{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T14:55:48Z","timestamp":1743000948829,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819629138"},{"type":"electronic","value":"9789819629145"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-2914-5_21","type":"book-chapter","created":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T09:34:58Z","timestamp":1741599298000},"page":"223-232","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Transformer-Based Visual Tracking for Edge Computing Devices"],"prefix":"10.1007","author":[{"given":"Yixin","family":"Xu","sequence":"first","affiliation":[]},{"given":"Tianyang","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Wenkang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jinhui","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Zinan","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Wankou","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,11]]},"reference":[{"key":"21_CR1","unstructured":"Vaswani, A., et al.: Attention is all You need. In: Advances in Neural Information Processing Systems. Curran Associates, Inc. (2017)"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., Lu, H.: Transformer tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8126\u20138135 (2021)","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"21_CR3","doi-asserted-by":"publisher","unstructured":"Ye, B., Chang, H., Ma, B., Shan, S., Chen, X.: Joint feature learning and relation modeling for tracking: a one-stream framework. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13682, pp. 341\u2013357. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_20","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"21_CR4","doi-asserted-by":"publisher","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.S.: Fully-convolutional Siamese networks for object tracking. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 850\u2013865. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_56","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Kang, B., Chen, X., Wang, D., Peng, H., Lu, H.: Exploring lightweight hierarchical vision transformers for efficient visual tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9612\u20139621 (2023)","DOI":"10.1109\/ICCV51070.2023.00881"},{"issue":"1","key":"21_CR6","doi-asserted-by":"publisher","first-page":"1126","DOI":"10.1109\/TITS.2022.3155488","volume":"24","author":"S Yang","year":"2022","unstructured":"Yang, S., Lu, H., Li, J.: Multifeature fusion-based object detection for intelligent transportation systems. IEEE Trans. Intell. Transp. Syst. 24(1), 1126\u20131133 (2022)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Tao, R., Gavves, E., Smeulders, A.W.M.: Siamese instance search for tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1420\u20131429 (2016)","DOI":"10.1109\/CVPR.2016.158"},{"key":"21_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jiang, C., Wang, L., Wu, G.: MixFormer: end-to-end tracking with iterative mixed attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13608\u201313618 (2022)","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Chen, X., Peng, H., Wang, D., Lu, H., Hu, H.: SeqTrack: sequence to sequence learning for visual object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14572\u201314581 (2023)","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Wei, X., Bai, Y., Zheng, Y., Shi, D., Gong, Y.: Autoregressive visual tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9697\u20139706 (2023)","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"21_CR12","first-page":"3","volume":"1","author":"C Ma","year":"2021","unstructured":"Ma, C., et al.: Visual information processing for deep-sea visual monitoring system. Cogn. Rob. 1, 3\u201311 (2021)","journal-title":"Cogn. Rob."},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Tang, M., Feng, J.: Multi-kernel correlation filter for visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3038\u20133046 (2015)","DOI":"10.1109\/ICCV.2015.348"},{"issue":"1","key":"21_CR14","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1109\/TFUZZ.2020.2984991","volume":"29","author":"H Lu","year":"2020","unstructured":"Lu, H., Zhang, M., Xu, X., Li, Y., Shen, H.T.: Deep fuzzy hashing network for efficient image retrieval. IEEE Trans. Fuzzy Syst. 29(1), 166\u2013176 (2020)","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Yan, B., Peng, H., Wu, K., Wang, D., Fu, J., Lu, H.: LightTrack: finding lightweight neural networks for object tracking via one-shot architecture search. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15180\u201315189 (2021)","DOI":"10.1109\/CVPR46437.2021.01493"},{"key":"21_CR16","doi-asserted-by":"publisher","unstructured":"Borsuk, V., Vei, R., Kupyn, O., Martyniuk, T., Krashenyi, I., Matas, J.: FEAR: fast, efficient, accurate and robust visual tracker. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13682, pp. 644\u2013663. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_37","DOI":"10.1007\/978-3-031-20047-2_37"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Blatter, P., Kanakis, M., Danelljan, M., Van Gool, L.: Efficient visual tracking with exemplar transformers. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1571\u20131581 (2023)","DOI":"10.1109\/WACV56688.2023.00162"},{"key":"21_CR18","doi-asserted-by":"publisher","unstructured":"Chen, X., Kang, B., Wang, D., Li, D., Lu, H.: Efficient visual tracking via hierarchical cross-attention transformer. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) ECCV 2022. LNCS, vol. 13808, pp. 461\u2013477. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-25085-9_26","DOI":"10.1007\/978-3-031-25085-9_26"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Chen, C.-F.R., Fan, Q., Panda, R.: CrossViT: cross-attention multi-scale vision transformer for image classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 357\u2013366 (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Graham, B., et al.: LeViT: a vision transformer in ConvNet\u2019s clothing for faster inference. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12259\u201312269 (2021)","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, H., Zhao, L., Chen, T., Arik, S.\u00d6., Pfister, T.: Nested hierarchical transformer: towards accurate, data-efficient and interpretable visual understanding. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3417\u20133425 (2022)","DOI":"10.1609\/aaai.v36i3.20252"},{"key":"21_CR23","unstructured":"Steiner, A., Kolesnikov, A., Zhai, X., Wightman, R., Uszkoreit, J., Beyer, L.: How to train your ViT data, augmentation, and regularization in vision transformers. arXiv preprint arXiv:2106.10270 (2021)"},{"key":"21_CR24","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1007\/978-3-030-01246-5_19","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M M\u00fcller","year":"2018","unstructured":"M\u00fcller, M., Bibi, A., Giancola, S., Alsubaihi, S., Ghanem, B.: TrackingNet: a large-scale dataset and benchmark for object tracking in the wild. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11205, pp. 310\u2013327. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_19"},{"issue":"5","key":"21_CR25","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1109\/TPAMI.2019.2957464","volume":"43","author":"L Huang","year":"2019","unstructured":"Huang, L., Zhao, X., Huang, K.: GOT-10k: a large high-diversity benchmark for generic object tracking in the wild. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1562\u20131577 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: LaSOT: a high-quality benchmark for large-scale single object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5374\u20135383 (2019)","DOI":"10.1109\/CVPR.2019.00552"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: COCO-Stuff: thing and stuff classes in context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1209\u20131218 (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"21_CR28","unstructured":"Cui, Y., Song, T., Wu, G., Wang, L.: MixFormerV2: efficient fully transformer tracking. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"issue":"7","key":"21_CR29","doi-asserted-by":"publisher","first-page":"8508","DOI":"10.1109\/TII.2022.3218839","volume":"19","author":"M Wang","year":"2022","unstructured":"Wang, M., Wang, J., Li, Y., et al.: Edge computing with complementary capsule networks for mental state detection in underground mining industry. IEEE Trans. Industr. Inf. 19(7), 8508\u20138517 (2022)","journal-title":"IEEE Trans. Industr. Inf."}],"container-title":["Communications in Computer and Information Science","Artificial Intelligence and Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2914-5_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T09:35:15Z","timestamp":1741599315000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2914-5_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819629138","9789819629145"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2914-5_21","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"11 March 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISAIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Artificial Intelligence and Robotics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guilin","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isair2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/isair.site\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}