{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:16:32Z","timestamp":1750220192578,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,9,23]],"date-time":"2022-09-23T00:00:00Z","timestamp":1663891200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,9,23]]},"DOI":"10.1145\/3573942.3574061","type":"proceedings-article","created":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T23:45:42Z","timestamp":1684280742000},"page":"547-554","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["GA-SATIC: Semi-autoregressive Transformer Image Captioning Based on Geometric Attention"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6810-6352","authenticated-orcid":false,"given":"Ziyi","family":"Li","sequence":"first","affiliation":[{"name":"Xi'an University of Posts and Telecommunications, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4359-0050","authenticated-orcid":false,"given":"Ma","family":"Li","sequence":"additional","affiliation":[{"name":"Xi'an University of Posts and Telecommunications, China"}]}],"member":"320","published-online":{"date-parts":[[2023,5,16]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"A Thorough Review on Recent Deep Learning Methodologies for Image Captioning","author":"Elhagry A.","year":"2021","unstructured":"A. Elhagry, K. Kadaoui, \u201cA Thorough Review on Recent Deep Learning Methodologies for Image Captioning,\u201d in arXiv: 2107.13114, July 2021."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18178\/joig.3.1.20-24"},{"key":"e_1_3_2_1_3_1","volume-title":"Recurrent neural network regularization","author":"Zaremba W.","year":"2015","unstructured":"W. Zaremba, I. Sutskever, O. Vinyals, \u201cRecurrent neural network regularization,\u201d in arXiv: 1409.2329, Feb. 2015."},{"key":"e_1_3_2_1_4_1","volume-title":"NeurIPS","author":"Vaswani A.","year":"2017","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A N. Gomez, \u0141. Kaiser, Polosukhin I, \u201cAttention is all you need,\u201d in NeurIPS, 2017."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"volume-title":"Fast image caption generation with position alignment","year":"1912","key":"e_1_3_2_1_6_1","unstructured":"Zheng-cong Fei, \u201cFast image caption generation with position alignment,\u201d in arXiv: 1912.06365, Dec. 2019."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/107"},{"key":"e_1_3_2_1_8_1","volume-title":"Masked non-autoregressive image captioning","author":"Gao Junlong","year":"1906","unstructured":"Junlong Gao, Xi Meng, Shiqi Wang, Xia Li, Shanshe Wang, Siwei Ma, and Wen Gao, \u201cMasked non-autoregressive image captioning,\u201d in arXiv: 1906.00717, June 2019."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16421"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.277"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16219"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18178\/joig.3.1.34-39"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on Learning Representations","author":"Gu Jiatao","year":"2018","unstructured":"Jiatao Gu, James Bradbury, Caiming Xiong, Victor OK Li, and Richard Socher, \u201cNon-autoregressive neural machine translation,\u201d in International Conference on Learning Representations, 2018."},{"volume-title":"AAAI","year":"2020","key":"e_1_3_2_1_17_1","unstructured":"Zheng-cong Fei, \u201cFast image caption generation with position alignment,\u201d in AAAI, 2020."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.12720\/joig.1.1.7-11"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1044"},{"key":"e_1_3_2_1_20_1","volume-title":"Masked non-autoregressive image captioning","author":"Gao Junlong","year":"1906","unstructured":"Junlong Gao, Xi Meng, Shiqi Wang, Xia Li, Shanshe Wang, Siwei Ma, and Wen Gao, \u201cMasked non-autoregressive image captioning,\u201d in arXiv: 1906.00717, June 2019."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_22_1","first-page":"91","author":"Ren S.","year":"2015","unstructured":"S. Ren, K. He, R. Girshick, and J. Sun, \u201cFaster R-CNN: Towards real-time object detection with region proposal networks,\u201d in Advances in Neural Information Processing Systems, 2015, pp. 91\u201399.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"e_1_3_2_1_26_1","volume-title":"CPTR: Full Transformer Network for Image Captioning","author":"Liu W.","year":"2021","unstructured":"W. Liu, S. Chen, L. Guo, X. Zhu, and J. Liu, \u201cCPTR: Full Transformer Network for Image Captioning,\u201d in arXiv: 2101.10804, 2021."}],"event":{"name":"AIPR 2022: 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","acronym":"AIPR 2022","location":"Xiamen China"},"container-title":["Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3573942.3574061","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3573942.3574061","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:32Z","timestamp":1750186952000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3573942.3574061"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,23]]},"references-count":26,"alternative-id":["10.1145\/3573942.3574061","10.1145\/3573942"],"URL":"https:\/\/doi.org\/10.1145\/3573942.3574061","relation":{},"subject":[],"published":{"date-parts":[[2022,9,23]]},"assertion":[{"value":"2023-05-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}