{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:I3KSDRGEVPDUY34MHOAPBSSNZS","short_pith_number":"pith:I3KSDRGE","schema_version":"1.0","canonical_sha256":"46d521c4c4abc74c6f8c3b80f0ca4dcc8c67fbc08753936a80b7e2021dc1bc32","source":{"kind":"arxiv","id":"2309.11082","version":3},"attestation_state":"computed","paper":{"title":"Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chen Jiang, Hong Liu, Jia Xu, Ming Yang, Qingpei Guo, Qing Wang, Wei Chu, Xuzheng Yu, Yuan Cheng, Yuan Qi, Zhongyi Liu","submitted_at":"2023-09-20T06:08:11Z","abstract_excerpt":"In recent years, the explosion of web videos makes text-video retrieval increasingly essential and popular for video filtering, recommendation, and search. Text-video retrieval aims to rank relevant text/video higher than irrelevant ones. The core of this task is to precisely measure the cross-modal similarity between texts and videos. Recently, contrastive learning methods have shown promising results for text-video retrieval, most of which focus on the construction of positive and negative pairs to learn text and video representations. Nevertheless, they do not pay enough attention to hard n"},"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":"2309.11082","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-20T06:08:11Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"b805348a792916bfee250553c3f62e62f12ed1fbbda88dfa086e69ccc8cd8c38","abstract_canon_sha256":"9484c313aff5e326cc953278a0e0d2a9afc7118c31ca6e5d15c5305e1b25544a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:10.644016Z","signature_b64":"ITY14FHg6etnL3+p/et58ceUxEWBTWh2z6ISnqt3NKUdB92gTX4Uh1kPkNO1JFh+QNIIhyHc/+NhM28fZrfPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46d521c4c4abc74c6f8c3b80f0ca4dcc8c67fbc08753936a80b7e2021dc1bc32","last_reissued_at":"2026-07-05T11:18:10.643502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:10.643502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chen Jiang, Hong Liu, Jia Xu, Ming Yang, Qingpei Guo, Qing Wang, Wei Chu, Xuzheng Yu, Yuan Cheng, Yuan Qi, Zhongyi Liu","submitted_at":"2023-09-20T06:08:11Z","abstract_excerpt":"In recent years, the explosion of web videos makes text-video retrieval increasingly essential and popular for video filtering, recommendation, and search. Text-video retrieval aims to rank relevant text/video higher than irrelevant ones. The core of this task is to precisely measure the cross-modal similarity between texts and videos. Recently, contrastive learning methods have shown promising results for text-video retrieval, most of which focus on the construction of positive and negative pairs to learn text and video representations. Nevertheless, they do not pay enough attention to hard n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11082","kind":"arxiv","version":3},"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/2309.11082/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":"2309.11082","created_at":"2026-07-05T11:18:10.643564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.11082v3","created_at":"2026-07-05T11:18:10.643564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11082","created_at":"2026-07-05T11:18:10.643564+00:00"},{"alias_kind":"pith_short_12","alias_value":"I3KSDRGEVPDU","created_at":"2026-07-05T11:18:10.643564+00:00"},{"alias_kind":"pith_short_16","alias_value":"I3KSDRGEVPDUY34M","created_at":"2026-07-05T11:18:10.643564+00:00"},{"alias_kind":"pith_short_8","alias_value":"I3KSDRGE","created_at":"2026-07-05T11:18:10.643564+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/I3KSDRGEVPDUY34MHOAPBSSNZS","json":"https://pith.science/pith/I3KSDRGEVPDUY34MHOAPBSSNZS.json","graph_json":"https://pith.science/api/pith-number/I3KSDRGEVPDUY34MHOAPBSSNZS/graph.json","events_json":"https://pith.science/api/pith-number/I3KSDRGEVPDUY34MHOAPBSSNZS/events.json","paper":"https://pith.science/paper/I3KSDRGE"},"agent_actions":{"view_html":"https://pith.science/pith/I3KSDRGEVPDUY34MHOAPBSSNZS","download_json":"https://pith.science/pith/I3KSDRGEVPDUY34MHOAPBSSNZS.json","view_paper":"https://pith.science/paper/I3KSDRGE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.11082&json=true","fetch_graph":"https://pith.science/api/pith-number/I3KSDRGEVPDUY34MHOAPBSSNZS/graph.json","fetch_events":"https://pith.science/api/pith-number/I3KSDRGEVPDUY34MHOAPBSSNZS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I3KSDRGEVPDUY34MHOAPBSSNZS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I3KSDRGEVPDUY34MHOAPBSSNZS/action/storage_attestation","attest_author":"https://pith.science/pith/I3KSDRGEVPDUY34MHOAPBSSNZS/action/author_attestation","sign_citation":"https://pith.science/pith/I3KSDRGEVPDUY34MHOAPBSSNZS/action/citation_signature","submit_replication":"https://pith.science/pith/I3KSDRGEVPDUY34MHOAPBSSNZS/action/replication_record"}},"created_at":"2026-07-05T11:18:10.643564+00:00","updated_at":"2026-07-05T11:18:10.643564+00:00"}