{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T11:26:40Z","timestamp":1751887600629,"version":"3.37.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030394684"},{"type":"electronic","value":"9783030394691"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-39469-1_2","type":"book-chapter","created":{"date-parts":[[2020,1,21]],"date-time":"2020-01-21T07:03:01Z","timestamp":1579590181000},"page":"16-28","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["PAIC: Parallelised Attentive Image Captioning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0107-7347","authenticated-orcid":false,"given":"Ziwei","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9738-4949","authenticated-orcid":false,"given":"Zi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6272-2971","authenticated-orcid":false,"given":"Yadan","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,1,21]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: CVPR, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Bin, Y., Yang, Y., Zhou, J., Huang, Z., Shen, H.T.: Adaptively attending to visual attributes and linguistic knowledge for captioning. In: ACM MM, pp. 1345\u20131353 (2017)","DOI":"10.1145\/3123266.3123391"},{"key":"2_CR3","unstructured":"Chen, X., et al.: Microsoft COCO captions: data collection and evaluation server. CoRR abs\/1504.00325 (2015)"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, J., Dong, L., Lapata, M.: Long short-term memory-networks for machine reading. In: EMNLP, pp. 551\u2013561 (2016)","DOI":"10.18653\/v1\/D16-1053"},{"issue":"4","key":"2_CR5","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1109\/TPAMI.2016.2599174","volume":"39","author":"J Donahue","year":"2017","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. TPAMI 39(4), 677\u2013691 (2017)","journal-title":"TPAMI"},{"key":"2_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-642-15561-1_2","volume-title":"Computer Vision \u2013 ECCV 2010","author":"A Farhadi","year":"2010","unstructured":"Farhadi, A., et al.: Every picture tells a story: generating sentences from images. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 15\u201329. Springer, Heidelberg (2010). \nhttps:\/\/doi.org\/10.1007\/978-3-642-15561-1_2"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Guo, Z., Gao, L., Song, J., Xu, X., Shao, J., Shen, H.T.: Attention-based LSTM with semantic consistency for videos captioning. In: ACM MM, pp. 357\u2013361 (2016)","DOI":"10.1145\/2964284.2967242"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"2_CR9","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"2_CR10","unstructured":"Hodosh, M., Young, P., Hockenmaier, J.: Framing image description as a ranking task: data, models and evaluation metrics. In: IJCAI, pp. 4188\u20134192 (2015)"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Johnson, J., Karpathy, A., Fei-Fei, L.: Densecap: fully convolutional localization networks for dense captioning. In: CVPR, pp. 4565\u20134574 (2016)","DOI":"10.1109\/CVPR.2016.494"},{"issue":"4","key":"2_CR12","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1109\/TPAMI.2016.2598339","volume":"39","author":"A Karpathy","year":"2017","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. TPAMI 39(4), 664\u2013676 (2017)","journal-title":"TPAMI"},{"key":"2_CR13","unstructured":"Kim, Y., Denton, C., Hoang, L., Rush, A.M.: Structured attention networks. In: ICLR (2017)"},{"key":"2_CR14","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"2_CR15","unstructured":"Kuznetsova, P., Ordonez, V., Berg, A.C., Berg, T.L., Choi, Y.: Collective generation of natural image descriptions. In: ACL, pp. 359\u2013368 (2012)"},{"key":"2_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). \nhttps:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Lu, J., Xiong, C., Parikh, D., Socher, R.: Knowing when to look: adaptive attention via a visual sentinel for image captioning. In: CVPR, pp. 3242\u20133250 (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Luo, Y., Huang, Z., Zhang, Z., Wang, Z., Li, J., Yang, Y.: Curiosity-driven reinforcement learning for diverse visual paragraph generation. In: ACM MM, pp. 2341\u20132350 (2019)","DOI":"10.1145\/3343031.3350961"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Luo, Y., Wang, Z., Huang, Z., Yang, Y., Zhao, C.: Coarse-to-fine annotation enrichment for semantic segmentation learning. In: CIKM, pp. 237\u2013246 (2018)","DOI":"10.1145\/3269206.3271672"},{"key":"2_CR20","unstructured":"Mitchell, M., et al.: Midge: generating image descriptions from computer vision detections. In: EACL, pp. 747\u2013756 (2012)"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Parikh, A.P., T\u00e4ckstr\u00f6m, O., Das, D., Uszkoreit, J.: A decomposable attention model for natural language inference. In: EMNLP, pp. 2249\u20132255 (2016)","DOI":"10.18653\/v1\/D16-1244"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Pedersoli, M., Lucas, T., Schmid, C., Verbeek, J.: Areas of attention for image captioning. In: ICCV, pp. 1251\u20131259 (2017)","DOI":"10.1109\/ICCV.2017.140"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: CVPR, pp. 1179\u20131195 (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Song, J., Gao, L., Guo, Z., Liu, W., Zhang, D., Shen, H.T.: Hierarchical LSTM with adjusted temporal attention for video captioning. In: IJCAI, pp. 2737\u20132743 (2017)","DOI":"10.24963\/ijcai.2017\/381"},{"key":"2_CR25","unstructured":"Sukhbaatar, S., Szlam, A., Weston, J., Fergus, R.: End-to-end memory networks. In: NeurIPS, pp. 2440\u20132448 (2015)"},{"key":"2_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS, pp. 6000\u20136010 (2017)"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: CVPR, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Wang, Z., Luo, Y., Li, Y., Huang, Z., Yin, H.: Look deeper see richer: depth-aware image paragraph captioning. In: ACM MM, pp. 672\u2013680 (2018)","DOI":"10.1145\/3240508.3240583"},{"key":"2_CR29","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML, pp. 2048\u20132057 (2015)"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., Qiu, Z., Mei, T.: Boosting image captioning with attributes. In: ICCV, pp. 4904\u20134912 (2017)","DOI":"10.1109\/ICCV.2017.524"},{"key":"2_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/978-3-319-68155-9_20","volume-title":"Databases Theory and Applications","author":"M Zhang","year":"2017","unstructured":"Zhang, M., Yang, Y., Zhang, H., Ji, Y., Xie, N., Shen, H.T.: Deep semantic indexing using convolutional localization network with region-based visual attention for image database. In: Huang, Z., Xiao, X., Cao, X. (eds.) ADC 2017. LNCS, vol. 10538, pp. 261\u2013272. Springer, Cham (2017). \nhttps:\/\/doi.org\/10.1007\/978-3-319-68155-9_20"}],"container-title":["Lecture Notes in Computer Science","Databases Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-39469-1_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,1,21]],"date-time":"2020-01-21T07:07:04Z","timestamp":1579590424000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-39469-1_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030394684","9783030394691"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-39469-1_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"21 January 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Database Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Melbourne, VIC","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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 February 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 February 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adc2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/adc2020.github.io\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}