{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:N7PYMJ6NGCIALW5GQY5MMAXL62","short_pith_number":"pith:N7PYMJ6N","schema_version":"1.0","canonical_sha256":"6fdf8627cd309005dba6863ac602ebf6bcc0c259221da40ab0ce5cadcf6e552f","source":{"kind":"arxiv","id":"1907.05092","version":1},"attestation_state":"computed","paper":{"title":"Activitynet 2019 Task 3: Exploring Contexts for Dense Captioning Events in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Hauptmann, Bei Liu, Jianlong Fu, Qin Jin, Shizhe Chen, Yida Zhao, Yuqing Song, Zhaoyang Zeng","submitted_at":"2019-07-11T10:29:04Z","abstract_excerpt":"Contextual reasoning is essential to understand events in long untrimmed videos. In this work, we systematically explore different captioning models with various contexts for the dense-captioning events in video task, which aims to generate captions for different events in the untrimmed video. We propose five types of contexts as well as two categories of event captioning models, and evaluate their contributions for event captioning from both accuracy and diversity aspects. The proposed captioning models are plugged into our pipeline system for the dense video captioning challenge. The overall"},"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":"1907.05092","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-11T10:29:04Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"0ff307e05130212eea716478111130279dfa1b6c2859e7718fd67a5a93d547ba","abstract_canon_sha256":"b87f483cd35dab17dfff70d921e73554e0faeb847706d51198802e7319e40831"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:53.975493Z","signature_b64":"LoibCaLY+q5I35bZTQh/KcjogdYpRhD5GXcM3BY8Jzg9ENnRQ07SApYe+9wjD05WuvBxey/3GvNAlhMr5RoOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fdf8627cd309005dba6863ac602ebf6bcc0c259221da40ab0ce5cadcf6e552f","last_reissued_at":"2026-05-17T23:40:53.974763Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:53.974763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Activitynet 2019 Task 3: Exploring Contexts for Dense Captioning Events in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Hauptmann, Bei Liu, Jianlong Fu, Qin Jin, Shizhe Chen, Yida Zhao, Yuqing Song, Zhaoyang Zeng","submitted_at":"2019-07-11T10:29:04Z","abstract_excerpt":"Contextual reasoning is essential to understand events in long untrimmed videos. In this work, we systematically explore different captioning models with various contexts for the dense-captioning events in video task, which aims to generate captions for different events in the untrimmed video. We propose five types of contexts as well as two categories of event captioning models, and evaluate their contributions for event captioning from both accuracy and diversity aspects. The proposed captioning models are plugged into our pipeline system for the dense video captioning challenge. The overall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.05092","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":"1907.05092","created_at":"2026-05-17T23:40:53.974866+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.05092v1","created_at":"2026-05-17T23:40:53.974866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05092","created_at":"2026-05-17T23:40:53.974866+00:00"},{"alias_kind":"pith_short_12","alias_value":"N7PYMJ6NGCIA","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"N7PYMJ6NGCIALW5G","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"N7PYMJ6N","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.17574","citing_title":"HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized Benchmarks","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N7PYMJ6NGCIALW5GQY5MMAXL62","json":"https://pith.science/pith/N7PYMJ6NGCIALW5GQY5MMAXL62.json","graph_json":"https://pith.science/api/pith-number/N7PYMJ6NGCIALW5GQY5MMAXL62/graph.json","events_json":"https://pith.science/api/pith-number/N7PYMJ6NGCIALW5GQY5MMAXL62/events.json","paper":"https://pith.science/paper/N7PYMJ6N"},"agent_actions":{"view_html":"https://pith.science/pith/N7PYMJ6NGCIALW5GQY5MMAXL62","download_json":"https://pith.science/pith/N7PYMJ6NGCIALW5GQY5MMAXL62.json","view_paper":"https://pith.science/paper/N7PYMJ6N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.05092&json=true","fetch_graph":"https://pith.science/api/pith-number/N7PYMJ6NGCIALW5GQY5MMAXL62/graph.json","fetch_events":"https://pith.science/api/pith-number/N7PYMJ6NGCIALW5GQY5MMAXL62/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N7PYMJ6NGCIALW5GQY5MMAXL62/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N7PYMJ6NGCIALW5GQY5MMAXL62/action/storage_attestation","attest_author":"https://pith.science/pith/N7PYMJ6NGCIALW5GQY5MMAXL62/action/author_attestation","sign_citation":"https://pith.science/pith/N7PYMJ6NGCIALW5GQY5MMAXL62/action/citation_signature","submit_replication":"https://pith.science/pith/N7PYMJ6NGCIALW5GQY5MMAXL62/action/replication_record"}},"created_at":"2026-05-17T23:40:53.974866+00:00","updated_at":"2026-05-17T23:40:53.974866+00:00"}