{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T17:19:15Z","timestamp":1770571155594,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819681792","type":"print"},{"value":"9789819681808","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-8180-8_11","type":"book-chapter","created":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T09:16:16Z","timestamp":1750324576000},"page":"130-141","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["$$T^2$$ Transformer for\u00a0Image Captioning"],"prefix":"10.1007","author":[{"given":"Quanjin","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guisheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanqing","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"11_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1007\/978-3-319-46454-1_24","volume-title":"Computer Vision \u2013 ECCV 2016","author":"P Anderson","year":"2016","unstructured":"Anderson, P., Fernando, B., Johnson, M., Gould, S.: SPICE: semantic propositional image caption evaluation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 382\u2013398. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_24"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: 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, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Chen, H., Wang, Y., Yang, X., Li, J.: Captioning transformer with scene graph guiding. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 2538\u20132542. IEEE (2021)","DOI":"10.1109\/ICIP42928.2021.9506193"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10578\u201310587 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Denkowski, M., Lavie, A.: Meteor universal: language specific translation evaluation for any target language. In: Proceedings of the Ninth Workshop on Statistical Machine Translation, pp. 376\u2013380 (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Dong, J., Hu, Z., Zhou, Y.: Revisiting knowledge distillation for image captioning. In: Artificial Intelligence: First CAAI International Conference, CICAI 2021, Hangzhou, China, 5\u20136 June 2021, Proceedings, Part I 1, pp. 613\u2013625. Springer (2021)","DOI":"10.1007\/978-3-030-93046-2_52"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Guo, J.: Robust image captioning using knowledge distillation. In: 2023 IEEE International Conference on Sensors, Electronics and Computer Engineering (ICSECE), pp. 881\u2013885. IEEE (2023)","DOI":"10.1109\/ICSECE58870.2023.10263327"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.Y.: Attention on attention for image captioning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4634\u20134643 (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"11_CR9","unstructured":"Huang, Y., Chen, J.: Teacher-critical training strategies for image captioning. CoRR abs\/2009.14405 (2020). https:\/\/arxiv.org\/abs\/2009.14405"},{"key":"11_CR10","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Lin, C.Y., Och, F.J.: Automatic evaluation of machine translation quality using longest common subsequence and skip-bigram statistics. In: Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL 2004), pp. 605\u2013612 (2004)","DOI":"10.3115\/1218955.1219032"},{"key":"11_CR12","first-page":"1865","volume":"33","author":"F Liu","year":"2020","unstructured":"Liu, F., et al.: Prophet attention: predicting attention with future attention. Adv. Neural. Inf. Process. Syst. 33, 1865\u20131876 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR13","unstructured":"Liu, W., Chen, S., Guo, L., Zhu, X., Liu, J.: CPTR: full transformer network for image captioning. arXiv preprint arXiv:2101.10804 (2021)"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Luo, J., et al.: Semantic-conditional diffusion networks for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23359\u201323368 (2023)","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"11_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109420","volume":"138","author":"Y Ma","year":"2023","unstructured":"Ma, Y., Ji, J., Sun, X., Zhou, Y., Ji, R.: Towards local visual modeling for image captioning. Pattern Recogn. 138, 109420 (2023)","journal-title":"Pattern Recogn."},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Pan, Y., Yao, T., Li, Y., Mei, T.: X-linear attention networks for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10971\u201310980 (2020)","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"11_CR18","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence\u00a0Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"issue":"2","key":"11_CR20","first-page":"1","volume":"18","author":"L Wang","year":"2024","unstructured":"Wang, L., Zheng, Y., Jin, D., Li, F., Qiao, Y., Pan, S.: Contrastive graph similarity networks. ACM Trans. Web 18(2), 1\u201320 (2024)","journal-title":"ACM Trans. Web"},{"key":"11_CR21","unstructured":"Wang, P., et al.: OFA: unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. In: International Conference on Machine Learning, pp. 23318\u201323340. PMLR (2022)"},{"key":"11_CR22","unstructured":"Wang, Z., Yu, J., Yu, A.W., Dai, Z., Tsvetkov, Y., Cao, Y.: Simvlm: simple visual language model pretraining with weak supervision. arXiv preprint arXiv:2108.10904 (2021)"},{"key":"11_CR23","unstructured":"Xu, K.: Show, attend and tell: neural image caption generation with visual attention. arXiv preprint arXiv:1502.03044 (2015)"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Yang, X., Tang, K., Zhang, H., Cai, J.: Auto-encoding scene graphs for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10685\u201310694 (2019)","DOI":"10.1109\/CVPR.2019.01094"},{"key":"11_CR25","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: Coca: contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: Vinvl: revisiting visual representations in vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5579\u20135588 (2021)","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: Rstnet: captioning with adaptive attention on visual and non-visual words. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15465\u201315474 (2021)","DOI":"10.1109\/CVPR46437.2021.01521"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-8180-8_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T20:30:39Z","timestamp":1757190639000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-8180-8_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819681792","9789819681808"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-8180-8_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"20 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}