{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T14:58:03Z","timestamp":1787497083048,"version":"build-2736575974"},"publisher-location":"Singapore","reference-count":38,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819722525","type":"print"},{"value":"9789819722532","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-2253-2_21","type":"book-chapter","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T06:02:11Z","timestamp":1713938531000},"page":"260-272","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Transformer based Multitask Learning for\u00a0Image Captioning and\u00a0Object Detection"],"prefix":"10.1007","author":[{"given":"Debolena","family":"Basak","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"P. K.","family":"Srijith","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maunendra Sankar","family":"Desarkar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,4,25]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et\u00a0al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on CVPR (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: delving into high quality object detection. In: Proceedings of the IEEE Conference on CVPR (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"21_CR3","doi-asserted-by":"publisher","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) Computer Vision. ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"21_CR4","unstructured":"Chen, T., et\u00a0al.: A unified sequence interface for vision tasks. In: NeurIPS (2022)"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Cornia, M., et\u00a0al.: Meshed-memory transformer for image captioning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"21_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"21_CR7","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"21_CR8","unstructured":"Fariha, A.: Automatic image captioning using multitask learning. In: NeurIPS, vol. 20 (2016)"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Girshick, R., et\u00a0al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on CVPR (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"21_CR11","unstructured":"Han, K., et\u00a0al.: Transformer in transformer. In: Advances in NeurIPS, pp. 15908\u201315919 (2021)"},{"key":"21_CR12","unstructured":"He, P., et\u00a0al.: Deberta: decoding-enhanced bert with disentangled attention. In: ICLR (2021)"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, H., et\u00a0al.: In defense of grid features for visual question answering. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Li, X., et\u00a0al.: Oscar: Object-semantics aligned pre-training for vision-language tasks. In: Computer Vision. ECCV 2020. Springer (2020)","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Liang, J., et\u00a0al.: Swinir: image restoration using Swin transformer. In: ICCV (2021)","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"21_CR16","doi-asserted-by":"publisher","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) Computer Vision. ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et\u00a0al.: Feature pyramid networks for object detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"21_CR18","unstructured":"Liu, H., et\u00a0al.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"21_CR19","unstructured":"Liu, Y., et\u00a0al.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., et\u00a0al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"21_CR21","doi-asserted-by":"publisher","unstructured":"Luo, Y., et al.: Dual-level collaborative transformer for image captioning. Proc. AAAI Conf. Artif. Intell. 35(3), 2286\u20132293 (2021). https:\/\/doi.org\/10.1609\/aaai.v35i3.16328","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"21_CR22","unstructured":"Mokady, R., Hertz, A., Bermano, A.H.: Clipcap: clip prefix for image captioning. arXiv preprint arXiv:2111.09734 (2021)"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Pan, Y., et\u00a0al.: X-linear attention networks for image captioning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"21_CR24","unstructured":"Radford, A., et\u00a0al.: Language models are unsupervised multitask learners. OpenAI blog (2019)"},{"key":"21_CR25","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"21_CR26","unstructured":"Ren, S., et\u00a0al.: Faster r-cnn: towards real-time object detection with region proposal networks. In: NeurIPS, vol.\u00a028 (2015)"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Touvron, H., et\u00a0al.: Training data-efficient image transformers and distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"21_CR28","unstructured":"Vaswani, A., et\u00a0al.: Attention is all you need. In: NeurIPS, vol.\u00a030 (2017)"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Vinyals, O., et\u00a0al: Show and tell: a neural image caption generator. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Wang, W., et\u00a0al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF ICCV, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"21_CR31","doi-asserted-by":"publisher","unstructured":"Wang, Y., Xu, J., Sun, Y.: End-to-end transformer based model for image captioning. Proc. AAAI Conf. Artif. Intell. 36(3), 2585\u20132594 (2022). https:\/\/doi.org\/10.1609\/aaai.v36i3.20160","DOI":"10.1609\/aaai.v36i3.20160"},{"key":"21_CR32","unstructured":"Xinlei\u00a0Chen, H.F., et\u00a0al.: Microsoft coco captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Xu, H., et\u00a0al.: E2e-vlp: end-to-end vision-language pre-training enhanced by visual learning. In: Proceedings of the 59th Annual Meeting of the ACL and the 11th IJCNLP (2021)","DOI":"10.18653\/v1\/2021.acl-long.42"},{"key":"21_CR34","unstructured":"Xu, K., et\u00a0al.: Show, attend and tell: neural image caption generation with visual attention. In: Proceedings of the 32nd ICML, vol.\u00a037, pp. 2048\u20132057. PMLR (2015)"},{"key":"21_CR35","unstructured":"Zhang, K., et\u00a0al.: Bertscore: evaluating text generation with bert. In: ICLR (2020)"},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, P., et\u00a0al.: Vinvl: revisiting visual representations in vision-language models. In: Proceedings of the IEEE\/CVF Conference on CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"21_CR37","doi-asserted-by":"crossref","unstructured":"Zhao, W., et al.: A multi-task learning approach for image captioning. In: IJCAI 2018","DOI":"10.24963\/ijcai.2018\/168"},{"key":"21_CR38","doi-asserted-by":"crossref","unstructured":"Zhuo, T.Y., et\u00a0al.: Rethinking round-trip translation for machine translation evaluation. In: Findings of the Association for Computational Linguistics: ACL (2023)","DOI":"10.18653\/v1\/2023.findings-acl.22"}],"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\/978-981-97-2253-2_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T18:07:50Z","timestamp":1731780470000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-2253-2_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819722525","9789819722532"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-2253-2_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"25 April 2024","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":"Taipei","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taiwan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 May 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 May 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}