{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T15:40:46Z","timestamp":1770392446232,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557578","type":"print"},{"value":"9789819557585","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-5758-5_8","type":"book-chapter","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T05:00:15Z","timestamp":1770354015000},"page":"85-98","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Decoupling Spatio-Temporal Feature Extraction for\u00a0Object Tracking"],"prefix":"10.1007","author":[{"given":"Wei","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Yuchao","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Yun","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,7]]},"reference":[{"key":"8_CR1","doi-asserted-by":"publisher","first-page":"80297","DOI":"10.1109\/ACCESS.2023.3298440","volume":"11","author":"J Kugarajeevan","year":"2023","unstructured":"Kugarajeevan, J., Kokul, T., Ramanan, A., Fernando, S.: Transformers in single object tracking: an experimental survey. IEEE Access 11, 80297\u201380326 (2023)","journal-title":"IEEE Access"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Yan, B., Peng, H., Fu, J., Wang, D., Lu, H.: Learning spatio-temporal transformer for visual tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10448\u201310457 (2021)","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Lan, J.P., et al.: Procontext: exploring progressive context transformer for tracking. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10094971"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Wang, S., Wang, Z., Sun, Q., Cheng, G., Ning, J.: Modelling of multiple spatial-temporal relations for robust visual object tracking. IEEE Transactions on Image Processing (2024)","DOI":"10.1109\/TIP.2024.3453028"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Fu, Z., Liu, Q., Fu, Z., Wang, Y.: Stmtrack: template-free visual tracking with space-time memory networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13774\u201313783 (2021)","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Cai, W., Liu, Q., Wang, Y.: Hiptrack: visual tracking with historical prompts. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19258\u201319267 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265019315","DOI":"10.1109\/CVPR52733.2024.01822"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Wang, N., Zhou, W., Wang, J., Li, H.: Transformer meets tracker: exploiting temporal context for robust visual tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1571\u20131580 (2021)","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Xie, F., Chu, L., Li, J., Lu, Y., Ma, C.: Videotrack: learning to track objects via video transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22826\u201322835 (2023)","DOI":"10.1109\/CVPR52729.2023.02186"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Ye, B., Chang, H., Ma, B., Shan, S., Chen, X.: Joint feature learning and relation modeling for tracking: a one-stream framework. In: European Conference on Computer Vision, pp. 341\u2013357. Springer (2022)","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"8_CR10","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: ICML, vol.\u00a02, p.\u00a04 (2021)"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: Vivit: a video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Neimark, D., Bar, O., Zohar, M., Asselmann, D.: Video transformer network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3163\u20133172 (2021)","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"8_CR13","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":"8_CR14","doi-asserted-by":"crossref","unstructured":"Gao, S., Zhou, C., Zhang, J.: Generalized relation modeling for transformer tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18686\u201318695 (2023)","DOI":"10.1109\/CVPR52729.2023.01792"},{"issue":"5","key":"8_CR15","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":"8_CR16","doi-asserted-by":"crossref","unstructured":"Gao, J., Zhong, B., Chen, Y.: Unambiguous object tracking by exploiting target cues. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 1997\u20132005 (2023)","DOI":"10.1145\/3581783.3612240"},{"key":"8_CR17","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"8_CR21","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":"8_CR22","doi-asserted-by":"crossref","unstructured":"Muller, M., Bibi, A., Giancola, S., Alsubaihi, S., Ghanem, B.: Trackingnet: a large-scale dataset and benchmark for object tracking in the wild. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 300\u2013317 (2018)","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: Computer vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, part v 13, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Kiani\u00a0Galoogahi, H., Fagg, A., Huang, C., Ramanan, D., Lucey, S.: Need for speed: a benchmark for higher frame rate object tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1125\u20131134 (2017)","DOI":"10.1109\/ICCV.2017.128"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Mueller, M., Smith, N., Ghanem, B.: A benchmark and simulator for UAV tracking. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision \u2013 ECCV 2016, pp. 445\u2013461. Springer International Publishing, Cham (2016)","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Towards more flexible and accurate object tracking with natural language: Algorithms and benchmark. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13763\u201313773 (2021)","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Zhu, J., et al.: Exploring dynamic transformer for efficient object tracking. IEEE Transactions on Neural Networks and Learning Systems (2025)","DOI":"10.1109\/TNNLS.2025.3545752"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Zhu, J., Tang, H., Chen, X., Wang, X., Wang, D., Lu, H.: Two-stream beats one-stream: asymmetric Siamese network for efficient visual tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a039, pp. 10959\u201310967 (2025)","DOI":"10.1609\/aaai.v39i10.33191"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Cai, Y., Liu, J., Tang, J., Wu, G.: Robust object modeling for visual tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9589\u20139600 (2023)","DOI":"10.1109\/ICCV51070.2023.00879"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: Backbone is all your need: a simplified architecture for visual object tracking. In: European Conference on Computer Vision, pp. 375\u2013392. Springer (2022)","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"8_CR31","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"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5758-5_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T05:00:22Z","timestamp":1770354022000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5758-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557578","9789819557585"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5758-5_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"7 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}},{"value":"All data generated or analyzed during this study are included in this published article.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Data Availability"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}