{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T15:14:56Z","timestamp":1726067696571},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811533402"},{"type":"electronic","value":"9789811533419"}],"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\/978-981-15-3341-9_10","type":"book-chapter","created":{"date-parts":[[2020,2,15]],"date-time":"2020-02-15T12:02:24Z","timestamp":1581768144000},"page":"115-125","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Attention-Based Top-Down Single-Task Action Recognition in Still Images"],"prefix":"10.1007","author":[{"given":"Jinhai","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hua","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,2,16]]},"reference":[{"key":"10_CR1","unstructured":"Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. arXiv preprint \narXiv:1412.7755\n\n (2014)"},{"key":"10_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1007\/978-3-642-33765-9_12","volume-title":"Computer Vision \u2013 ECCV 2012","author":"C Desai","year":"2012","unstructured":"Desai, C., Ramanan, D.: Detecting actions, poses, and objects with relational phraselets. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 158\u2013172. Springer, Heidelberg (2012). \nhttps:\/\/doi.org\/10.1007\/978-3-642-33765-9_12"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Diba, A., Mohammad Pazandeh, A., Pirsiavash, H., Van Gool, L.: DeepCamp: deep convolutional action & attribute mid-level patterns. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3557\u20133565 (2016)","DOI":"10.1109\/CVPR.2016.387"},{"issue":"3","key":"10_CR4","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1109\/TIP.2017.2778563","volume":"27","author":"W Du","year":"2017","unstructured":"Du, W., Wang, Y., Qiao, Y.: Recurrent spatial-temporal attention network for action recognition in videos. IEEE Trans. Image Process. 27(3), 1347\u20131360 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Du, W., Wang, Y., Qiao, Y.: RPAN: an end-to-end recurrent pose-attention network for action recognition in videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3725\u20133734 (2017)","DOI":"10.1109\/ICCV.2017.402"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Malik, J.: Contextual action recognition with r* CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1080\u20131088 (2015)","DOI":"10.1109\/ICCV.2015.129"},{"issue":"10","key":"10_CR7","doi-asserted-by":"publisher","first-page":"3343","DOI":"10.1016\/j.patcog.2014.04.018","volume":"47","author":"G Guo","year":"2014","unstructured":"Guo, G., Lai, A.: A survey on still image based human action recognition. Pattern Recogn. 47(10), 3343\u20133361 (2014)","journal-title":"Pattern Recogn."},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Kwak, S., Cho, M., Laptev, I.: Thin-slicing for pose: learning to understand pose without explicit pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4938\u20134947 (2016)","DOI":"10.1109\/CVPR.2016.534"},{"key":"10_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1007\/978-3-030-20873-8_10","volume-title":"Computer Vision \u2013 ACCV 2018","author":"L Liu","year":"2019","unstructured":"Liu, L., Tan, R.T., You, S.: Loss guided activation for action recognition in still images. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11365, pp. 152\u2013167. Springer, Cham (2019). \nhttps:\/\/doi.org\/10.1007\/978-3-030-20873-8_10"},{"key":"10_CR13","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1007\/978-3-030-01264-9_8","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Ningning Ma","year":"2018","unstructured":"Ma, N., Zhang, X., Zheng, H.T., Sun, J.: ShuffleNet v2: practical guidelines for efficient CNN architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 116\u2013131 (2018)"},{"key":"10_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_25","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Mallya","year":"2016","unstructured":"Mallya, A., Lazebnik, S.: Learning models for actions and person-object interactions with transfer to question answering. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905. Springer, Cham (2016). \nhttps:\/\/doi.org\/10.1007\/978-3-319-46448-0_25"},{"key":"10_CR15","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint \narXiv:1804.02767\n\n (2018)"},{"issue":"4","key":"10_CR16","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1145\/2523819","volume":"46","author":"ND Rodr\u00edguez","year":"2014","unstructured":"Rodr\u00edguez, N.D., Cu\u00e9llar, M.P., Lilius, J., Calvo-Flores, M.D.: A survey on ontologies for human behavior recognition. ACM Comput. Surv. (CSUR) 46(4), 43 (2014)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"10_CR17","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568\u2013576 (2014)"},{"key":"10_CR18","unstructured":"Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMs. In: International Conference on Machine Learning, pp. 843\u2013852 (2015)"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. arXiv preprint \narXiv:1902.09212\n\n (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"10_CR20","unstructured":"Sutskever, I., Martens, J., Dahl, G., Hinton, G.: On the importance of initialization and momentum in deep learning. In: International Conference on Machine Learning, pp. 1139\u20131147 (2013)"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"10_CR23","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y.: Towards good practices for very deep two-stream convnets. arXiv preprint \narXiv:1507.02159\n\n (2015)"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhou, L., Qiao, Y.: Temporal hallucinating for action recognition with few still images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5314\u20135322 (2018)","DOI":"10.1109\/CVPR.2018.00557"},{"key":"10_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/978-3-319-46478-7_28","volume-title":"Computer Vision \u2013 ECCV 2016","author":"H Xu","year":"2016","unstructured":"Xu, H., Saenko, K.: Ask, attend and answer: exploring question-guided spatial attention for visual question answering. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 451\u2013466. Springer, Cham (2016). \nhttps:\/\/doi.org\/10.1007\/978-3-319-46478-7_28"},{"key":"10_CR26","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"10_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/978-3-642-33765-9_13","volume-title":"Computer Vision \u2013 ECCV 2012","author":"B Yao","year":"2012","unstructured":"Yao, B., Fei-Fei, L.: Action recognition with exemplar based 2.5D graph matching. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 173\u2013186. Springer, Heidelberg (2012). \nhttps:\/\/doi.org\/10.1007\/978-3-642-33765-9_13"}],"container-title":["Communications in Computer and Information Science","Digital TV and Wireless Multimedia Communication"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-15-3341-9_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,15]],"date-time":"2020-02-15T12:03:22Z","timestamp":1581768202000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-981-15-3341-9_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9789811533402","9789811533419"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-15-3341-9_10","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"16 February 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IFTC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Forum on Digital TV and Wireless Multimedia Communications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"19 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iftc2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.siga.com.cn\/iftc2019.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"120","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"34","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"-","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}