{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T00:01:34Z","timestamp":1755993694381,"version":"3.44.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/robio49542.2019.8961665","type":"proceedings-article","created":{"date-parts":[[2020,1,21]],"date-time":"2020-01-21T14:49:51Z","timestamp":1579618191000},"page":"1173-1178","source":"Crossref","is-referenced-by-count":0,"title":["Positional Self-attention Based Hierarchical Image Captioning"],"prefix":"10.1109","author":[{"given":"Qianxia","family":"Ma","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingyan","family":"Song","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Collective generation of natural image descriptions","author":"kuznetsova","year":"2012","journal-title":"Meeting the Association for Computational Linguistics Long Papers"},{"key":"ref11","article-title":"Generating image descriptions using dependency relational patterns","author":"aker","year":"2010","journal-title":"Meeting of the Association for Computational Linguistics"},{"key":"ref12","article-title":"How many words is a picture worth? automatic caption generation for news images","author":"feng","year":"2011","journal-title":"Meeting of the Association for Computational Linguistics"},{"key":"ref13","article-title":"Multimodal neural language models","author":"kiros","year":"2014","journal-title":"International Conference on International Conference on Machine Learning"},{"key":"ref14","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"Computer Science"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref16","first-page":"988","article-title":"Image captioning with deep bidirectional lstms","author":"wang","year":"2016","journal-title":"Proceedings of ACM Conference Multimedia"},{"key":"ref17","article-title":"phi-lstm: A phrase-based hierarchical lstm model for image captioning","author":"tan","year":"2016","journal-title":"Asian Conference on Computer Vision"},{"key":"ref18","article-title":"Learning phrase representations using rnn encoder-decoder for statistical machine translation","author":"cho","year":"2014","journal-title":"Computer Science"},{"key":"ref19","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in Neural Information Processing Systems 27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04174-7_2"},{"key":"ref27","first-page":"4790","article-title":"Conditional image generation with pixelcnn decoders","author":"van den oord","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref6","first-page":"444","article-title":"Corpus-guided sentence generation of natural images","author":"yang","year":"2011","journal-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing"},{"key":"ref29","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"chen","year":"2015","journal-title":"Computer Science"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref7","first-page":"1143","article-title":"Im2text: describing images using 1 million captioned photographs","author":"ordonez","year":"2011","journal-title":"International Conference on Neural Information Processing Systems"},{"key":"ref2","article-title":"Explain images with multimodal recurrent neural networks","author":"mao","year":"2014","journal-title":"Computer Science"},{"key":"ref9","first-page":"220","article-title":"Composing simple image descriptions using web-scale n-grams","author":"li","year":"2011","journal-title":"Proceedings of the Fifteenth Conference on Computational Natural Language Learning"},{"key":"ref1","first-page":"1","article-title":"Multimodal machine learning: A survey and taxonomy","author":"baltru\u0161aitis","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis & Machine Intelligence"},{"key":"ref20","article-title":"On the properties of neural machine translation: Encoder-decoder approaches","author":"cho","year":"2014","journal-title":"Computer Science"},{"key":"ref22","first-page":"4904","article-title":"Boosting image captioning with attributes","author":"yao","year":"2016","journal-title":"IEEE International Conference on Computer Vision"},{"key":"ref21","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"Computer Science"},{"key":"ref24","first-page":"933","article-title":"Language mod-eling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12283","article-title":"Learning to guide decoding for image captioning","author":"jiang","year":"2018"},{"key":"ref26","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref25","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"}],"event":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","start":{"date-parts":[[2019,12,6]]},"location":"Dali, China","end":{"date-parts":[[2019,12,8]]}},"container-title":["2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8953068\/8961374\/08961665.pdf?arnumber=8961665","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:44:02Z","timestamp":1755909842000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8961665\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/robio49542.2019.8961665","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}