{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:N3HPCEOSR5IBBAXRKHA7EU4QMO","short_pith_number":"pith:N3HPCEOS","schema_version":"1.0","canonical_sha256":"6ecef111d28f501082f151c1f25390639fc0e0e14ab5ac44d5b77d0df912fb28","source":{"kind":"arxiv","id":"2203.07086","version":1},"attestation_state":"computed","paper":{"title":"MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Kunitsyn, Andrei Ivaniuta, Maksim Dzabraev, Maksim Kalashnikov","submitted_at":"2022-03-14T13:15:09Z","abstract_excerpt":"In this work we present a new State-of-The-Art on the text-to-video retrieval task on MSR-VTT, LSMDC, MSVD, YouCook2 and TGIF obtained by a single model. Three different data sources are combined: weakly-supervised videos, crowd-labeled text-image pairs and text-video pairs. A careful analysis of available pre-trained networks helps to choose the best prior-knowledge ones. We introduce three-stage training procedure that provides high transfer knowledge efficiency and allows to use noisy datasets during training without prior knowledge degradation. Additionally, double positional encoding is u"},"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":"2203.07086","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T13:15:09Z","cross_cats_sorted":[],"title_canon_sha256":"af4da665cde887b93b6b2439a63a602286ec4c88cbad9c8b93a64c9aeab3a2ee","abstract_canon_sha256":"e4a5e2ea6724bda19888c80c4bc57c8798c3fee4a4aa2c5f7f49974b73d5df85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:59.304266Z","signature_b64":"XWBqdY9+MNFE5pGaVnOvtUTtaXpi8+UBOLoyF9p/MhJEl4DjRJiYJ+4EzMTlcvBOy5Oql3AqVE5GGGEH3houAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ecef111d28f501082f151c1f25390639fc0e0e14ab5ac44d5b77d0df912fb28","last_reissued_at":"2026-07-05T04:04:59.303770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:59.303770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Kunitsyn, Andrei Ivaniuta, Maksim Dzabraev, Maksim Kalashnikov","submitted_at":"2022-03-14T13:15:09Z","abstract_excerpt":"In this work we present a new State-of-The-Art on the text-to-video retrieval task on MSR-VTT, LSMDC, MSVD, YouCook2 and TGIF obtained by a single model. Three different data sources are combined: weakly-supervised videos, crowd-labeled text-image pairs and text-video pairs. A careful analysis of available pre-trained networks helps to choose the best prior-knowledge ones. We introduce three-stage training procedure that provides high transfer knowledge efficiency and allows to use noisy datasets during training without prior knowledge degradation. Additionally, double positional encoding is u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.07086","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/2203.07086/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":"2203.07086","created_at":"2026-07-05T04:04:59.303827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.07086v1","created_at":"2026-07-05T04:04:59.303827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.07086","created_at":"2026-07-05T04:04:59.303827+00:00"},{"alias_kind":"pith_short_12","alias_value":"N3HPCEOSR5IB","created_at":"2026-07-05T04:04:59.303827+00:00"},{"alias_kind":"pith_short_16","alias_value":"N3HPCEOSR5IBBAXR","created_at":"2026-07-05T04:04:59.303827+00:00"},{"alias_kind":"pith_short_8","alias_value":"N3HPCEOS","created_at":"2026-07-05T04:04:59.303827+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/N3HPCEOSR5IBBAXRKHA7EU4QMO","json":"https://pith.science/pith/N3HPCEOSR5IBBAXRKHA7EU4QMO.json","graph_json":"https://pith.science/api/pith-number/N3HPCEOSR5IBBAXRKHA7EU4QMO/graph.json","events_json":"https://pith.science/api/pith-number/N3HPCEOSR5IBBAXRKHA7EU4QMO/events.json","paper":"https://pith.science/paper/N3HPCEOS"},"agent_actions":{"view_html":"https://pith.science/pith/N3HPCEOSR5IBBAXRKHA7EU4QMO","download_json":"https://pith.science/pith/N3HPCEOSR5IBBAXRKHA7EU4QMO.json","view_paper":"https://pith.science/paper/N3HPCEOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.07086&json=true","fetch_graph":"https://pith.science/api/pith-number/N3HPCEOSR5IBBAXRKHA7EU4QMO/graph.json","fetch_events":"https://pith.science/api/pith-number/N3HPCEOSR5IBBAXRKHA7EU4QMO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N3HPCEOSR5IBBAXRKHA7EU4QMO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N3HPCEOSR5IBBAXRKHA7EU4QMO/action/storage_attestation","attest_author":"https://pith.science/pith/N3HPCEOSR5IBBAXRKHA7EU4QMO/action/author_attestation","sign_citation":"https://pith.science/pith/N3HPCEOSR5IBBAXRKHA7EU4QMO/action/citation_signature","submit_replication":"https://pith.science/pith/N3HPCEOSR5IBBAXRKHA7EU4QMO/action/replication_record"}},"created_at":"2026-07-05T04:04:59.303827+00:00","updated_at":"2026-07-05T04:04:59.303827+00:00"}