{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:F67KROBVTN46KPTPEOOGOZKRTU","short_pith_number":"pith:F67KROBV","schema_version":"1.0","canonical_sha256":"2fbea8b8359b79e53e6f239c6765519d354944fd3e37f39b19de53cb04a4443c","source":{"kind":"arxiv","id":"2003.03715","version":5},"attestation_state":"computed","paper":{"title":"OVC-Net: Object-Oriented Video Captioning with Temporal Graph and Detail Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangyi Zhu, Guang Chen, Jenq-Neng Hwang, Jun Guo, Zhanyu Ma","submitted_at":"2020-03-08T04:34:58Z","abstract_excerpt":"Traditional video captioning requests a holistic description of the video, yet the detailed descriptions of the specific objects may not be available. Without associating the moving trajectories, these image-based data-driven methods cannot understand the activities from the spatio-temporal transitions in the inter-object visual features. Besides, adopting ambiguous clip-sentence pairs in training, it goes against learning the multi-modal functional mappings owing to the one-to-many nature. In this paper, we propose a novel task to understand the videos in object-level, named object-oriented v"},"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":"2003.03715","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-08T04:34:58Z","cross_cats_sorted":[],"title_canon_sha256":"29b078b52d79f262fd88115ecd57e18ce8ad3c80c4ffccc9192655f539ed9617","abstract_canon_sha256":"3b1ac68a4f49cc39c3f3a87fb3c73316bff8affc3550f453f8b7f01b205b109a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:18:55.102464Z","signature_b64":"KvjBelkmh/4J9IxHB0u6TOaUfcvRZ8MOYFdgaTxYHx0IQf+6A9L6+I8v5cDAjU5lzLrq9ZoUm5XJZ/d5olr1DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fbea8b8359b79e53e6f239c6765519d354944fd3e37f39b19de53cb04a4443c","last_reissued_at":"2026-07-05T01:18:55.101985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:18:55.101985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OVC-Net: Object-Oriented Video Captioning with Temporal Graph and Detail Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangyi Zhu, Guang Chen, Jenq-Neng Hwang, Jun Guo, Zhanyu Ma","submitted_at":"2020-03-08T04:34:58Z","abstract_excerpt":"Traditional video captioning requests a holistic description of the video, yet the detailed descriptions of the specific objects may not be available. Without associating the moving trajectories, these image-based data-driven methods cannot understand the activities from the spatio-temporal transitions in the inter-object visual features. Besides, adopting ambiguous clip-sentence pairs in training, it goes against learning the multi-modal functional mappings owing to the one-to-many nature. In this paper, we propose a novel task to understand the videos in object-level, named object-oriented v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.03715","kind":"arxiv","version":5},"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/2003.03715/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":"2003.03715","created_at":"2026-07-05T01:18:55.102038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.03715v5","created_at":"2026-07-05T01:18:55.102038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.03715","created_at":"2026-07-05T01:18:55.102038+00:00"},{"alias_kind":"pith_short_12","alias_value":"F67KROBVTN46","created_at":"2026-07-05T01:18:55.102038+00:00"},{"alias_kind":"pith_short_16","alias_value":"F67KROBVTN46KPTP","created_at":"2026-07-05T01:18:55.102038+00:00"},{"alias_kind":"pith_short_8","alias_value":"F67KROBV","created_at":"2026-07-05T01:18:55.102038+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18531","citing_title":"IntentVCNet: Bridging Spatio-Temporal Gaps for Intention-Oriented Controllable Video Captioning","ref_index":64,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F67KROBVTN46KPTPEOOGOZKRTU","json":"https://pith.science/pith/F67KROBVTN46KPTPEOOGOZKRTU.json","graph_json":"https://pith.science/api/pith-number/F67KROBVTN46KPTPEOOGOZKRTU/graph.json","events_json":"https://pith.science/api/pith-number/F67KROBVTN46KPTPEOOGOZKRTU/events.json","paper":"https://pith.science/paper/F67KROBV"},"agent_actions":{"view_html":"https://pith.science/pith/F67KROBVTN46KPTPEOOGOZKRTU","download_json":"https://pith.science/pith/F67KROBVTN46KPTPEOOGOZKRTU.json","view_paper":"https://pith.science/paper/F67KROBV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.03715&json=true","fetch_graph":"https://pith.science/api/pith-number/F67KROBVTN46KPTPEOOGOZKRTU/graph.json","fetch_events":"https://pith.science/api/pith-number/F67KROBVTN46KPTPEOOGOZKRTU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F67KROBVTN46KPTPEOOGOZKRTU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F67KROBVTN46KPTPEOOGOZKRTU/action/storage_attestation","attest_author":"https://pith.science/pith/F67KROBVTN46KPTPEOOGOZKRTU/action/author_attestation","sign_citation":"https://pith.science/pith/F67KROBVTN46KPTPEOOGOZKRTU/action/citation_signature","submit_replication":"https://pith.science/pith/F67KROBVTN46KPTPEOOGOZKRTU/action/replication_record"}},"created_at":"2026-07-05T01:18:55.102038+00:00","updated_at":"2026-07-05T01:18:55.102038+00:00"}