{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YCPY2JL23A4OQI25DZMSMF6NTA","short_pith_number":"pith:YCPY2JL2","schema_version":"1.0","canonical_sha256":"c09f8d257ad838e8235d1e592617cd98136c3d5cb86d81324b06795d19c1610c","source":{"kind":"arxiv","id":"2112.01194","version":2},"attestation_state":"computed","paper":{"title":"Video-Text Pre-training with Learned Regions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Alex Jinpeng Wang, Guanyu Cai, Jinhui Tang, Mike Zheng Shou, Rui Yan, Xudong Lin, Yixiao Ge","submitted_at":"2021-12-02T13:06:53Z","abstract_excerpt":"Video-Text pre-training aims at learning transferable representations from large-scale video-text pairs via aligning the semantics between visual and textual information. State-of-the-art approaches extract visual features from raw pixels in an end-to-end fashion. However, these methods operate at frame-level directly and thus overlook the spatio-temporal structure of objects in video, which yet has a strong synergy with nouns in textual descriptions. In this work, we propose a simple yet effective module for video-text representation learning, namely RegionLearner, which can take into account"},"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":"2112.01194","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-02T13:06:53Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"6a5c4e1b492505ebc3ec19d52a302ab012dcc45c0ee8988a4dfd23777a8bae00","abstract_canon_sha256":"64c9d9d067712d4cbc0611ebe92b95c5856bcf192f0ee8f843e217accdc04da7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:37:48.615426Z","signature_b64":"SuS92WrRcPyrO4X8lPIbC8rtzvMqptM5BWzu+CbuHWj0ROKsFcRjnK7Ts2iVEJim9mtXe91mq+lNfTlzwJXcAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c09f8d257ad838e8235d1e592617cd98136c3d5cb86d81324b06795d19c1610c","last_reissued_at":"2026-07-05T03:37:48.615048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:37:48.615048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video-Text Pre-training with Learned Regions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Alex Jinpeng Wang, Guanyu Cai, Jinhui Tang, Mike Zheng Shou, Rui Yan, Xudong Lin, Yixiao Ge","submitted_at":"2021-12-02T13:06:53Z","abstract_excerpt":"Video-Text pre-training aims at learning transferable representations from large-scale video-text pairs via aligning the semantics between visual and textual information. State-of-the-art approaches extract visual features from raw pixels in an end-to-end fashion. However, these methods operate at frame-level directly and thus overlook the spatio-temporal structure of objects in video, which yet has a strong synergy with nouns in textual descriptions. In this work, we propose a simple yet effective module for video-text representation learning, namely RegionLearner, which can take into account"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01194","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/2112.01194/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":"2112.01194","created_at":"2026-07-05T03:37:48.615099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.01194v2","created_at":"2026-07-05T03:37:48.615099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01194","created_at":"2026-07-05T03:37:48.615099+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCPY2JL23A4O","created_at":"2026-07-05T03:37:48.615099+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCPY2JL23A4OQI25","created_at":"2026-07-05T03:37:48.615099+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCPY2JL2","created_at":"2026-07-05T03:37:48.615099+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00826","citing_title":"Understanding the Performance Plateau in Text-to-Video Retrieval: A Comprehensive Empirical and Linguistic Analysis","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YCPY2JL23A4OQI25DZMSMF6NTA","json":"https://pith.science/pith/YCPY2JL23A4OQI25DZMSMF6NTA.json","graph_json":"https://pith.science/api/pith-number/YCPY2JL23A4OQI25DZMSMF6NTA/graph.json","events_json":"https://pith.science/api/pith-number/YCPY2JL23A4OQI25DZMSMF6NTA/events.json","paper":"https://pith.science/paper/YCPY2JL2"},"agent_actions":{"view_html":"https://pith.science/pith/YCPY2JL23A4OQI25DZMSMF6NTA","download_json":"https://pith.science/pith/YCPY2JL23A4OQI25DZMSMF6NTA.json","view_paper":"https://pith.science/paper/YCPY2JL2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.01194&json=true","fetch_graph":"https://pith.science/api/pith-number/YCPY2JL23A4OQI25DZMSMF6NTA/graph.json","fetch_events":"https://pith.science/api/pith-number/YCPY2JL23A4OQI25DZMSMF6NTA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCPY2JL23A4OQI25DZMSMF6NTA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCPY2JL23A4OQI25DZMSMF6NTA/action/storage_attestation","attest_author":"https://pith.science/pith/YCPY2JL23A4OQI25DZMSMF6NTA/action/author_attestation","sign_citation":"https://pith.science/pith/YCPY2JL23A4OQI25DZMSMF6NTA/action/citation_signature","submit_replication":"https://pith.science/pith/YCPY2JL23A4OQI25DZMSMF6NTA/action/replication_record"}},"created_at":"2026-07-05T03:37:48.615099+00:00","updated_at":"2026-07-05T03:37:48.615099+00:00"}