{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:K3M2KEY4JIG2VMVVSACEKVQVKJ","short_pith_number":"pith:K3M2KEY4","schema_version":"1.0","canonical_sha256":"56d9a5131c4a0daab2b59004455615524302b8d8440d32a2669cb26c15839884","source":{"kind":"arxiv","id":"2001.05691","version":3},"attestation_state":"computed","paper":{"title":"Learning Spatiotemporal Features via Video and Text Pair Discrimination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Limin Wang, Tianhao Li","submitted_at":"2020-01-16T08:28:57Z","abstract_excerpt":"Current video representations heavily rely on learning from manually annotated video datasets which are time-consuming and expensive to acquire. We observe videos are naturally accompanied by abundant text information such as YouTube titles and Instagram captions. In this paper, we leverage this visual-textual connection to learn spatiotemporal features in an efficient weakly-supervised manner. We present a general cross-modal pair discrimination (CPD) framework to capture this correlation between a video and its associated text. Specifically, we adopt noise-contrastive estimation to tackle th"},"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":"2001.05691","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-16T08:28:57Z","cross_cats_sorted":[],"title_canon_sha256":"e0e28fca3d47c5e1bc1666e405a315bc1494875bb23a7d804b4797f056b1bb7f","abstract_canon_sha256":"28095f42a00b063a69399b0900d08a74f77eb749c1d04d7c761b197e95084558"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:10:23.856846Z","signature_b64":"8N1W2qa+daa19IPc921KC+xxyyr9F4CaBjD0Ml2T9+wQhWNQGLmKquhAzi2DRdcdgF8nRiXcUSYNipyAmu/hDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56d9a5131c4a0daab2b59004455615524302b8d8440d32a2669cb26c15839884","last_reissued_at":"2026-07-05T02:10:23.856407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:10:23.856407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Spatiotemporal Features via Video and Text Pair Discrimination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Limin Wang, Tianhao Li","submitted_at":"2020-01-16T08:28:57Z","abstract_excerpt":"Current video representations heavily rely on learning from manually annotated video datasets which are time-consuming and expensive to acquire. We observe videos are naturally accompanied by abundant text information such as YouTube titles and Instagram captions. In this paper, we leverage this visual-textual connection to learn spatiotemporal features in an efficient weakly-supervised manner. We present a general cross-modal pair discrimination (CPD) framework to capture this correlation between a video and its associated text. Specifically, we adopt noise-contrastive estimation to tackle th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.05691","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/2001.05691/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":"2001.05691","created_at":"2026-07-05T02:10:23.856468+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.05691v3","created_at":"2026-07-05T02:10:23.856468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.05691","created_at":"2026-07-05T02:10:23.856468+00:00"},{"alias_kind":"pith_short_12","alias_value":"K3M2KEY4JIG2","created_at":"2026-07-05T02:10:23.856468+00:00"},{"alias_kind":"pith_short_16","alias_value":"K3M2KEY4JIG2VMVV","created_at":"2026-07-05T02:10:23.856468+00:00"},{"alias_kind":"pith_short_8","alias_value":"K3M2KEY4","created_at":"2026-07-05T02:10:23.856468+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20838","citing_title":"USV: Towards Understanding the User-generated Short-form Videos","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2212.03191","citing_title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06942","citing_title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2305.06355","citing_title":"VideoChat: Chat-Centric Video Understanding","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K3M2KEY4JIG2VMVVSACEKVQVKJ","json":"https://pith.science/pith/K3M2KEY4JIG2VMVVSACEKVQVKJ.json","graph_json":"https://pith.science/api/pith-number/K3M2KEY4JIG2VMVVSACEKVQVKJ/graph.json","events_json":"https://pith.science/api/pith-number/K3M2KEY4JIG2VMVVSACEKVQVKJ/events.json","paper":"https://pith.science/paper/K3M2KEY4"},"agent_actions":{"view_html":"https://pith.science/pith/K3M2KEY4JIG2VMVVSACEKVQVKJ","download_json":"https://pith.science/pith/K3M2KEY4JIG2VMVVSACEKVQVKJ.json","view_paper":"https://pith.science/paper/K3M2KEY4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.05691&json=true","fetch_graph":"https://pith.science/api/pith-number/K3M2KEY4JIG2VMVVSACEKVQVKJ/graph.json","fetch_events":"https://pith.science/api/pith-number/K3M2KEY4JIG2VMVVSACEKVQVKJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K3M2KEY4JIG2VMVVSACEKVQVKJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K3M2KEY4JIG2VMVVSACEKVQVKJ/action/storage_attestation","attest_author":"https://pith.science/pith/K3M2KEY4JIG2VMVVSACEKVQVKJ/action/author_attestation","sign_citation":"https://pith.science/pith/K3M2KEY4JIG2VMVVSACEKVQVKJ/action/citation_signature","submit_replication":"https://pith.science/pith/K3M2KEY4JIG2VMVVSACEKVQVKJ/action/replication_record"}},"created_at":"2026-07-05T02:10:23.856468+00:00","updated_at":"2026-07-05T02:10:23.856468+00:00"}