{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:04:40Z","timestamp":1750309480132,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,9,22]],"date-time":"2023-09-22T00:00:00Z","timestamp":1695340800000},"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":[[2023,9,22]]},"DOI":"10.1145\/3641584.3641586","type":"proceedings-article","created":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T22:44:43Z","timestamp":1718405083000},"page":"8-14","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multi-stage Feature Enhancement Network with Second-Attention for Image Captioning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1515-8663","authenticated-orcid":false,"given":"Xiaobao","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science, Xi'an University of Posts and Telecommunications, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0540-4938","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Xi'an University of Posts and Telecommunications, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3974-5838","authenticated-orcid":false,"given":"Junsheng","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Software, Northwestern Polytechnical University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8588-8111","authenticated-orcid":false,"given":"Sugang","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computer Science, Xi'an University of Posts and Telecommunications, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8059-5395","authenticated-orcid":false,"given":"Zhiqiang","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Computer Science, Xi'an University of Posts and Telecommunications, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9893-2838","authenticated-orcid":false,"given":"Bohui","family":"Song","sequence":"additional","affiliation":[{"name":"School of Computer Science, Xi'an University of Posts and Telecommunications, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,14]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"3164","volume-title":"Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. (CVPR)","author":"Vinyals O.","year":"2015","unstructured":"O. Vinyals, A. Toshev, S. Bengio, and D. Erhan, \u201cShow and tell: A neural image caption generator,\u201d in Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. (CVPR), pp. 3156\u20133164, 2015."},{"key":"e_1_3_2_1_2_1","first-page":"2057","volume-title":"International Conference on Machine Learning","author":"Xu K.","year":"2015","unstructured":"K. Xu, J. Ba, R. Kiros, K. Cho, A. Courville, R. Salakhudinov, R. Zemel, and Y. Bengio, \u201cShow, attend and tell: Neural image caption generation with visual attention,\u201d in International Conference on Machine Learning, pp. 2048\u20132057, 2015."},{"key":"e_1_3_2_1_3_1","first-page":"3250","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Lu J.","year":"2017","unstructured":"J. Lu, C. Xiong, D. Parikh, and R. Socher, \u201cKnowing when to look: Adaptive attention via a visual sentinel for image captioning,\u201d in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3242\u20133250, 2017."},{"key":"e_1_3_2_1_4_1","first-page":"42","volume-title":"Machine Intelligence and Signal Processing: Proceedings of International Conference, MISP 2019","author":"Bhalekar M.","year":"2020","unstructured":"M. Bhalekar, S. Sureka, S. Joshi, and M. Bedekar, \u201cGeneration of image captions using vgg and resnet cnn models cascaded with rnn approach,\u201d in Machine Intelligence and Signal Processing: Proceedings of International Conference, MISP 2019, pp. 27\u201342, 2020."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/3909726"},{"key":"e_1_3_2_1_6_1","first-page":"1","article-title":"Lstm and multiple cnns based event image classification","volume":"80","author":"Li P.","year":"2021","unstructured":"P. Li, T. Huadong, J. Yu, and S. Wei, \u201cLstm and multiple cnns based event image classification,\u201d Multimedia Tools and Applications, vol. 80, pp. 1\u201318, 08 2021.","journal-title":"Multimedia Tools and Applications"},{"key":"e_1_3_2_1_7_1","first-page":"222","volume-title":"2017 International Conference on Green Informatics (ICGI)","author":"Chen J.","year":"2017","unstructured":"J. Chen, Y. Wang, Y. Wu, and C. Cai, \u201cAn ensemble of convolutional neural networks for image classification based on lstm,\u201d in 2017 International Conference on Green Informatics (ICGI), pp. 217\u2013222, 2017."},{"key":"e_1_3_2_1_8_1","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani A.","year":"2017","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, \u0141. Kaiser, and I. Polosukhin, \u201cAttention is all you need,\u201d Advances in Neural Information Processing Systems, vol. 30, pp. 5998\u20136008, 2017.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_9_1","first-page":"4186","volume-title":"Proceedings of NAACL-HLT","author":"Kenton J. D. M.-W. C.","year":"2019","unstructured":"J. D. M.-W. C. Kenton and L. K. Toutanova, \u201cBert: Pre-training of deep bidirectional transformers for language understanding,\u201d in Proceedings of NAACL-HLT, pp. 4171\u20134186, 2019."},{"key":"e_1_3_2_1_10_1","first-page":"10584","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Cornia M.","year":"2020","unstructured":"M. Cornia, M. Stefanini, L. Baraldi, and R. Cucchiara, \u201cMeshed-memory transformer for image captioning,\u201d in 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10575\u201310584, IEEE, 2020."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_1_12_1","volume-title":"Mfpn: A novel mixture feature pyramid network of multiple architectures for object detection","author":"Liang T.","year":"1912","unstructured":"T. Liang, Y. Wang, Q. Zhao, Z. Tang, H. Ling, , \u201cMfpn: A novel mixture feature pyramid network of multiple architectures for object detection,\u201d arXiv preprint arXiv:1912.09748, 2019."},{"key":"e_1_3_2_1_13_1","first-page":"526","volume-title":"2019 34rd Youth Academic Annual Conference of Chinese Association of Automation (YAC)","author":"Zhang W.","year":"2019","unstructured":"W. Zhang, W. Nie, X. Li, and Y. Yu, \u201cImage caption generation with adaptive transformer,\u201d in 2019 34rd Youth Academic Annual Conference of Chinese Association of Automation (YAC), pp. 521\u2013526, 2019."