{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T18:41:57Z","timestamp":1747161717885,"version":"3.40.5"},"reference-count":40,"publisher":"Elsevier BV","issue":"2","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T00:00:00Z","timestamp":1700524800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["High-Confidence Computing"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1016\/j.hcc.2023.100184","type":"journal-article","created":{"date-parts":[[2023,11,22]],"date-time":"2023-11-22T19:25:57Z","timestamp":1700681157000},"page":"100184","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"title":["Coreference resolution helps visual dialogs to focus"],"prefix":"10.1016","volume":"4","author":[{"given":"Tianwei","family":"Yue","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9665-3783","authenticated-orcid":false,"given":"Wenping","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dachi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Congrui","family":"Hetang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuewei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.hcc.2023.100184_b1","doi-asserted-by":"crossref","unstructured":"A. Das, S. Kottur, K. Gupta, A. Singh, D. Yadav, J.M. Moura, D. Parikh, D. Batra, Visual dialog, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 326\u2013335.","DOI":"10.1109\/CVPR.2017.121"},{"year":"2019","series-title":"CLEVR-dialog: A diagnostic dataset for multi-round reasoning in visual dialog","author":"Kottur","key":"10.1016\/j.hcc.2023.100184_b2"},{"key":"10.1016\/j.hcc.2023.100184_b3","doi-asserted-by":"crossref","unstructured":"A. Agrawal, D. Batra, D. Parikh, A. Kembhavi, Don\u2019t just assume; look and answer: Overcoming priors for visual question answering, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 4971\u20134980.","DOI":"10.1109\/CVPR.2018.00522"},{"issue":"16","key":"10.1016\/j.hcc.2023.100184_b4","doi-asserted-by":"crossref","DOI":"10.3390\/app13169461","article-title":"Unlocking everyday wisdom: Enhancing machine comprehension with script knowledge integration","volume":"13","author":"Zhou","year":"2023","journal-title":"Appl. Sci."},{"key":"10.1016\/j.hcc.2023.100184_b5","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32, No. 1","article-title":"Region-based quality estimation network for large-scale person re-identification","author":"Song","year":"2018"},{"key":"10.1016\/j.hcc.2023.100184_b6","article-title":"Depth-wise decomposition for accelerating separable convolutions in efficient convolutional neural networks","author":"He","year":"2019","journal-title":"arXiv preprint arXiv:1910.09455"},{"key":"10.1016\/j.hcc.2023.100184_b7","doi-asserted-by":"crossref","unstructured":"Y. Niu, H. Zhang, M. Zhang, J. Zhang, Z. Lu, J.-R. Wen, Recursive visual attention in visual dialog, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 6679\u20136688.","DOI":"10.1109\/CVPR.2019.00684"},{"year":"2023","series-title":"Faster, Stronger, and More Interpretable: Massive Transformer Architectures for Vision-Language Tasks","author":"Chen","key":"10.1016\/j.hcc.2023.100184_b8"},{"key":"10.1016\/j.hcc.2023.100184_b9","article-title":"Integrity and junkiness failure handling for embedding-based retrieval: a case study in social network search","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2304.09287"},{"key":"10.1016\/j.hcc.2023.100184_b10","series-title":"Advances in Neural Information Processing Systems","first-page":"314","article-title":"Best of both worlds: Transferring knowledge from discriminative learning to a generative visual dialog model","author":"Lu","year":"2017"},{"year":"2023","series-title":"InkGAN: Generative Adversarial Networks for Ink-And-Wash Style Transfer of Photographs","author":"Yu","key":"10.1016\/j.hcc.2023.100184_b11"},{"key":"10.1016\/j.hcc.2023.100184_b12","doi-asserted-by":"crossref","unstructured":"Q. Wu, P. Wang, C. Shen, I. Reid, A. van\u00a0den Hengel, Are you talking to me? reasoned visual dialog generation through adversarial