{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PDBYOXSXRJP444ZMJLWIK522YE","short_pith_number":"pith:PDBYOXSX","schema_version":"1.0","canonical_sha256":"78c3875e578a5fce732c4aec85775ac12c0792fc9202c91b8ac96a861265180d","source":{"kind":"arxiv","id":"2003.07758","version":2},"attestation_state":"computed","paper":{"title":"Multi-modal Dense Video Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD","eess.AS","eess.IV"],"primary_cat":"cs.CV","authors_text":"Esa Rahtu, Vladimir Iashin","submitted_at":"2020-03-17T15:15:17Z","abstract_excerpt":"Dense video captioning is a task of localizing interesting events from an untrimmed video and producing textual description (captions) for each localized event. Most of the previous works in dense video captioning are solely based on visual information and completely ignore the audio track. However, audio, and speech, in particular, are vital cues for a human observer in understanding an environment. In this paper, we present a new dense video captioning approach that is able to utilize any number of modalities for event description. Specifically, we show how audio and speech modalities may im"},"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":"2003.07758","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-03-17T15:15:17Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD","eess.AS","eess.IV"],"title_canon_sha256":"99f20e9ad4516d6a7172d426bb801da3ace56e6f92a35d2984f290c1a2c31319","abstract_canon_sha256":"78b4eb69cb060aad53af684d586b93bd0dbef58db59e07ce9f3f2a76725e58eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:50.434551Z","signature_b64":"AKIcxXTOk9sOoC2bi17dfed/0BNGC4czV+jMAmwHIJgBfBgS2tK8BHZBZDpHuwTW4o+k1bx0TWNehjHqM5ojDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78c3875e578a5fce732c4aec85775ac12c0792fc9202c91b8ac96a861265180d","last_reissued_at":"2026-07-05T01:00:50.434173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:50.434173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-modal Dense Video Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD","eess.AS","eess.IV"],"primary_cat":"cs.CV","authors_text":"Esa Rahtu, Vladimir Iashin","submitted_at":"2020-03-17T15:15:17Z","abstract_excerpt":"Dense video captioning is a task of localizing interesting events from an untrimmed video and producing textual description (captions) for each localized event. Most of the previous works in dense video captioning are solely based on visual information and completely ignore the audio track. However, audio, and speech, in particular, are vital cues for a human observer in understanding an environment. In this paper, we present a new dense video captioning approach that is able to utilize any number of modalities for event description. Specifically, we show how audio and speech modalities may im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.07758","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/2003.07758/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":"2003.07758","created_at":"2026-07-05T01:00:50.434229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.07758v2","created_at":"2026-07-05T01:00:50.434229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.07758","created_at":"2026-07-05T01:00:50.434229+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDBYOXSXRJP4","created_at":"2026-07-05T01:00:50.434229+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDBYOXSXRJP444ZM","created_at":"2026-07-05T01:00:50.434229+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDBYOXSX","created_at":"2026-07-05T01:00:50.434229+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/PDBYOXSXRJP444ZMJLWIK522YE","json":"https://pith.science/pith/PDBYOXSXRJP444ZMJLWIK522YE.json","graph_json":"https://pith.science/api/pith-number/PDBYOXSXRJP444ZMJLWIK522YE/graph.json","events_json":"https://pith.science/api/pith-number/PDBYOXSXRJP444ZMJLWIK522YE/events.json","paper":"https://pith.science/paper/PDBYOXSX"},"agent_actions":{"view_html":"https://pith.science/pith/PDBYOXSXRJP444ZMJLWIK522YE","download_json":"https://pith.science/pith/PDBYOXSXRJP444ZMJLWIK522YE.json","view_paper":"https://pith.science/paper/PDBYOXSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.07758&json=true","fetch_graph":"https://pith.science/api/pith-number/PDBYOXSXRJP444ZMJLWIK522YE/graph.json","fetch_events":"https://pith.science/api/pith-number/PDBYOXSXRJP444ZMJLWIK522YE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDBYOXSXRJP444ZMJLWIK522YE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDBYOXSXRJP444ZMJLWIK522YE/action/storage_attestation","attest_author":"https://pith.science/pith/PDBYOXSXRJP444ZMJLWIK522YE/action/author_attestation","sign_citation":"https://pith.science/pith/PDBYOXSXRJP444ZMJLWIK522YE/action/citation_signature","submit_replication":"https://pith.science/pith/PDBYOXSXRJP444ZMJLWIK522YE/action/replication_record"}},"created_at":"2026-07-05T01:00:50.434229+00:00","updated_at":"2026-07-05T01:00:50.434229+00:00"}