},{"key":"e_1_3_2_1_14_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 arXiv preprint arXiv:2101.10804, 2021."},{"key":"e_1_3_2_1_15_1","first-page":"296","volume-title":"17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part IX","author":"Li Y.","year":"2022","unstructured":"Y. Li, H. Mao, R. Girshick, and K. He, \u201cExploring plain vision transformer backbones for object detection,\u201d in Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part IX, pp. 280\u2013296, Springer, 2022."},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy A.","year":"2021","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, , \u201cAn image is worth 16x16 words: Transformers for image recognition at scale,\u201d in International Conference on Learning Representations, 2021."},{"key":"e_1_3_2_1_17_1","first-page":"10002","volume-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Liu Z.","year":"2021","unstructured":"Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, and B. Guo, \u201cSwin transformer: Hierarchical vision transformer using shifted windows,\u201d in 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9992\u201310002, 2021."},{"key":"e_1_3_2_1_18_1","first-page":"17978","volume-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Li Y.","year":"2022","unstructured":"Y. Li, Y. Pan, T. Yao, and T. Mei, \u201cComprehending and ordering semantics for image captioning,\u201d in 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 17969\u201317978, 2022."},{"key":"e_1_3_2_1_19_1","first-page":"2594","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"36","author":"Wang Y.","year":"2022","unstructured":"Y. Wang, J. Xu, and Y. Sun, \u201cEnd-to-end transformer based model for image captioning,\u201d in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 2585\u20132594, 2022."},{"key":"e_1_3_2_1_20_1","first-page":"610","volume-title":"15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XVI 15","author":"Yu C.","year":"2018","unstructured":"C. Yu, X. Zhao, Q. Zheng, P. Zhang, and X. You, \u201cHierarchical bilinear pooling for fine-grained visual recognition,\u201d in Computer Vision\u2013ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XVI 15, pp. 595\u2013610, 2018."},{"key":"e_1_3_2_1_21_1","first-page":"10977","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Pan Y.","year":"2020","unstructured":"Y. Pan, T. Yao, Y. Li, and T. Mei, \u201cX-linear attention networks for image captioning,\u201d in 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10968\u201310977, 2020."},{"key":"e_1_3_2_1_22_1","volume-title":"Generating long sequences with sparse transformers","author":"Child R.","year":"1904","unstructured":"R. Child, S. Gray, A. Radford, and I. Sutskever, \u201cGenerating long sequences with sparse transformers,\u201d arXiv preprint arXiv:1904.10509, 2019."},{"key":"e_1_3_2_1_23_1","first-page":"17297","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Zaheer M.","year":"2020","unstructured":"M. Zaheer, G. Guruganesh, A. Dubey, J. Ainslie, C. Alberti, S. Ontanon, P. Pham, A. Ravula, Q. Wang, L. Yang, , \u201cBig bird: transformers for longer sequences,\u201d in Proceedings of the 34th International Conference on Neural Information Processing Systems, pp. 17283\u201317297, 2020."},{"key":"e_1_3_2_1_24_1","first-page":"9557","volume-title":"International Conference on Machine Learning","author":"Shi H.","year":"2021","unstructured":"H. Shi, J. Gao, X. Ren, H. Xu, X. Liang, Z. Li, and J. T.-Y. Kwok, \u201cSparsebert: Rethinking the importance analysis in self-attention,\u201d in International Conference on Machine Learning, pp. 9547\u20139557, 2021."},{"key":"e_1_3_2_1_25_1","first-page":"8964","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"33","author":"Wang W.","year":"2019","unstructured":"W. Wang, Z. Chen, and H. Hu, \u201cHierarchical attention network for image captioning,\u201d in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8957\u20138964, 2019."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","first-page":"2004","DOI":"10.1109\/TMM.2021.3074803","article-title":"Image difference captioning with instance-level fine-grained feature representation","volume":"24","author":"Huang Q.","year":"2021","unstructured":"Q. Huang, Y. Liang, J. Wei, Y. Cai, H. Liang, H.-f. Leung, and Q. Li, \u201cImage difference captioning with instance-level fine-grained feature representation,\u201d IEEE Transactions on Multimedia, vol. 24, pp. 2004\u20132017, 2021.","journal-title":"IEEE Transactions on Multimedia"},{"key":"e_1_3_2_1_27_1","first-page":"558","volume-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Wang W.","year":"2021","unstructured":"W. Wang, E. Xie, X. Li, D.-P. Fan, K. Song, D. Liang, T. Lu, P. Luo, and L. Shao, \u201cPyramid vision transformer: A versatile backbone for dense prediction without convolutions,\u201d in 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 548\u2013558, 2021."},{"key":"e_1_3_2_1_28_1","volume-title":"International Conference on Learning Representations","author":"Zhu X.","year":"2020","unstructured":"X. Zhu, W. Su, L. Lu, B. Li, X. Wang, and J. Dai, \u201cDeformable detr: De-formable transformers for end-to-end object detection,\u201d in International Conference on Learning Representations, 2020."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"}],"event":{"name":"AIPR 2023: 2023 6th International Conference on Artificial Intelligence and Pattern Recognition","acronym":"AIPR 2023","location":"Xiamen China"},"container-title":["2023 6th International Conference on Artificial Intelligence and Pattern Recognition (AIPR)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641584.3641586","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3641584.3641586","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:29Z","timestamp":1750295849000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641584.3641586"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,22]]},"references-count":29,"alternative-id":["10.1145\/3641584.3641586","10.1145\/3641584"],"URL":"https:\/\/doi.org\/10.1145\/3641584.3641586","relation":{},"subject":[],"published":{"date-parts":[[2023,9,22]]},"assertion":[{"value":"2024-06-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}