{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T21:01:43Z","timestamp":1765486903486,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031270765"},{"type":"electronic","value":"9783031270772"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-27077-2_29","type":"book-chapter","created":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T05:03:10Z","timestamp":1679979790000},"page":"373-384","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["EvIs-Kitchen: Egocentric Human Activities Recognition with\u00a0Video and\u00a0Inertial Sensor Data"],"prefix":"10.1007","author":[{"given":"Yuzhe","family":"Hao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kuniaki","family":"Uto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Asako","family":"Kanezaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ikuro","family":"Sato","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rei","family":"Kawakami","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Koichi","family":"Shinoda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,29]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Afouras, T., Chung, J.S., Senior, A., Vinyals, O., Zisserman, A.: Deep audio-visual speech recognition. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 8717\u20138727 (2018)","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Chen, C., Jafari, R., Kehtarnavaz, N.: Utd-mhad: A multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor. In: ICIP, pp. 168\u2013172 (2015)","DOI":"10.1109\/ICIP.2015.7350781"},{"key":"29_CR3","doi-asserted-by":"publisher","unstructured":"Damen, D., et al.: Scaling egocentric vision: The epic-kitchens dataset. In: ECCV, pp. 720\u2013736 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_44","DOI":"10.1007\/978-3-030-01225-0_44"},{"issue":"1","key":"29_CR4","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s11263-021-01531-2","volume":"130","author":"D Damen","year":"2022","unstructured":"Damen, D., et al.: Rescaling egocentric vision: collection, pipeline and challenges for epic-kitchens-100. IJCV 130(1), 33\u201355 (2022)","journal-title":"IJCV"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Eitel, A., Springenberg, J.T., Spinello, L., Riedmiller, M., Burgard, W.: Multimodal deep learning for robust rgb-d object recognition. In: IROS, pp. 681\u2013687 (2015)","DOI":"10.1109\/IROS.2015.7353446"},{"key":"29_CR6","doi-asserted-by":"publisher","unstructured":"Fathi, A., Li, Y., Rehg, J.M.: Learning to recognize daily actions using gaze. In: ECCV, pp. 314\u2013327 (2012). https:\/\/doi.org\/10.1007\/978-3-642-33718-5_23","DOI":"10.1007\/978-3-642-33718-5_23"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Ghadiyaram, D., Tran, D., Mahajan, D.: Large-scale weakly-supervised pre-training for video action recognition. In: CVPR, pp. 12046\u201312055 (2019)","DOI":"10.1109\/CVPR.2019.01232"},{"key":"29_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"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Imran, J., Raman, B.: Multimodal egocentric activity recognition using multi-stream cnn. In: ICVGIP, pp. 1\u20138 (2018)","DOI":"10.1145\/3293353.3293363"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Jang, Y., Sullivan, B., Ludwig, C., Gilchrist, I., Damen, D., Mayol-Cuevas, W.: Epic-tent: An egocentric video dataset for camping tent assembly. In: ICCV Workshops, pp. 0\u20130 (2019)","DOI":"10.1109\/ICCVW.2019.00547"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Kapidis, G., Poppe, R., Van Dam, E., Noldus, L., Veltkamp, R.: Egocentric hand track and object-based human action recognition. In: SmartWorld\/SCALCOM\/UIC\/ATC\/CBDCom\/IOP\/SCI, pp. 922\u2013929 (2019)","DOI":"10.1109\/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00185"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Kazakos, E., Nagrani, A., Zisserman, A., Damen, D.: Epic-fusion: Audio-visual temporal binding for egocentric action recognition. In: CVPR, pp. 5492\u20135501 (2019)","DOI":"10.1109\/ICCV.2019.00559"},{"key":"29_CR13","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.patrec.2018.07.011","volume":"112","author":"H Kwon","year":"2018","unstructured":"Kwon, H., Kim, Y., Lee, J.S., Cho, M.: First person action recognition via two-stream convnet with long-term fusion pooling. Pattern Recogn. Lett. 112, 161\u2013167 (2018)","journal-title":"Pattern Recogn. Lett."},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: CVPR, pp. 1\u20138. