{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T06:36:01Z","timestamp":1775889361606,"version":"3.50.1"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585358","type":"print"},{"value":"9783030585365","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58536-5_7","type":"book-chapter","created":{"date-parts":[[2020,11,2]],"date-time":"2020-11-02T23:02:42Z","timestamp":1604358162000},"page":"105-123","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":45,"title":["In-Home Daily-Life Captioning Using Radio Signals"],"prefix":"10.1007","author":[{"given":"Lijie","family":"Fan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianhong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dina","family":"Katabi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,3]]},"reference":[{"key":"7_CR1","unstructured":"Adib, F., Kabelac, Z., Katabi, D., Miller, R.C.: 3D tracking via body radio reflections. In: 11th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2014, pp. 317\u2013329 (2014)"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Adib, F., Katabi, D.: See through walls with WiFi!, vol. 43. ACM (2013)","DOI":"10.1145\/2486001.2486039"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Baraldi, L., Grana, C., Cucchiara, R.: Hierarchical boundary-aware neural encoder for video captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1657\u20131666 (2017)","DOI":"10.1109\/CVPR.2017.339"},{"issue":"4","key":"7_CR4","doi-asserted-by":"publisher","first-page":"331","DOI":"10.5594\/J07262","volume":"73","author":"L Barbrow","year":"1964","unstructured":"Barbrow, L.: International lighting vocabulary. J. SMPTE 73(4), 331\u2013332 (1964)","journal-title":"J. SMPTE"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"7_CR6","unstructured":"Chen, X., et al.: Microsoft COCO captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Chetty, K., Chen, Q., Ritchie, M., Woodbridge, K.: A low-cost through-the-wall FMCW radar for stand-off operation and activity detection. In: Radar Sensor Technology XXI, vol. 10188, p. 1018808. International Society for Optics and Photonics (2017)","DOI":"10.1117\/12.2261680"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Denkowski, M., Lavie, A.: Meteor universal: language specific translation evaluation for any target language. In: Proceedings of the 9th Workshop on Statistical Machine Translation, pp. 376\u2013380 (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Du, Y., Fu, Y., Wang, L.: Skeleton based action recognition with convolutional neural network. In: 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), pp. 579\u2013583. IEEE (2015)","DOI":"10.1109\/ACPR.2015.7486569"},{"key":"7_CR10","unstructured":"Fakoor, R., Mohamed, A., Mitchell, M., Kang, S.B., Kohli, P.: Memory-augmented attention modelling for videos. arXiv preprint arXiv:1611.02261 (2016)"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Fan, L., Li, T., Fang, R., Hristov, R., Yuan, Y., Katabi, D.: Learning longterm representations for person re-identification using radio signals. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10699\u201310709 (2020)","DOI":"10.1109\/CVPR42600.2020.01071"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Gan, C., Gan, Z., He, X., Gao, J., Deng, L.: StyleNet: generating attractive visual captions with styles. In: CVPR, pp. 3137\u20133146 (2017)","DOI":"10.1109\/CVPR.2017.108"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Gan, Z., et al.: Semantic compositional networks for visual captioning. In: CVPR, pp. 5630\u20135639 (2017)","DOI":"10.1109\/CVPR.2017.127"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Hsu, C.Y., Ahuja, A., Yue, S., Hristov, R., Kabelac, Z., Katabi, D.: Zero-effort in-home sleep and insomnia monitoring using radio signals. In: Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, vol. 1, no. 3, pp. 1\u201318 (2017)","DOI":"10.1145\/3130924"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Hsu, C.Y., Hristov, R., Lee, G.H., Zhao, M., Katabi, D.: Enabling identification and behavioral sensing in homes using radio reflections. In: Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, p. 548. ACM (2019)","DOI":"10.1145\/3290605.3300778"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Hsu, C.Y., Liu, Y., Kabelac, Z., Hristov, R., Katabi, D., Liu, C.: Extracting gait velocity and stride length from surrounding radio signals. In: Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, pp. 2116\u20132126 (2017)","DOI":"10.1145\/3025453.3025937"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Hu, Y., Chen, Z., Zha, Z.J., Wu, F.: Hierarchical global-local temporal modeling for video captioning. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 774\u2013783 (2019)","DOI":"10.1145\/3343031.3351072"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Li, C., Zhong, Q., Xie, D., Pu, S.: Co-occurrence feature learning from skeleton data for action recognition and detection with hierarchical aggregation. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence, pp. 786\u2013792 (2018)","DOI":"10.24963\/ijcai.2018\/109"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Li, T., Fan, L., Zhao, M., Liu, Y., Katabi, D.: Making the invisible visible: action recognition through walls and occlusions. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 872\u2013881 (2019)","DOI":"10.1109\/ICCV.2019.00096"},{"issue":"4","key":"7_CR20","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1145\/2897824.2925953","volume":"35","author":"J Lien","year":"2016","unstructured":"Lien, J.: Soli: ubiquitous gesture sensing with millimeter wave radar. ACM Trans. Graph. (TOG) 35(4), 142 (2016)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"7_CR21","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out (2004)"},{"key":"7_CR22","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1162\/tacl_a_00013","volume":"6","author":"X Long","year":"2018","unstructured":"Long, X., Gan, C., de Melo, G.: Video captioning with multi-faceted attention. Trans. Assoc. Comput. Linguist. 