{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:55:43Z","timestamp":1781974543554,"version":"3.54.5"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,7]]},"DOI":"10.1109\/icme.2019.00256","type":"proceedings-article","created":{"date-parts":[[2019,8,6]],"date-time":"2019-08-06T01:24:41Z","timestamp":1565054681000},"page":"1480-1485","source":"Crossref","is-referenced-by-count":61,"title":["Large-Scale Datasets for Going Deeper in Image Understanding"],"prefix":"10.1109","author":[{"given":"Jiahong","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baoming","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjia","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shipei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guosen","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanwei","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yizhou","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonggang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref32","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"ACL2 Workshop"},{"key":"ref31","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"ACL"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref10","author":"wah","year":"2011","journal-title":"The Caltech-UCSD Birds-200-2011 Dataset"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"ref12","article-title":"Zero-shot learning with semantic output codes","author":"palatucci","year":"2009","journal-title":"NIPS"},{"key":"ref13","article-title":"Zero-shot learning by convex combination of semantic embeddings","author":"norouzi","year":"2013","journal-title":"NIPS"},{"key":"ref14","article-title":"An embarrassingly simple approach to zero-shot learning","author":"romera-paredes","year":"2015","journal-title":"ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.575"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.15"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.310"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912049"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref27","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"ordonez","year":"2011","journal-title":"NIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref6","article-title":"Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop","author":"yu","year":"2015","journal-title":"arXiv 1506 03365"},{"key":"ref29","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"chen","year":"2015","journal-title":"arXiv 1504 00325"},{"key":"ref5","article-title":"Places: A 10 million image database for scene recognition","author":"zhou","year":"2017","journal-title":"PAMI"},{"key":"ref8","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref7","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"ref2","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.11231","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"AAAI"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref21","article-title":"Ssd: Single shot multibox detector","author":"liu","year":"2016","journal-title":"ECCV"},{"key":"ref24","article-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","author":"chen","year":"2016","journal-title":"TPAMI"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref26","article-title":"Framing image description as a ranking task: Data, models and evaluation metrics","author":"hodosh","year":"2015","journal-title":"IJCAI"},{"key":"ref25","article-title":"Every picture tells a story: Generating sentences from images","author":"farhadi","year":"2010","journal-title":"ECCV"}],"event":{"name":"2019 IEEE International Conference on Multimedia and Expo (ICME)","location":"Shanghai, China","start":{"date-parts":[[2019,7,8]]},"end":{"date-parts":[[2019,7,12]]}},"container-title":["2019 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx7\/8777226\/8784700\/08785018.pdf?arnumber=8785018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,25]],"date-time":"2022-09-25T06:01:00Z","timestamp":1664085660000},"score":1,"resource":{"primary":{"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/ieeexplore.ieee.org\/document\/8785018\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":33,"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.1109\/icme.2019.00256","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}