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., Ye, Z., Rehg, J.M.: Delving into egocentric actions. In: CVPR, pp. 287\u2013295 (2015)","DOI":"10.1109\/CVPR.2015.7298625"},{"issue":"8","key":"29_CR16","doi-asserted-by":"publisher","first-page":"3703","DOI":"10.1109\/TIP.2019.2901707","volume":"28","author":"M Lu","year":"2019","unstructured":"Lu, M., Li, Z.N., Wang, Y., Pan, G.: Deep attention network for egocentric action recognition. IEEE Trans. Image Process. 28(8), 3703\u20133713 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Lu, M., Liao, D., Li, Z.N.: Learning spatiotemporal attention for egocentric action recognition. In: ICCV Workshops, pp. 4425\u20134434 (2019)","DOI":"10.1109\/ICCVW.2019.00543"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Ma, M., Fan, H., Kitani, K.M.: Going deeper into first-person activity recognition. In: CVPR, pp. 1894\u20131903 (2016)","DOI":"10.1109\/CVPR.2016.209"},{"issue":"13","key":"29_CR19","doi-asserted-by":"publisher","first-page":"3812","DOI":"10.1093\/nar\/gkg509","volume":"31","author":"PC Ng","year":"2003","unstructured":"Ng, P.C., Henikoff, S.: Sift: predicting amino acid changes that affect protein function. Nucleic Acids Res. 31(13), 3812\u20133814 (2003)","journal-title":"Nucleic Acids Res."},{"key":"29_CR20","doi-asserted-by":"publisher","unstructured":"Owens, A., Efros, A.A.: Audio-visual scene analysis with self-supervised multisensory features. In: ECCV, pp. 631\u2013648 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_39","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"29_CR21","doi-asserted-by":"publisher","first-page":"53540","DOI":"10.1109\/ACCESS.2021.3070646","volume":"9","author":"Y Shavit","year":"2021","unstructured":"Shavit, Y., Klein, I.: Boosting inertial-based human activity recognition with transformers. IEEE Access 9, 53540\u201353547 (2021)","journal-title":"IEEE Access"},{"key":"29_CR22","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. arXiv preprint arXiv:1406.2199 (2014)"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Singh, S., Arora, C., Jawahar, C.: First person action recognition using deep learned descriptors. In: CVPR, pp. 2620\u20132628 (2016)","DOI":"10.1109\/CVPR.2016.287"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Song, S., et al.: Multimodal multi-stream deep learning for egocentric activity recognition. In: CVPR Workshops, pp. 24\u201331 (2016)","DOI":"10.1109\/CVPRW.2016.54"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Song, S., Cheung, N.M., Chandrasekhar, V., Mandal, B., Liri, J.: Egocentric activity recognition with multimodal fisher vector. In: ICASSP, pp. 2717\u20132721 (2016)","DOI":"10.1109\/ICASSP.2016.7472171"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Sudhakaran, S., Escalera, S., Lanz, O.: Lsta: Long short-term attention for egocentric action recognition. In: CVPR, pp. 9954\u20139963 (2019)","DOI":"10.1109\/CVPR.2019.01019"},{"issue":"10","key":"29_CR27","doi-asserted-by":"publisher","first-page":"3001","DOI":"10.1109\/TCSVT.2018.2875441","volume":"29","author":"Y Tang","year":"2018","unstructured":"Tang, Y., Wang, Z., Lu, J., Feng, J., Zhou, J.: Multi-stream deep neural networks for rgb-d egocentric action recognition. IEEE Trans. Circuits Syst. Video Technol. 29(10), 3001\u20133015 (2018)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"29_CR28","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: ICCV, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"29_CR29","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: CVPR, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Wang, X., Wu, Y., Zhu, L., Yang, Y.: Symbiotic attention with privileged information for egocentric action recognition. In: AAAI, vol. 34, pp. 12249\u201312256 (2020)","DOI":"10.1609\/aaai.v34i07.6907"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-27077-2_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T05:14:30Z","timestamp":1679980470000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-27077-2_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031270765","9783031270772"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-27077-2_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"29 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bergen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Norway","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 January 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2023","order":10,"name":"conference_id","label":"Conference ID","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":"Conftool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"267","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":"86","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":"32% - 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":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}