6, 173\u2013184 (2018)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Pan, P., Xu, Z., Yang, Y., Wu, F., Zhuang, Y.: Hierarchical recurrent neural encoder for video representation with application to captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1029\u20131038 (2016)","DOI":"10.1109\/CVPR.2016.117"},{"key":"7_CR24","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 on Association for Computational Linguistics, pp. 311\u2013318. Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Pasunuru, R., Bansal, M.: Reinforced video captioning with entailment rewards. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 979\u2013985 (2017)","DOI":"10.18653\/v1\/D17-1103"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Peng, Z., Mu\u00f1oz-Ferreras, J.M., G\u00f3mez-Garc\u00eda, R., Li, C.: FMCW radar fall detection based on ISAR processing utilizing the properties of RCS, range, and Doppler. In: 2016 IEEE MTT-S International Microwave Symposium (IMS), pp. 1\u20133. IEEE (2016)","DOI":"10.1109\/MWSYM.2016.7540121"},{"key":"7_CR27","unstructured":"Ranzato, M., Chopra, S., Auli, M., Zaremba, W.: Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732 (2015)"},{"key":"7_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1007\/978-3-319-46448-0_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"GA Sigurdsson","year":"2016","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: crowdsourcing data collection for activity understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 510\u2013526. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_31"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Song, J., Guo, Z., Gao, L., Liu, W., Zhang, D., Shen, H.T.: Hierarchical LSTM with adjusted temporal attention for video captioning. arXiv preprint arXiv:1706.01231 (2017)","DOI":"10.24963\/ijcai.2017\/381"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Stove, A.G.: Linear FMCW radar techniques. In: IEE Proceedings F (Radar and Signal Processing), vol. 139, pp. 343\u2013350. IET (1992)","DOI":"10.1049\/ip-f-2.1992.0048"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Tian, Y., Lee, G.H., He, H., Hsu, C.Y., Katabi, D.: RF-based fall monitoring using convolutional neural networks. In: Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, vol. 2, no. 3, p. 137 (2018)","DOI":"10.1145\/3264947"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, 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"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Rohrbach, M., Donahue, J., Mooney, R., Darrell, T., Saenko, K.: Sequence to sequence-video to text. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4534\u20134542 (2015)","DOI":"10.1109\/ICCV.2015.515"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Xu, H., Donahue, J., Rohrbach, M., Mooney, R., Saenko, K.: Translating videos to natural language using deep recurrent neural networks. In: Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1494\u20131504 (2015)","DOI":"10.3115\/v1\/N15-1173"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Wang, X., Chen, W., Wu, J., Wang, Y.F., Yang Wang, W.: Video captioning via hierarchical reinforcement learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4213\u20134222 (2018)","DOI":"10.1109\/CVPR.2018.00443"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Wu, X., Li, G., Cao, Q., Ji, Q., Lin, L.: Interpretable video captioning via trajectory structured localization. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 6829\u20136837 (2018)","DOI":"10.1109\/CVPR.2018.00714"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Yao, L., et al.: Describing videos by exploiting temporal structure. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4507\u20134515 (2015)","DOI":"10.1109\/ICCV.2015.512"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Yu, H., Wang, J., Huang, Z., Yang, Y., Xu, W.: Video paragraph captioning using hierarchical recurrent neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4584\u20134593 (2016)","DOI":"10.1109\/CVPR.2016.496"},{"issue":"8","key":"7_CR39","doi-asserted-by":"publisher","first-page":"3278","DOI":"10.1109\/JSEN.2018.2808688","volume":"18","author":"Z Zhang","year":"2018","unstructured":"Zhang, Z., Tian, Z., Zhou, M.: Latern: dynamic continuous hand gesture recognition using FMCW radar sensor. IEEE Sens. J. 18(8), 3278\u20133289 (2018)","journal-title":"IEEE Sens. J."},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Zhao, M., Adib, F., Katabi, D.: Emotion recognition using wireless signals. In: Proceedings of the 22nd Annual International Conference on Mobile Computing and Networking, pp. 95\u2013108. ACM (2016)","DOI":"10.1145\/2973750.2973762"},{"key":"7_CR41","doi-asserted-by":"crossref","unstructured":"Zhao, M., et al.: Through-wall human pose estimation using radio signals. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7356\u20137365 (2018)","DOI":"10.1109\/CVPR.2018.00768"},{"key":"7_CR42","doi-asserted-by":"crossref","unstructured":"Zhao, M., et al.: Through-wall human mesh recovery using radio signals. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 10113\u201310122 (2019)","DOI":"10.1109\/ICCV.2019.01021"},{"key":"7_CR43","doi-asserted-by":"crossref","unstructured":"Zhao, M., et al.: RF-based 3D skeletons. In: Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication, pp. 267\u2013281. ACM (2018)","DOI":"10.1145\/3230543.3230579"},{"key":"7_CR44","unstructured":"Zhao, M., Yue, S., Katabi, D., Jaakkola, T.S., Bianchi, M.T.: Learning sleep stages from radio signals: a conditional adversarial architecture. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 4100\u20134109. JMLR. org (2017)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58536-5_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:35:46Z","timestamp":1730594146000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58536-5_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585358","9783030585365"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58536-5_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"3 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","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":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","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":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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":"7","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}