{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:Z6YYHNT2P5NHIEN2VNEG5NVKBP","short_pith_number":"pith:Z6YYHNT2","schema_version":"1.0","canonical_sha256":"cfb183b67a7f5a7411baab486eb6aa0bf54efd5c66fe7f6e897e6904fdce003b","source":{"kind":"arxiv","id":"2006.11693","version":2},"attestation_state":"computed","paper":{"title":"Dense-Captioning Events in Videos: SYSU Submission to ActivityNet Challenge 2020","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huicheng Zheng, Mingjing Yu, Teng Wang","submitted_at":"2020-06-21T02:38:59Z","abstract_excerpt":"This technical report presents a brief description of our submission to the dense video captioning task of ActivityNet Challenge 2020. Our approach follows a two-stage pipeline: first, we extract a set of temporal event proposals; then we propose a multi-event captioning model to capture the event-level temporal relationships and effectively fuse the multi-modal information. Our approach achieves a 9.28 METEOR score on the test set."},"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":"2006.11693","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-21T02:38:59Z","cross_cats_sorted":[],"title_canon_sha256":"4f1ae6a34bd2a6a6f7c4f3c81a1fee9f11afa982f824ece3b8741708e5e62801","abstract_canon_sha256":"82bef743656e047105480aeb59534a0e859d28fedef04fb82c530b0348274b9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:41.983913Z","signature_b64":"XXn09r9WV7g1Ns275GM7EPpjOsXtygHP04Vv19Omrp30Ysdn9RPuZPqQTcY8WmnP/hKmCLIKInzY0yidPsepCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfb183b67a7f5a7411baab486eb6aa0bf54efd5c66fe7f6e897e6904fdce003b","last_reissued_at":"2026-07-05T01:26:41.983464Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:41.983464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dense-Captioning Events in Videos: SYSU Submission to ActivityNet Challenge 2020","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huicheng Zheng, Mingjing Yu, Teng Wang","submitted_at":"2020-06-21T02:38:59Z","abstract_excerpt":"This technical report presents a brief description of our submission to the dense video captioning task of ActivityNet Challenge 2020. Our approach follows a two-stage pipeline: first, we extract a set of temporal event proposals; then we propose a multi-event captioning model to capture the event-level temporal relationships and effectively fuse the multi-modal information. Our approach achieves a 9.28 METEOR score on the test set."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11693","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.11693/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":"2006.11693","created_at":"2026-07-05T01:26:41.983521+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.11693v2","created_at":"2026-07-05T01:26:41.983521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11693","created_at":"2026-07-05T01:26:41.983521+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z6YYHNT2P5NH","created_at":"2026-07-05T01:26:41.983521+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z6YYHNT2P5NHIEN2","created_at":"2026-07-05T01:26:41.983521+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z6YYHNT2","created_at":"2026-07-05T01:26:41.983521+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04602","citing_title":"Sali4Vid: Saliency-Aware Video Reweighting and Adaptive Caption Retrieval for Dense Video Captioning","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z6YYHNT2P5NHIEN2VNEG5NVKBP","json":"https://pith.science/pith/Z6YYHNT2P5NHIEN2VNEG5NVKBP.json","graph_json":"https://pith.science/api/pith-number/Z6YYHNT2P5NHIEN2VNEG5NVKBP/graph.json","events_json":"https://pith.science/api/pith-number/Z6YYHNT2P5NHIEN2VNEG5NVKBP/events.json","paper":"https://pith.science/paper/Z6YYHNT2"},"agent_actions":{"view_html":"https://pith.science/pith/Z6YYHNT2P5NHIEN2VNEG5NVKBP","download_json":"https://pith.science/pith/Z6YYHNT2P5NHIEN2VNEG5NVKBP.json","view_paper":"https://pith.science/paper/Z6YYHNT2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.11693&json=true","fetch_graph":"https://pith.science/api/pith-number/Z6YYHNT2P5NHIEN2VNEG5NVKBP/graph.json","fetch_events":"https://pith.science/api/pith-number/Z6YYHNT2P5NHIEN2VNEG5NVKBP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z6YYHNT2P5NHIEN2VNEG5NVKBP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z6YYHNT2P5NHIEN2VNEG5NVKBP/action/storage_attestation","attest_author":"https://pith.science/pith/Z6YYHNT2P5NHIEN2VNEG5NVKBP/action/author_attestation","sign_citation":"https://pith.science/pith/Z6YYHNT2P5NHIEN2VNEG5NVKBP/action/citation_signature","submit_replication":"https://pith.science/pith/Z6YYHNT2P5NHIEN2VNEG5NVKBP/action/replication_record"}},"created_at":"2026-07-05T01:26:41.983521+00:00","updated_at":"2026-07-05T01:26:41.983521+00:00"}