{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VW6PVMI3WWZKOWFROGZ4MQB646","short_pith_number":"pith:VW6PVMI3","schema_version":"1.0","canonical_sha256":"adbcfab11bb5b2a758b171b3c6403ee7834e1d03629f7932a0befd215da694c4","source":{"kind":"arxiv","id":"1705.00754","version":1},"attestation_state":"computed","paper":{"title":"Dense-Captioning Events in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Frederic Ren, Juan Carlos Niebles, Kenji Hata, Li Fei-Fei, Ranjay Krishna","submitted_at":"2017-05-02T01:21:58Z","abstract_excerpt":"Most natural videos contain numerous events. For example, in a video of a \"man playing a piano\", the video might also contain \"another man dancing\" or \"a crowd clapping\". We introduce the task of dense-captioning events, which involves both detecting and describing events in a video. We propose a new model that is able to identify all events in a single pass of the video while simultaneously describing the detected events with natural language. Our model introduces a variant of an existing proposal module that is designed to capture both short as well as long events that span minutes. To captu"},"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":"1705.00754","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-02T01:21:58Z","cross_cats_sorted":[],"title_canon_sha256":"f12c11d108cdff2d5b1e46b19bf2ae215d90dbd7defcbfa597d8e51ae63f2e11","abstract_canon_sha256":"bd0e79d772f996c6efaa5fc5a0e24e4342f1c0281d5e6cb7d72aa3ab2cd6c262"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:09.934509Z","signature_b64":"GfbjMtY6kP1yp+S8C0xSZ75Ds4DxyT2U4tCSluojzzqX2CC3unfXhZKLSCHefeO2/PPwnTYfopboOfSeEUn6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adbcfab11bb5b2a758b171b3c6403ee7834e1d03629f7932a0befd215da694c4","last_reissued_at":"2026-05-18T00:45:09.933837Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:09.933837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dense-Captioning Events in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Frederic Ren, Juan Carlos Niebles, Kenji Hata, Li Fei-Fei, Ranjay Krishna","submitted_at":"2017-05-02T01:21:58Z","abstract_excerpt":"Most natural videos contain numerous events. For example, in a video of a \"man playing a piano\", the video might also contain \"another man dancing\" or \"a crowd clapping\". We introduce the task of dense-captioning events, which involves both detecting and describing events in a video. We propose a new model that is able to identify all events in a single pass of the video while simultaneously describing the detected events with natural language. Our model introduces a variant of an existing proposal module that is designed to capture both short as well as long events that span minutes. To captu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.00754","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":""},"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":"1705.00754","created_at":"2026-05-18T00:45:09.933958+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.00754v1","created_at":"2026-05-18T00:45:09.933958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.00754","created_at":"2026-05-18T00:45:09.933958+00:00"},{"alias_kind":"pith_short_12","alias_value":"VW6PVMI3WWZK","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VW6PVMI3WWZKOWFR","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VW6PVMI3","created_at":"2026-05-18T12:31:49.984773+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/VW6PVMI3WWZKOWFROGZ4MQB646","json":"https://pith.science/pith/VW6PVMI3WWZKOWFROGZ4MQB646.json","graph_json":"https://pith.science/api/pith-number/VW6PVMI3WWZKOWFROGZ4MQB646/graph.json","events_json":"https://pith.science/api/pith-number/VW6PVMI3WWZKOWFROGZ4MQB646/events.json","paper":"https://pith.science/paper/VW6PVMI3"},"agent_actions":{"view_html":"https://pith.science/pith/VW6PVMI3WWZKOWFROGZ4MQB646","download_json":"https://pith.science/pith/VW6PVMI3WWZKOWFROGZ4MQB646.json","view_paper":"https://pith.science/paper/VW6PVMI3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.00754&json=true","fetch_graph":"https://pith.science/api/pith-number/VW6PVMI3WWZKOWFROGZ4MQB646/graph.json","fetch_events":"https://pith.science/api/pith-number/VW6PVMI3WWZKOWFROGZ4MQB646/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VW6PVMI3WWZKOWFROGZ4MQB646/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VW6PVMI3WWZKOWFROGZ4MQB646/action/storage_attestation","attest_author":"https://pith.science/pith/VW6PVMI3WWZKOWFROGZ4MQB646/action/author_attestation","sign_citation":"https://pith.science/pith/VW6PVMI3WWZKOWFROGZ4MQB646/action/citation_signature","submit_replication":"https://pith.science/pith/VW6PVMI3WWZKOWFROGZ4MQB646/action/replication_record"}},"created_at":"2026-05-18T00:45:09.933958+00:00","updated_at":"2026-05-18T00:45:09.933958+00:00"}