{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DICSPAHQJIDRPX7RSEK4OEXKQP","short_pith_number":"pith:DICSPAHQ","schema_version":"1.0","canonical_sha256":"1a052780f04a0717dff19115c712ea83ed31d6d8f3753b1c7f1f642206b274d8","source":{"kind":"arxiv","id":"2412.12791","version":2},"attestation_state":"computed","paper":{"title":"Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Liu Qin, Qiang Chen, Qing Gu, Shiping Ge, Yafeng Yin, Zhiwei Jiang, Ziyao Chen","submitted_at":"2024-12-17T10:52:50Z","abstract_excerpt":"Weakly-Supervised Dense Video Captioning (WSDVC) aims to localize and describe all events of interest in a video without requiring annotations of event boundaries. This setting poses a great challenge in accurately locating the temporal location of event, as the relevant supervision is unavailable. Existing methods rely on explicit alignment constraints between event locations and captions, which involve complex event proposal procedures during both training and inference. To tackle this problem, we propose a novel implicit location-caption alignment paradigm by complementary masking, which si"},"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":"2412.12791","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T10:52:50Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"3160f3a0f6d96fb42d3377ff83955aa9bc804eed401101a85f9705f081fe2526","abstract_canon_sha256":"150b5524ffa1333fff571619edaa7845b7107af8e0d8898fd49046c380e05a48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:47.302333Z","signature_b64":"3mkBs6rCLrlb+hegi8kpEC2XHR3CxQLizahqNYirnArl0Qn0py6fS9vf1CecaGdL2mWoQlqx1swZ9pokiPN3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a052780f04a0717dff19115c712ea83ed31d6d8f3753b1c7f1f642206b274d8","last_reissued_at":"2026-07-05T10:05:47.301572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:47.301572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Liu Qin, Qiang Chen, Qing Gu, Shiping Ge, Yafeng Yin, Zhiwei Jiang, Ziyao Chen","submitted_at":"2024-12-17T10:52:50Z","abstract_excerpt":"Weakly-Supervised Dense Video Captioning (WSDVC) aims to localize and describe all events of interest in a video without requiring annotations of event boundaries. This setting poses a great challenge in accurately locating the temporal location of event, as the relevant supervision is unavailable. Existing methods rely on explicit alignment constraints between event locations and captions, which involve complex event proposal procedures during both training and inference. To tackle this problem, we propose a novel implicit location-caption alignment paradigm by complementary masking, which si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12791","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/2412.12791/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":"2412.12791","created_at":"2026-07-05T10:05:47.301666+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12791v2","created_at":"2026-07-05T10:05:47.301666+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12791","created_at":"2026-07-05T10:05:47.301666+00:00"},{"alias_kind":"pith_short_12","alias_value":"DICSPAHQJIDR","created_at":"2026-07-05T10:05:47.301666+00:00"},{"alias_kind":"pith_short_16","alias_value":"DICSPAHQJIDRPX7R","created_at":"2026-07-05T10:05:47.301666+00:00"},{"alias_kind":"pith_short_8","alias_value":"DICSPAHQ","created_at":"2026-07-05T10:05:47.301666+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/DICSPAHQJIDRPX7RSEK4OEXKQP","json":"https://pith.science/pith/DICSPAHQJIDRPX7RSEK4OEXKQP.json","graph_json":"https://pith.science/api/pith-number/DICSPAHQJIDRPX7RSEK4OEXKQP/graph.json","events_json":"https://pith.science/api/pith-number/DICSPAHQJIDRPX7RSEK4OEXKQP/events.json","paper":"https://pith.science/paper/DICSPAHQ"},"agent_actions":{"view_html":"https://pith.science/pith/DICSPAHQJIDRPX7RSEK4OEXKQP","download_json":"https://pith.science/pith/DICSPAHQJIDRPX7RSEK4OEXKQP.json","view_paper":"https://pith.science/paper/DICSPAHQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12791&json=true","fetch_graph":"https://pith.science/api/pith-number/DICSPAHQJIDRPX7RSEK4OEXKQP/graph.json","fetch_events":"https://pith.science/api/pith-number/DICSPAHQJIDRPX7RSEK4OEXKQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DICSPAHQJIDRPX7RSEK4OEXKQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DICSPAHQJIDRPX7RSEK4OEXKQP/action/storage_attestation","attest_author":"https://pith.science/pith/DICSPAHQJIDRPX7RSEK4OEXKQP/action/author_attestation","sign_citation":"https://pith.science/pith/DICSPAHQJIDRPX7RSEK4OEXKQP/action/citation_signature","submit_replication":"https://pith.science/pith/DICSPAHQJIDRPX7RSEK4OEXKQP/action/replication_record"}},"created_at":"2026-07-05T10:05:47.301666+00:00","updated_at":"2026-07-05T10:05:47.301666+00:00"}