{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:35:36Z","timestamp":1778081736994,"version":"3.51.4"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687898","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Attentional Distance for Zero-Shot Classification with Text-to-Image Diffusion Model"],"prefix":"10.1109","author":[{"given":"Kailai","family":"Feng","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,Faculty of Computing,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minheng","family":"Ni","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Faculty of Computing,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxiu","family":"Jiang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Faculty of Computing,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhilu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Faculty of Computing,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Faculty of Computing,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Imagenet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012","journal-title":"NeurIPS"},{"key":"ref2","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"ICLR","author":"Simonyan"},{"key":"ref3","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref4","article-title":"Albert: A lite bert for self-supervised learning of language representations","volume-title":"ICLR","author":"Lan"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25159"},{"key":"ref6","article-title":"Ref-diff: Zero-shot referring image segmentation with generative models","author":"Ni","year":"2023"},{"key":"ref7","article-title":"Label-efficient semantic segmentation with diffusion models","volume-title":"ICLR","author":"Baranchuk"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"ref11","article-title":"Text-to-image diffusion models are zero-shot classifiers","author":"Clark","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_29"},{"key":"ref14","article-title":"Ig captioner: Information gain captioners are strong zero-shot classifiers","author":"Yang","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00581"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2019.01052","article-title":"f-vaegan-d2: A feature generating framework for anyshot learning","volume-title":"CVPR","author":"Xian"},{"key":"ref17","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00844"},{"key":"ref19","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1007\/s11263-023-01891-x","article-title":"Clip-adapter: Better vision-language models with feature adapters","volume-title":"IJCV","author":"Gao"},{"key":"ref22","article-title":"Controlvideo: Trainingfree controllable text-to-video generation","author":"Zhang","year":"2023"},{"key":"ref23","article-title":"Mc2: Multi-concept guidance for customized multi-concept generation","author":"Jiang","year":"2024"},{"key":"ref24","article-title":"Beyond generation: Harnessing text to image models for object detection and segmentation","author":"Ge","year":"2023"},{"key":"ref25","article-title":"Imaginarynet: Learning object detectors without real images and annotations","volume-title":"ICLR","author":"Ni"},{"key":"ref26","article-title":"Diffusion models for zero-shot open-vocabulary segmentation","author":"Karazija","year":"2023"},{"key":"ref27","article-title":"Segdiff: Image segmentation with diffusion probabilistic models","author":"Amit","year":"2021"},{"key":"ref28","article-title":"Broadly applicable and accurate protein design by integrating structure prediction networks and diffusion generative models","author":"Watson","year":"2022","journal-title":"BioRxiv"},{"key":"ref29","article-title":"A general single-cell analysis framework via conditional diffusion generative models","author":"Tang","year":"2023","journal-title":"bioRxiv"},{"key":"ref30","article-title":"Diffusion model is secretly a training-free open vocabulary semantic segmenter","author":"Wang","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128437"},{"key":"ref32","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687898.pdf?arnumber=10687898","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:21:14Z","timestamp":1727763674000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687898\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687898","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}