{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:30:43Z","timestamp":1776889843224,"version":"3.51.2"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031441943","type":"print"},{"value":"9783031441950","type":"electronic"}],"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\/978-3-031-44195-0_20","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T12:04:08Z","timestamp":1695297848000},"page":"233-245","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Visual-Haptic-Kinesthetic Object Recognition with\u00a0Multimodal Transformer"],"prefix":"10.1007","author":[{"given":"Xinyuan","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyong","family":"Lan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyuan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Allen, P.K.: Surface descriptions from vision and touch. In: IEEE International Conference on Robotics & Automation, pp. 394\u2013397 (1984)","DOI":"10.1109\/ROBOT.1984.1087191"},{"key":"20_CR2","unstructured":"Allen, P.K.: Integrating Vision and Touch for Object Recognition Tasks, pp. 407\u2013440. Ablex Publishing Corp., USA (1995)"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Bednarek, M., Kicki, P., Walas, K.: On robustness of multi-modal fusion-robotics perspective. Electronics 9, 1152 (2020)","DOI":"10.3390\/electronics9071152"},{"key":"20_CR4","unstructured":"Bonner, L.E.R., Buhl, D.D., Kristensen, K., Navarro-Guerrero, N.: Au dataset for visuo-haptic object recognition for robots (2021)"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Cao, G., Zhou, Y., Bollegala, D., Luo, S.: Spatio-temporal attention model for tactile texture recognition. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 9896\u20139902 (2020)","DOI":"10.1109\/IROS45743.2020.9341333"},{"key":"20_CR6","unstructured":"Chen, Y., Sipos, A., Van der Merwe, M., Fazeli, N.: Visuo-tactile transformers for manipulation. In: 2022 Conference on Robot Learning (CoRL). Proceedings of Machine Learning Research, vol. 205, pp. 2026\u20132040 (2022)"},{"key":"20_CR7","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1016\/j.robot.2014.09.021","volume":"63","author":"V Chu","year":"2015","unstructured":"Chu, V., et al.: Robotic learning of haptic adjectives through physical interaction. Robot. Auton. Syst. 63, 279\u2013292 (2015)","journal-title":"Robot. Auton. Syst."},{"issue":"2","key":"20_CR8","doi-asserted-by":"publisher","first-page":"9529","DOI":"10.1016\/j.ifacol.2020.12.2430","volume":"53","author":"S Cui","year":"2020","unstructured":"Cui, S., Wei, J., Li, X., Wang, R., Wang, S.: Generalized visual-tactile transformer network for slip detection. IFAC-PapersOnLine 53(2), 9529\u20139534 (2020)","journal-title":"IFAC-PapersOnLine"},{"issue":"4","key":"20_CR9","doi-asserted-by":"publisher","first-page":"5827","DOI":"10.1109\/LRA.2020.3010720","volume":"5","author":"S Cui","year":"2020","unstructured":"Cui, S., Wang, R., Wei, J., Hu, J., Wang, S.: Self-attention based visual-tactile fusion learning for predicting grasp outcomes. IEEE Robot. Autom. Lett. 5(4), 5827\u20135834 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"20_CR11","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale (2020)"},{"key":"20_CR12","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.robot.2016.10.001","volume":"91","author":"SR Fanello","year":"2017","unstructured":"Fanello, S.R., Ciliberto, C., Noceti, N., Metta, G., Odone, F.: Visual recognition for humanoid robots. Robot. Auton. Syst. 91, 151\u2013168 (2017)","journal-title":"Robot. Auton. Syst."},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Gao, Y., Hendricks, L.A., Kuchenbecker, K.J., Darrell, T.: Deep learning for tactile understanding from visual and haptic data (2015)","DOI":"10.1109\/ICRA.2016.7487176"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Networks Official J. Int. Neural Network Soc. 18, 602\u201310 (2005)","DOI":"10.1016\/j.neunet.2005.06.042"},{"issue":"8","key":"20_CR15","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":"20_CR16","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations, December 2014"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Le, M., Rathour, V., Truong, Q., Mai, Q., Brijesh, P., Le, N.: Multi-module recurrent convolutional neural network with transformer encoder for ECG arrhythmia classification, pp. 1\u20135 (2021)","DOI":"10.1109\/BHI50953.2021.9508527"},{"issue":"2","key":"20_CR18","doi-asserted-by":"publisher","first-page":"996","DOI":"10.1109\/TASE.2016.2549552","volume":"14","author":"H Liu","year":"2017","unstructured":"Liu, H., Yu, Y., Sun, F., Gu, J.: Visual-tactile fusion for object recognition. IEEE Trans. Autom. Sci. Eng. 14(2), 996\u20131008 (2017)","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Luo, S., Yuan, W., Adelson, E., Cohn, A.G., Fuentes, R.: Vitac: feature sharing between vision and tactile sensing for cloth texture recognition. