{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4V33B2RI4JWG535RI4MGRIEYNH","short_pith_number":"pith:4V33B2RI","schema_version":"1.0","canonical_sha256":"e577b0ea28e26c6eefb1471868a09869f49d681d9b4ccad5227196be693049d6","source":{"kind":"arxiv","id":"2301.13606","version":1},"attestation_state":"computed","paper":{"title":"Multi-video Moment Ranking with Multimodal Clue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Danyang Hou, Huawei Shen, Liang Pang, Xueqi Cheng, Yanyan Lan","submitted_at":"2023-01-29T18:38:13Z","abstract_excerpt":"Video corpus moment retrieval~(VCMR) is the task of retrieving a relevant video moment from a large corpus of untrimmed videos via a natural language query. State-of-the-art work for VCMR is based on two-stage method. In this paper, we focus on improving two problems of two-stage method: (1) Moment prediction bias: The predicted moments for most queries come from the top retrieved videos, ignoring the possibility that the target moment is in the bottom retrieved videos, which is caused by the inconsistency of Shared Normalization during training and inference. (2) Latent key content: Different"},"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":"2301.13606","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-29T18:38:13Z","cross_cats_sorted":[],"title_canon_sha256":"9441a4e97521d3ec28842762f772f9c31187b5000508a6bc347f828491ac53fb","abstract_canon_sha256":"e4287778ab1f262f249aea62dad98db5bd896200bdae6525af82fc488ff324da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:37:16.705102Z","signature_b64":"JWkRZ7JYIzqKIbqrurXPV8arfFAYBnm+SK9lXyGhmdsgQR55aP64y6e48MLdqzfyN+nVpdSyTcYem9n5hazLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e577b0ea28e26c6eefb1471868a09869f49d681d9b4ccad5227196be693049d6","last_reissued_at":"2026-07-05T05:37:16.704553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:37:16.704553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-video Moment Ranking with Multimodal Clue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Danyang Hou, Huawei Shen, Liang Pang, Xueqi Cheng, Yanyan Lan","submitted_at":"2023-01-29T18:38:13Z","abstract_excerpt":"Video corpus moment retrieval~(VCMR) is the task of retrieving a relevant video moment from a large corpus of untrimmed videos via a natural language query. State-of-the-art work for VCMR is based on two-stage method. In this paper, we focus on improving two problems of two-stage method: (1) Moment prediction bias: The predicted moments for most queries come from the top retrieved videos, ignoring the possibility that the target moment is in the bottom retrieved videos, which is caused by the inconsistency of Shared Normalization during training and inference. (2) Latent key content: Different"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13606","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2301.13606/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":"2301.13606","created_at":"2026-07-05T05:37:16.704610+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13606v1","created_at":"2026-07-05T05:37:16.704610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13606","created_at":"2026-07-05T05:37:16.704610+00:00"},{"alias_kind":"pith_short_12","alias_value":"4V33B2RI4JWG","created_at":"2026-07-05T05:37:16.704610+00:00"},{"alias_kind":"pith_short_16","alias_value":"4V33B2RI4JWG535R","created_at":"2026-07-05T05:37:16.704610+00:00"},{"alias_kind":"pith_short_8","alias_value":"4V33B2RI","created_at":"2026-07-05T05:37:16.704610+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/4V33B2RI4JWG535RI4MGRIEYNH","json":"https://pith.science/pith/4V33B2RI4JWG535RI4MGRIEYNH.json","graph_json":"https://pith.science/api/pith-number/4V33B2RI4JWG535RI4MGRIEYNH/graph.json","events_json":"https://pith.science/api/pith-number/4V33B2RI4JWG535RI4MGRIEYNH/events.json","paper":"https://pith.science/paper/4V33B2RI"},"agent_actions":{"view_html":"https://pith.science/pith/4V33B2RI4JWG535RI4MGRIEYNH","download_json":"https://pith.science/pith/4V33B2RI4JWG535RI4MGRIEYNH.json","view_paper":"https://pith.science/paper/4V33B2RI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13606&json=true","fetch_graph":"https://pith.science/api/pith-number/4V33B2RI4JWG535RI4MGRIEYNH/graph.json","fetch_events":"https://pith.science/api/pith-number/4V33B2RI4JWG535RI4MGRIEYNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4V33B2RI4JWG535RI4MGRIEYNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4V33B2RI4JWG535RI4MGRIEYNH/action/storage_attestation","attest_author":"https://pith.science/pith/4V33B2RI4JWG535RI4MGRIEYNH/action/author_attestation","sign_citation":"https://pith.science/pith/4V33B2RI4JWG535RI4MGRIEYNH/action/citation_signature","submit_replication":"https://pith.science/pith/4V33B2RI4JWG535RI4MGRIEYNH/action/replication_record"}},"created_at":"2026-07-05T05:37:16.704610+00:00","updated_at":"2026-07-05T05:37:16.704610+00:00"}