{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:46:11Z","timestamp":1778082371419,"version":"3.51.4"},"reference-count":87,"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\/iccv51701.2025.01406","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15147-15158","source":"Crossref","is-referenced-by-count":1,"title":["VEGGIE: Instructional Editing and Reasoning Video Concepts with Grounded Generation"],"prefix":"10.1109","author":[{"given":"Shoubin","family":"Yu","sequence":"first","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Difan","family":"Liu","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziqiao","family":"Ma","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yicong","family":"Hong","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhou","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":"Joyce","family":"Chai","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohit","family":"Bansal","sequence":"additional","affiliation":[{"name":"UNC Chapel Hill"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0219"},{"key":"ref2","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref4","article-title":"Video generation models as world simulators","volume-title":"OpenAI","author":"Brooks","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02121"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02106"},{"key":"ref8","article-title":"Shikra: Unleashing multimodal 1lm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref9","article-title":"Consistent video-to-video transfer using synthetic dataset","volume-title":"The Twelfth International Conference on Learning Representations","author":"Cheng","year":"2024"},{"key":"ref10","article-title":"Flatten: optical FLow-guided ATTENtion for consistent text-to-video editing","volume-title":"The Twelfth International Conference on Learning Representations","author":"Cong","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00806"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00806"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2307\/1932409.JSTOR1932409"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref16","volume-title":"Vitron: A unified pixel-level vision llm for understanding, generating, segmenting, editing","author":"Fei","year":"2024"},{"key":"ref17","article-title":"Guiding instruction-based image editing via multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref18","article-title":"Seed-data-edit technical report: A hybrid dataset for instructional image editing","author":"Ge","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01208"},{"key":"ref20","article-title":"Tokenflow: Consistent diffusion features for consistent video editing","author":"Geyer","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref21","volume-title":"pt 4o","year":"2024"},{"key":"ref22","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref23","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref24","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref26","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","volume-title":"The Eleventh International Conference on Learning Representations","author":"Hong","year":"2023"},{"issue":"2","key":"ref27","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref28","article-title":"Vivid10 m: A dataset and baseline for versatile and interactive video local editing","author":"Hu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00799"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-8137.1912.tb05611.x"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref34","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref35","article-title":"Anyv2v: A tuning-free framework for any video-tovideo editing tasks","author":"Ku","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref36","article-title":"Lisa: Reasoning segmentation via large language model","author":"Lai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref38","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref39","article-title":"Training-free guidance in text-to-video generation via multimodal planning and structured noise initialization","author":"Li","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00715"},{"key":"ref42","article-title":"Llm-grounded video diffusion models","author":"Lian","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"Videodirectorgpt: Consistent multi-scene video generation via 1lm-guided planning","author":"Lin","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01650"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.31"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26094"},{"key":"ref50","volume-title":"Towards temporally consistent referring video object segmentation","author":"Miao","year":"2024"},{"key":"ref51","article-title":"Grounding multimodal large language models to the world","volume-title":"The Twelfth International Conference on Learning Representations","author":"Peng","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.876"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687529"},{"key":"ref55","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32763"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00542"},{"key":"ref61","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":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0334"},{"key":"ref63","article-title":"Genartist: Multimodal 11 m as an agent for unified image generation and editing","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref64","article-title":"Omniedit: Building image editing generalist models through specialist supervision","author":"Wei","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01023"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01188"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref68","article-title":"Cvpr 2023 text guided video editing competition","author":"Wu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"ref70","article-title":"Vidiff: Translating videos via multi-modal instructions with diffusion models","author":"Xing","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref71","article-title":"Videogpt: Video generation using vq-vae and transformers","author":"Yan","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref72","article-title":"Qwen2 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref73","article-title":"Qwen2 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref74","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref75","article-title":"Raccoon: Remove, add, and change video content with auto-generated narratives","author":"Yoon","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref76","article-title":"Ferret: Refer and ground anything anywhere at any granularity","volume-title":"The Twelfth International Conference on Learning Representations","author":"You","year":"2023"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681394"},{"key":"ref79","article-title":"Inpaint anything: Segment anything meets image inpainting","author":"Yu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_2"},{"key":"ref82","article-title":"Ferret-v2: An improved baseline for referring and grounding with large language models","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1365"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01349"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00684"},{"key":"ref86","article-title":"Effived: Efficient video editing via text-instruction diffusion models","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref87","article-title":"Bubogpt: Enabling visual grounding in multi-modal 11 ms","author":"Zhao","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\/11445030.pdf?arnumber=11445030","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:13:02Z","timestamp":1777529582000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445030\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":87,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01406","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}