{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T13:45:14Z","timestamp":1726062314676},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030367107"},{"type":"electronic","value":"9783030367114"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-36711-4_42","type":"book-chapter","created":{"date-parts":[[2019,12,10]],"date-time":"2019-12-10T08:03:52Z","timestamp":1575965032000},"page":"504-515","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Transformer-DW: A Transformer Network with Dynamic and Weighted Head"],"prefix":"10.1007","author":[{"given":"Ruxin","family":"Tan","sequence":"first","affiliation":[]},{"given":"Jiahui","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Su","sequence":"additional","affiliation":[]},{"given":"Gongshen","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,12,9]]},"reference":[{"key":"42_CR1","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"},{"key":"42_CR2","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91\u201399 (2015)"},{"key":"42_CR3","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"42_CR4","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"42_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MD Zeiler","year":"2014","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818\u2013833. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53"},{"key":"42_CR6","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS, pp. 6000\u20136010. Curran Associates Inc. (2017)"},{"key":"42_CR7","unstructured":"Dehghani, M., Gouws, S., Vinyals, O., Uszkoreit, J., Kaiser, \u0141.: Universal transformers (2018). arXiv preprint arXiv:1807.03819"},{"key":"42_CR8","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations. In: NAACL, vol. 2, pp. 464\u2013468 (2018)","DOI":"10.18653\/v1\/N18-2074"},{"key":"42_CR9","doi-asserted-by":"crossref","unstructured":"Bapna, A., Chen, M., Firat, O., Cao, Y., Wu, Y.: Training deeper neural machine translation models with transparent attention. In: EMNLP, pp. 3028\u20133033 (2018)","DOI":"10.18653\/v1\/D18-1338"},{"key":"42_CR10","unstructured":"Dai, Z., et al.: Transformer-XL: attentive language models beyond a fixed-length context (2019). arXiv preprint arXiv:1901.02860"},{"issue":"11","key":"42_CR11","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"42_CR12","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 1097\u20131105 (2012)"},{"key":"42_CR13","unstructured":"Ahmed, K., Keskar, N.S., Socher, R.: Weighted transformer network for machine translation (2017). arXiv preprint arXiv:1711.02132"},{"key":"42_CR14","unstructured":"Zhang, B., Xiong, D., Su, J.: Accelerating neural transformer via an average attention network (2018). arXiv preprint arXiv:1805.00631"},{"key":"42_CR15","doi-asserted-by":"crossref","unstructured":"Britz, D., Goldie, A., Luong, M.-T., Le, Q.: Massive exploration of neural machine translation architectures. In: EMNLP, pp. 1442\u20131451 (2017)","DOI":"10.18653\/v1\/D17-1151"},{"key":"42_CR16","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2014). arXiv preprint arXiv:1412.6980"},{"key":"42_CR17","unstructured":"Zhang, J., et al.: THUMT: an open source toolkit for neural machine translation (2017). arXiv preprint arXiv:1706.06415"},{"key":"42_CR18","doi-asserted-by":"crossref","unstructured":"Sordoni, A., et al.: A neural network approach to context-sensitive generation of conversational responses. In: NAACL, pp. 196\u2013205 (2015)","DOI":"10.3115\/v1\/N15-1020"},{"key":"42_CR19","doi-asserted-by":"crossref","unstructured":"Shang, L., Lu, Z., Li, H.: Neural responding machine for short-text conversation. In: ACL (Volume 1: Long Papers), pp. 1577\u20131586 (2015)","DOI":"10.3115\/v1\/P15-1152"},{"key":"42_CR20","doi-asserted-by":"crossref","unstructured":"Serban, I.V., Sordoni, A., Bengio, Y., Courville, A.C., Pineau, J.: Building end-to-end dialogue systems using generative hierarchical neural network models. In: AAAI, vol. 16, pp. 3776\u20133784 (2016)","DOI":"10.1609\/aaai.v30i1.9883"},{"key":"42_CR21","doi-asserted-by":"crossref","unstructured":"Serban, I.V., et al.: A hierarchical latent variable encoder-decoder model for generating dialogues. In: AAAI, pp. 3295\u20133301 (2017)","DOI":"10.1609\/aaai.v31i1.10983"},{"key":"42_CR22","doi-asserted-by":"crossref","unstructured":"Xing, C., Wu, Y., Wu, W., Huang, Y., Zhou, M.: Hierarchical recurrent attention network for response generation. In: AAAI (2018)","DOI":"10.1609\/aaai.v31i1.10981"},{"key":"42_CR23","doi-asserted-by":"crossref","unstructured":"Tian, Z., Yan, R., Mou, L., Song, Y., Feng, Y., Zhao, D.: How to make context more useful? An empirical study on context-aware neural conversational models. In: ACL (Volume 2: Short Papers), pp. 231\u2013236 (2017)","DOI":"10.18653\/v1\/P17-2036"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-36711-4_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T02:02:59Z","timestamp":1665194579000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-36711-4_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030367107","9783030367114"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-36711-4_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"9 December 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","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":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 December 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ajiips.com.au\/iconip2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}