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 2722\u20132727 (2018)","DOI":"10.1109\/ICRA.2018.8460494"},{"issue":"2","key":"20_CR20","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1109\/TOH.2019.2952118","volume":"13","author":"M Strese","year":"2020","unstructured":"Strese, M., Brudermueller, L., Kirsch, J., Steinbach, E.: Haptic material analysis and classification inspired by human exploratory procedures. IEEE Trans. Haptics 13(2), 404\u2013424 (2020)","journal-title":"IEEE Trans. Haptics"},{"issue":"7","key":"20_CR21","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1109\/TSMC.2016.2524059","volume":"46","author":"F Sun","year":"2016","unstructured":"Sun, F., Liu, C., Huang, W., Zhang, J.: Object classification and grasp planning using visual and tactile sensing. IEEE Trans. Syst. Man Cybern. Syst. 46(7), 969\u2013979 (2016)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818\u20132826. Los Alamitos, CA, USA, June 2016","DOI":"10.1109\/CVPR.2016.308"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Tatiya, G., Sinapov, J.: Deep multi-sensory object category recognition using interactive behavioral exploration. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 7872\u20137878 (2019)","DOI":"10.1109\/ICRA.2019.8794095"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Toprak, S., Navarro-Guerrero, N., Wermter, S.: Evaluating integration strategies for visuo-haptic object recognition. Cognitive Comput. 10, 408\u2013425 (2018)","DOI":"10.1007\/s12559-017-9536-7"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H., Bai, S., Liang, P., Kolter, J., Morency, L.P., Salakhutdinov, R.: Multimodal transformer for unaligned multimodal language sequences, vol. 2019, pp. 6558\u20136569, July 2019","DOI":"10.18653\/v1\/P19-1656"},{"key":"20_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS 2017, pp. 6000\u20136010. Curran Associates Inc., Red Hook (2017)"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Yang, J., Liu, H., Sun, F., Gao, M.: Object recognition using tactile and image information. In: 2015 IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 1746\u20131751 (2015)","DOI":"10.1109\/ROBIO.2015.7419024"},{"key":"20_CR28","doi-asserted-by":"publisher","first-page":"54525","DOI":"10.1109\/ACCESS.2022.3174874","volume":"10","author":"P Zhang","year":"2022","unstructured":"Zhang, P., Zhou, M., Shan, D., Chen, Z., Wang, X.: Object description using visual and tactile data. IEEE Access 10, 54525\u201354536 (2022)","journal-title":"IEEE Access"},{"issue":"11","key":"20_CR29","doi-asserted-by":"publisher","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","volume":"30","author":"ZQ Zhao","year":"2019","unstructured":"Zhao, Z.Q., Zheng, P., Xu, S.T., Wu, X.: Object detection with deep learning: a review. IEEE Trans. Neural Networks Learn. Syst. 30(11), 3212\u20133232 (2019)","journal-title":"IEEE Trans. Neural Networks Learn. Syst."}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44195-0_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T16:05:47Z","timestamp":1730131547000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44195-0_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031441943","9783031441950"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44195-0_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heraklion","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","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":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","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":"426","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":"22","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":"45% - 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":"2.4","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)"}},{"value":"type of other papers accepted : 9 Abstract","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)"}}]}}