{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:58:18Z","timestamp":1777888698589,"version":"3.51.4"},"reference-count":74,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01382","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14898-14908","source":"Crossref","is-referenced-by-count":0,"title":["TIP-I2V: A Million-Scale Real Text and Image Prompt Dataset for Image-to-Video Generation"],"prefix":"10.1109","author":[{"given":"Wenhao","family":"Wang","sequence":"first","affiliation":[{"name":"University of Technology Sydney"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Hailuo ai video generator - reimagine video creation - image-to-video","year":"2024"},{"key":"ref2","volume-title":"Kling - kuaishou - image-to-video","year":"2024"},{"key":"ref3","volume-title":"Movie gen: Ai video generation tool","year":"2024"},{"key":"ref4","volume-title":"Sora: Ai text-to-video model","year":"2024"},{"key":"ref5","volume-title":"Pika - creative video editing platform","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-demo.9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref8","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref9","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref11","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_14"},{"key":"ref15","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref16","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref17","volume-title":"Falconsai. Falconsai: nsfw image detection","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.tbench.2024.100152"},{"key":"ref19","article-title":"Leveraging frequency analysis for deep fake image recognition","volume-title":"International conference on machine learning","author":"Frank","year":"2020"},{"key":"ref20","author":"Golub","year":"2024","journal-title":"Discordchatexporter"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657407"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref26","article-title":"Miradata: A large-scale video dataset with long durations and structured captions","volume-title":"Thirty-eighth Conference on Neural Information Processing Systems","author":"Ju","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897820"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref31","volume-title":"PKU-Yuan Lab and Tuzhan AI etc. Open-sora-plan","year":"2024"},{"key":"ref32","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_6"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00205"},{"key":"ref37","article-title":"Slip: Self-supervision meets language-image pretraining","volume-title":"European Conference on Computer Vision","author":"Mu","year":"2022"},{"key":"ref38","article-title":"Openvid-1m: A large-scale high-quality dataset for text-tovideo generation","author":"Nan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01769"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02345"},{"key":"ref41","volume-title":"OpenAI. New embedding models and api updates","year":"2024"},{"key":"ref42","volume-title":"OpenAI. Hello gpt-4o","year":"2024"},{"key":"ref43","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref44","article-title":"Results and findings of the 2021 image similarity challenge","author":"Papakipos","year":"2022","journal-title":"NeurIPS 2021 Competitions and Demonstrations Track"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01413"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.103997"},{"key":"ref47","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref49","article-title":"Consisti2v: Enhancing visual consistency for image-to-video generation","author":"Ren","journal-title":"Transactions on Machine Learning Research"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01165"},{"key":"ref51","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"International conference on machine learning","author":"Tan","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref54","volume-title":"Unitary team. Detoxify","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"ref56","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2096"},{"key":"ref59","article-title":"Bag of tricks and a strong baseline for image copy detection","author":"Wang","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25366"},{"key":"ref61","article-title":"Anypattern: Towards in-context image copy detection","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref62","article-title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Wang","year":"2024"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02051"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.51"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-demo.50"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3696415"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"ref69","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref70","article-title":"Contrastive learning with large memory bank and negative embedding subtraction for accurate copy detection","author":"Yokoo","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref71","article-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00828"},{"key":"ref73","author":"Zheng","year":"2024","journal-title":"Open-sora: Democratizing efficient video production for all"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.244"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445174.pdf?arnumber=11445174","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:55:32Z","timestamp":1777611332000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445174\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01382","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}