{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T20:08:43Z","timestamp":1778789323618,"version":"3.51.4"},"reference-count":77,"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"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2007951,IIS2143895"],"award-info":[{"award-number":["IIS-2007951,IIS2143895"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02279","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24580-24590","source":"Crossref","is-referenced-by-count":0,"title":["DiffTell: A High-Quality Dataset for Describing Image Manipulation Changes"],"prefix":"10.1109","author":[{"given":"Zonglin","family":"Di","sequence":"first","affiliation":[{"name":"University of California,Santa Cruz"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Shi","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifei","family":"Fan","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Tan","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Black","sequence":"additional","affiliation":[{"name":"ACVSSP, University of Surrey"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Collomosse","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"University of California,Santa Cruz"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref3","article-title":"Openflamingo: An opensource framework for training large autoregressive visionlanguage models","author":"Awadalla","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref4","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref5","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee"},{"key":"ref6","volume-title":"Introducing our multimodal models","author":"Bavishi","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3485441.3485650"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27843"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref10","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.195"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0410"},{"key":"ref13","article-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1065"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.aacl-short.5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.aacl-short.5"},{"key":"ref18","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref19","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0908-6_7"},{"key":"ref21","article-title":"Hq-edit: A high-quality dataset for instruction-based image editing","author":"Hui","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1436"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1436"},{"key":"ref24","article-title":"Mantis: Interleaved multiimage instruction tuning","author":"Jiang","year":"2024","journal-title":"arXiv"},{"key":"ref25","article-title":"Transparent human evaluation for image captioning","author":"Kasai","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00210"},{"key":"ref27","first-page":"2095","article-title":"Agnostic change captioning with cycle consistency","volume-title":"Proc. ICCV","author":"Kim","year":"2021"},{"key":"ref28","article-title":"Building and better understanding visionlanguage models: insights and future directions","volume-title":"Workshop on Responsibly Building the Next Generation of Multimodal Foundational Models","author":"Lauren\u00e7on","year":"2024"},{"key":"ref29","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref30","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref31","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref32","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref34","article-title":"Aligning large multi-modal model with robust instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref39","volume-title":"Llava-next: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref40","article-title":"Internchat: Solving vision-centric tasks by interacting with chatbots beyond language","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref42","article-title":"Simpo: Simple preference optimization with a reference-free reward","author":"Meng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00472"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00472"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01413"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00198"},{"key":"ref49","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref50","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref51","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on Machine Learning","author":"Ramesh"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69544-6_38"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_34"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1002\/int.22821"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1182"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.6"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3268004"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3268004"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3268004"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3254162"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3254162"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00263"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref68","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref69","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20218"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20218"},{"key":"ref74","article-title":"Magicbrush: A manually annotated dataset for instruction-guided image editing","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref75","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref76","article-title":"Bertscore: Evaluating text generation with bert","author":"Zhang","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref77","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint arXiv"}],"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\/11445610.pdf?arnumber=11445610","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T19:54:16Z","timestamp":1778788456000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445610\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02279","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}