{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:33:44Z","timestamp":1761896024203,"version":"build-2065373602"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11208999","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["An End-to-End Model for Photo-Sharing Multi-Modal Dialogue Generation"],"prefix":"10.1109","author":[{"given":"Peiming","family":"Guo","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sinuo","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Edinburgh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanzhao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dingkun","family":"Long","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengju","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meishan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.219"},{"article-title":"MMChat: Multimodal chat dataset on social media","volume-title":"Proceedings of LREC","author":"Zheng","key":"ref3"},{"year":"2024","key":"ref4","article-title":"Llama 3 model card"},{"article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","year":"2023","author":"Bai","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.113"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.479"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.204"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.405"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.108"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.288"},{"article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proceedings of ICML","author":"Esser","key":"ref12"},{"article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","year":"2013","author":"Bengio","key":"ref13"},{"article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"Proceedings of ICLR","author":"Jang","key":"ref14"},{"article-title":"The concrete distribution: A continuous relaxation of discrete random variables","volume-title":"Proceedings of ICLR","author":"Maddison","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.527"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"article-title":"Neural discrete representation learning","volume-title":"Proceedings of NeurIPS","author":"van den Oord","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"article-title":"Synergistic dual spatial-aware generation of image-to-text and text-to-image","volume-title":"Proceedings of NeurIPS","author":"Zhao","key":"ref20"},{"article-title":"Hierarchical text-conditional image generation with clip latents","year":"2022","author":"Ramesh","key":"ref21"},{"article-title":"Visual instruction tuning","volume-title":"Proceedings of NeurIPS","author":"Liu","key":"ref22"},{"article-title":"Chameleon: Mixed-modal early-fusion foundation models","year":"2024","author":"Team","key":"ref23"},{"article-title":"Making LLaMA SEE and draw with SEED tokenizer","volume-title":"Proceedings of ICLR","author":"Ge","key":"ref24"},{"article-title":"Gpt-4 technical report","year":"2023","author":"Achiam","key":"ref25"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11208999.pdf?arnumber=11208999","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T06:05:25Z","timestamp":1761890725000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11208999\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11208999","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}