learning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 6106\u20136115.","DOI":"10.1109\/CVPR.2018.00639"},{"key":"10.1016\/j.hcc.2023.100184_b13","doi-asserted-by":"crossref","unstructured":"D. Guo, C. Xu, D. Tao, Image-question-answer synergistic network for visual dialog, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 10434\u201310443.","DOI":"10.1109\/CVPR.2019.01068"},{"key":"10.1016\/j.hcc.2023.100184_b14","article-title":"Euclidreamer: fast and high-quality texturing for 3d models with stable diffusion depth","author":"Le","year":"2023","journal-title":"arXiv preprint arXiv:2311.15573"},{"key":"10.1016\/j.hcc.2023.100184_b15","doi-asserted-by":"crossref","unstructured":"J. Andreas, M. Rohrbach, T. Darrell, D. Klein, Neural module networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 39\u201348.","DOI":"10.1109\/CVPR.2016.12"},{"key":"10.1016\/j.hcc.2023.100184_b16","doi-asserted-by":"crossref","unstructured":"J. Johnson, B. Hariharan, L. van\u00a0der Maaten, J. Hoffman, L. Fei-Fei, C. Lawrence\u00a0Zitnick, R. Girshick, Inferring and executing programs for visual reasoning, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2989\u20132998.","DOI":"10.1109\/ICCV.2017.325"},{"key":"10.1016\/j.hcc.2023.100184_b17","article-title":"Novel view synthesis from a single rgbd image for indoor scenes","author":"Hetang","year":"2023","journal-title":"arXiv preprint arXiv:2311.01065"},{"key":"10.1016\/j.hcc.2023.100184_b18","doi-asserted-by":"crossref","unstructured":"R. Hu, J. Andreas, M. Rohrbach, T. Darrell, K. Saenko, Learning to reason: End-to-end module networks for visual question answering, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 804\u2013813.","DOI":"10.1109\/ICCV.2017.93"},{"year":"2017","series-title":"End-to-end optimization of goal-driven and visually grounded dialogue systems","author":"Strub","key":"10.1016\/j.hcc.2023.100184_b19"},{"key":"10.1016\/j.hcc.2023.100184_b20","doi-asserted-by":"crossref","unstructured":"P. Anderson, Q. Wu, D. Teney, J. Bruce, M. Johnson, N. S\u00fcnderhauf, I. Reid, S. Gould, A. van\u00a0den Hengel, Vision-and-language navigation: Interpreting visually-grounded navigation instructions in real environments, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 3674\u20133683.","DOI":"10.1109\/CVPR.2018.00387"},{"issue":"10","key":"10.1016\/j.hcc.2023.100184_b21","doi-asserted-by":"crossref","first-page":"2413","DOI":"10.1109\/TPAMI.2017.2754246","article-title":"Fvqa: Fact-based visual question answering","volume":"40","author":"Wang","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"10.1016\/j.hcc.2023.100184_b22","doi-asserted-by":"crossref","first-page":"74","DOI":"10.54364\/AAIML.2023.1174","article-title":"Sentiment analysis: a systematic case study with yelp scores","volume":"3","author":"Wang","year":"2023","journal-title":"Advances in Artificial Intelligence and Machine Learning"},{"key":"10.1016\/j.hcc.2023.100184_b23","doi-asserted-by":"crossref","unstructured":"Y. Li, N. Duan, B. Zhou, X. Chu, W. Ouyang, X. Wang, M. Zhou, Visual question generation as dual task of visual question answering, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 6116\u20136124.","DOI":"10.1109\/CVPR.2018.00640"},{"year":"2016","series-title":"Multimodal compact bilinear pooling for visual question answering and visual grounding","author":"Fukui","key":"10.1016\/j.hcc.2023.100184_b24"},{"key":"10.1016\/j.hcc.2023.100184_b25","series-title":"International Colloquium on Automata, Languages, and Programming","first-page":"693","article-title":"Finding frequent items in data streams","author":"Charikar","year":"2002"},{"key":"10.1016\/j.hcc.2023.100184_b26","doi-asserted-by":"crossref","unstructured":"K.J. Shih, S. Singh, D. Hoiem, Where to look: Focus regions for visual question answering, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 4613\u20134621.","DOI":"10.1109\/CVPR.2016.499"},{"key":"10.1016\/j.hcc.2023.100184_b27","doi-asserted-by":"crossref","unstructured":"P. Anderson, X. He, C. Buehler, D. Teney, M. Johnson, S. Gould, L. Zhang, Bottom-up