{"paper":{"title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"OpenVid-1M supplies over a million precise text-video pairs with expressive captions to improve text-to-video generation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Yang, Kepan Nan, Penghao Zhou, Rui Xie, Tiehan Fan, Xiang Li, Ying Tai, Zhenheng Yang, Zhijie Chen","submitted_at":"2024-07-02T15:40:29Z","abstract_excerpt":"Text-to-video (T2V) generation has recently garnered significant attention thanks to the large multi-modality model Sora. However, T2V generation still faces two important challenges: 1) Lacking a precise open sourced high-quality dataset. The previous popular video datasets, e.g. WebVid-10M and Panda-70M, are either with low quality or too large for most research institutions. Therefore, it is challenging but crucial to collect a precise high-quality text-video pairs for T2V generation. 2) Ignoring to fully utilize textual information. Recent T2V methods have focused on vision transformers, u"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we introduce OpenVid-1M, a precise high-quality dataset with expressive captions. This open-scenario dataset contains over 1 million text-video pairs, facilitating research on T2V generation. Furthermore, we curate 433K 1080p videos from OpenVid-1M to create OpenVidHD-0.4M... Additionally, we propose a novel Multi-modal Video Diffusion Transformer (MVDiT) capable of mining both structure information from visual tokens and semantic information from text tokens.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the newly collected videos and captions are verifiably higher quality and more precise than prior datasets such as WebVid-10M and Panda-70M, and that the MVDiT architecture delivers measurable gains attributable to its joint structure-semantic processing rather than other training factors.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"OpenVid-1M supplies 1 million high-quality text-video pairs and introduces MVDiT to improve text-to-video generation by better using both visual structure and text semantics.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"OpenVid-1M supplies over a million precise text-video pairs with expressive captions to improve text-to-video generation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d1e5a278a927f2f0a14fb25bf3a2e912f56c98493e2af206dcb0108d0b413303"},"source":{"id":"2407.02371","kind":"arxiv","version":3},"verdict":{"id":"7a7d6e26-b04b-4512-b9c3-177d8561f47c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:30:33.458442Z","strongest_claim":"we introduce OpenVid-1M, a precise high-quality dataset with expressive captions. This open-scenario dataset contains over 1 million text-video pairs, facilitating research on T2V generation. Furthermore, we curate 433K 1080p videos from OpenVid-1M to create OpenVidHD-0.4M... Additionally, we propose a novel Multi-modal Video Diffusion Transformer (MVDiT) capable of mining both structure information from visual tokens and semantic information from text tokens.","one_line_summary":"OpenVid-1M supplies 1 million high-quality text-video pairs and introduces MVDiT to improve text-to-video generation by better using both visual structure and text semantics.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the newly collected videos and captions are verifiably higher quality and more precise than prior datasets such as WebVid-10M and Panda-70M, and that the MVDiT architecture delivers measurable gains attributable to its joint structure-semantic processing rather than other training factors.","pith_extraction_headline":"OpenVid-1M supplies over a million precise text-video pairs with expressive captions to improve text-to-video generation."},"references":{"count":16,"sample":[{"doi":"","year":null,"title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","work_id":"4f68eada-27e3-437a-a2fe-6e4ca524d0d3","ref_index":1,"cited_arxiv_id":"2311.15127","is_internal_anchor":true},{"doi":"","year":null,"title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","work_id":"4d4486c5-6317-4d8d-bb5b-3b100d732a83","ref_index":2,"cited_arxiv_id":"2310.19512","is_internal_anchor":true},{"doi":"","year":null,"title":"Adam: A Method for Stochastic Optimization","work_id":"1910796d-9b52-4683-bf5c-de9632c1028b","ref_index":3,"cited_arxiv_id":"1412.6980","is_internal_anchor":true},{"doi":"","year":2024,"title":"arXiv preprint arXiv:2310.11440 (2023) 2, 4","work_id":"7e755299-7217-4af5-a711-0d29a31768fb","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Latte: Latent Diffusion Transformer for Video Generation","work_id":"5328e907-7278-4781-a2bb-c5ef40dc87fb","ref_index":5,"cited_arxiv_id":"2401.03048","is_internal_anchor":true}],"resolved_work":16,"snapshot_sha256":"97813cc35b2ce4c32c795a3b2aba207cca435a803e2588e68f6a894280c6688f","internal_anchors":7},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8592a80c8d210d691955b92044057aa2dcc2f948421406dcfe90d9009d355ee8"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}