{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T06:58:29Z","timestamp":1760597909090,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T00:00:00Z","timestamp":1571097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"ARC","award":["DP 190102353"],"award-info":[{"award-number":["DP 190102353"]}]},{"name":"National Natural Science Foundation of China","award":["61632007","61572108"],"award-info":[{"award-number":["61632007","61572108"]}]},{"name":"Sichuan Science and Technology Program","award":["2018GZDZX0032"],"award-info":[{"award-number":["2018GZDZX0032"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3350961","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"2341-2350","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":27,"title":["Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation"],"prefix":"10.1145","author":[{"given":"Yadan","family":"Luo","sequence":"first","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}]},{"given":"Zi","family":"Huang","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}]},{"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}]},{"given":"Ziwei","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}]},{"given":"Jingjing","family":"Li","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chendu, China"}]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}]}],"member":"320","published-online":{"date-parts":[[2019,10,15]]},"reference":[{"volume-title":"Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning. CoRR","year":"2017","author":"Achiam Joshua","key":"e_1_3_2_1_1_1"},{"volume-title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018","year":"2018","author":"Anderson Peter","key":"e_1_3_2_1_2_1"},{"volume-title":"Unifying Count-Based Exploration and Intrinsic Motivation. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016","year":"2016","author":"Bellemare Marc G.","key":"e_1_3_2_1_3_1"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123391"},{"volume-title":"Efros","year":"2018","author":"Burda Yuri","key":"e_1_3_2_1_5_1"},{"volume-title":"Exploration by Random Network Distillation. CoRR","year":"2018","author":"Burda Yuri","key":"e_1_3_2_1_6_1"},{"volume-title":"Proceedings, Part II. 747--763","author":"Chatterjee Moitreya","key":"e_1_3_2_1_7_1"},{"volume-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18)","year":"2018","author":"Chen Hui","key":"e_1_3_2_1_8_1"},{"volume-title":"Adapt and Tell: Adversarial Training of Cross-Domain Image Captioner. In IEEE International Conference on Computer Vision, ICCV 2017","year":"2017","author":"Chen Tseng-Hung","key":"e_1_3_2_1_9_1"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.323"},{"volume-title":"Proceedings of the Ninth Workshop on Statistical Machine Translation, WMT@ACL 2014","year":"2014","author":"Michael","key":"e_1_3_2_1_11_1"},{"volume-title":"Generative Adversarial Nets. In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014","year":"2014","author":"Goodfellow Ian J.","key":"e_1_3_2_1_12_1"},{"volume-title":"Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016","year":"2016","author":"He Kaiming","key":"e_1_3_2_1_13_1"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"volume-title":"VIME: Variational Information Maximizing Exploration. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016","year":"2016","author":"Houthooft Rein","key":"e_1_3_2_1_15_1"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"volume-title":"DenseCap: Fully Convolutional Localization Networks for Dense Captioning. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016","year":"2016","author":"Johnson Justin","key":"e_1_3_2_1_17_1"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"volume-title":"Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings .","author":"Diederik","key":"e_1_3_2_1_19_1"},{"volume-title":"Kingma and Max Welling","year":"2013","author":"Diederik","key":"e_1_3_2_1_20_1"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.356"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1107"},{"volume-title":"Context-Aware Attention-Based Data Augmentation for POI Recommendation. In 35th IEEE International Conference on Data Engineering Workshops, ICDE Workshops 2019","year":"2019","author":"Li Yang","key":"e_1_3_2_1_23_1"},{"volume-title":"Recurrent Topic-Transition GAN for Visual Paragraph Generation. In IEEE International Conference on Computer Vision, ICCV 2017","year":"2017","author":"Liang Xiaodan","key":"e_1_3_2_1_24_1"},{"volume-title":"Context-Aware Visual Policy Network for Sequence-Level Image Captioning. In 2018 ACM Multimedia Conference on Multimedia Conference, MM 2018","year":"2018","author":"Liu Daqing","key":"e_1_3_2_1_25_1"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3241910"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3241910"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"volume-title":"Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3--6","year":"2012","author":"Lopes Manuel","key":"e_1_3_2_1_29_1"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271672"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/592"},{"volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, July 6--12","year":"2002","author":"Papineni Kishore","key":"e_1_3_2_1_32_1"},{"key":"e_1_3_2_1_33_1","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in PyTorch. (2017).  Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in PyTorch. (2017)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"volume-title":"ICLR","author":"Ranzato Marc'Aurelio","key":"e_1_3_2_1_35_1"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00794"},{"volume-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015","year":"2015","author":"Ren Shaoqing","key":"e_1_3_2_1_37_1"},{"volume-title":"Deep Reinforcement Learning-Based Image Captioning with Embedding Reward. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","year":"2017","author":"Ren Zhou","key":"e_1_3_2_1_38_1"},{"volume-title":"Self-Critical Sequence Training for Image Captioning. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","year":"2017","author":"Rennie Steven J.","key":"e_1_3_2_1_39_1"},{"volume-title":"NIPS 2004","year":"2004","author":"Singh Satinder P.","key":"e_1_3_2_1_40_1"},{"key":"e_1_3_2_1_41_1","volume-title":"et almbox","author":"Sutton Richard S","year":"2017","edition":"2"},{"volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","year":"2017","author":"Tang Haoran","key":"e_1_3_2_1_42_1"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1083"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240583"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/bf00992696"},{"volume-title":"Proceedings of the 32nd International Conference on Machine Learning, ICML 2015","year":"2015","author":"Xu Kelvin","key":"e_1_3_2_1_49_1"},{"volume-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18)","year":"2018","author":"Xu Linli","key":"e_1_3_2_1_50_1"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/631"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855422"},{"volume-title":"Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016","year":"2016","author":"Yu Haonan","key":"e_1_3_2_1_53_1"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/820"},{"volume-title":"Actor-Critic Sequence Training for Image Captioning. In NIPS Workshop on Visually-Grounded Interaction and Language .","year":"2017","author":"Zhang Li","key":"e_1_3_2_1_55_1"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855415"}],"event":{"name":"MM '19: The 27th ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Nice France","acronym":"MM '19"},"container-title":["Proceedings of the 27th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350961","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3350961","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:17Z","timestamp":1750201997000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350961"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":56,"alternative-id":["10.1145\/3343031.3350961","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3350961","relation":{},"subject":[],"published":{"date-parts":[[2019,10,15]]},"assertion":[{"value":"2019-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}