and top-down attention for image captioning and visual question answering, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 6077\u20136086.","DOI":"10.1109\/CVPR.2018.00636"},{"key":"10.1016\/j.hcc.2023.100184_b28","series-title":"Advances in Neural Information Processing Systems","first-page":"3719","article-title":"Visual reference resolution using attention memory for visual dialog","author":"Seo","year":"2017"},{"year":"2019","series-title":"Dual attention networks for visual reference resolution in visual dialog","author":"Kang","key":"10.1016\/j.hcc.2023.100184_b29"},{"key":"10.1016\/j.hcc.2023.100184_b30","doi-asserted-by":"crossref","unstructured":"S. Kottur, J.M. Moura, D. Parikh, D. Batra, M. Rohrbach, Visual coreference resolution in visual dialog using neural module networks, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 153\u2013169.","DOI":"10.1007\/978-3-030-01267-0_10"},{"year":"2022","series-title":"Autonomous path generation with path optimization","author":"Hetang","key":"10.1016\/j.hcc.2023.100184_b31"},{"issue":"2","key":"10.1016\/j.hcc.2023.100184_b32","doi-asserted-by":"crossref","first-page":"66","DOI":"10.54364\/AAIML.2023.1166","article-title":"Linguistically-inspired neural coreference resolution","volume":"3","author":"Yang","year":"2023","journal-title":"Advances in Artificial Intelligence and Machine Learning"},{"key":"10.1016\/j.hcc.2023.100184_b33","series-title":"Advances in Neural Information Processing Systems","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"Ren","year":"2015"},{"key":"10.1016\/j.hcc.2023.100184_b34","doi-asserted-by":"crossref","unstructured":"C. Hetang, Impression Network for Video Object Detection, in: 2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence, Vol. 3, ICIBA, 2023, pp. 735\u2013743.","DOI":"10.1109\/ICIBA56860.2023.10165600"},{"year":"2021","series-title":"Methods and apparatuses for recognizing video and training, electronic device and medium","author":"Tangcongrui","key":"10.1016\/j.hcc.2023.100184_b35"},{"key":"10.1016\/j.hcc.2023.100184_b36","article-title":"Sliding-BERT: Striding towards conversational machine comprehension in long context","volume":"3","author":"Longxiang","year":"2023","journal-title":"Adv. Artif. Intell. Mach. Learn."},{"year":"2022","series-title":"Stop Location Change Detection","author":"Thibaux","key":"10.1016\/j.hcc.2023.100184_b37"},{"year":"2022","series-title":"Implementing synthetic scenes for autonomous vehicles","author":"Hetang","key":"10.1016\/j.hcc.2023.100184_b38"},{"year":"2023","series-title":"Autonomous vehicle driving path label generation for machine learning models","author":"Hetang","key":"10.1016\/j.hcc.2023.100184_b39"},{"key":"10.1016\/j.hcc.2023.100184_b40","series-title":"Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","first-page":"239","article-title":"Fast and scalable polynomial kernels via explicit feature maps","author":"Pham","year":"2013"}],"container-title":["High-Confidence Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S266729522300082X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S266729522300082X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T03:01:44Z","timestamp":1718593304000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S266729522300082X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":40,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["S266729522300082X"],"URL":"https:\/\/doi.org\/10.1016\/j.hcc.2023.100184","relation":{},"ISSN":["2667-2952"],"issn-type":[{"type":"print","value":"2667-2952"}],"subject":[],"published":{"date-parts":[[2024,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Coreference resolution helps visual dialogs to focus","name":"articletitle","label":"Article Title"},{"value":"High-Confidence Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.hcc.2023.100184","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 The Author(s). Published by Elsevier B.V. on behalf of Shandong University.","name":"copyright","label":"Copyright"}],"article-number":"100184"}}