR7","created_at":"2026-07-05T00:44:09.959457+00:00"},{"alias_kind":"pith_short_8","alias_value":"R3YCT4AU","created_at":"2026-07-05T00:44:09.959457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.03846","citing_title":"Hardware-Aware Data and Instruction Mapping for AI Tasks: Balancing Parallelism, I/O and Memory Tradeoffs","ref_index":2002,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R3YCT4AUDP6S5IR7IX4VS6YBVK","json":"https://pith.science/pith/R3YCT4AUDP6S5IR7IX4VS6YBVK.json","graph_json":"https://pith.science/api/pith-number/R3YCT4AUDP6S5IR7IX4VS6YBVK/graph.json","events_json":"https://pith.science/api/pith-number/R3YCT4AUDP6S5IR7IX4VS6YBVK/events.json","paper":"https://pith.science/paper/R3YCT4AU"},"agent_actions":{"view_html":"https://pith.science/pith/R3YCT4AUDP6S5IR7IX4VS6YBVK","download_json":"https://pith.science/pith/R3YCT4AUDP6S5IR7IX4VS6YBVK.json","view_paper":"https://pith.science/paper/R3YCT4AU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.11886&json=true","fetch_graph":"https://pith.science/api/pith-number/R3YCT4AUDP6S5IR7IX4VS6YBVK/graph.json","fetch_events":"https://pith.science/api/pith-number/R3YCT4AUDP6S5IR7IX4VS6YBVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R3YCT4AUDP6S5IR7IX4VS6YBVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R3YCT4AUDP6S5IR7IX4VS6YBVK/action/storage_attestation","attest_author":"https://pith.science/pith/R3YCT4AUDP6S5IR7IX4VS6YBVK/action/author_attestation","sign_citation":"https://pith.science/pith/R3YCT4AUDP6S5IR7IX4VS6YBVK/action/citation_signature","submit_replication":"https://pith.science/pith/R3YCT4AUDP6S5IR7IX4VS6YBVK/action/replication_record"}},"created_at":"2026-07-05T00:44:09.959457+00:00","updated_at":"2026-07-05T00:44:09.959457+00:00"}