{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T08:59:46Z","timestamp":1772787586288,"version":"3.50.1"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"21","license":[{"start":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T00:00:00Z","timestamp":1724112000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T00:00:00Z","timestamp":1724112000000},"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":["Appl Intell"],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1007\/s10489-024-05710-9","type":"journal-article","created":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T07:03:37Z","timestamp":1724137417000},"page":"10581-10595","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Swin transformer-based traffic video text tracking"],"prefix":"10.1007","volume":"54","author":[{"given":"Jinyao","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4245-3246","authenticated-orcid":false,"given":"Jiangbo","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Xin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihong","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,20]]},"reference":[{"key":"5710_CR1","doi-asserted-by":"crossref","unstructured":"Wang L, Wang Y, Shan S, Su F (2018) Scene text detection and tracking in video with background cues. Proceedings of the 2018 ACM on international conference on multimedia retrieval, pp 160\u2013168","DOI":"10.1145\/3206025.3206051"},{"key":"5710_CR2","doi-asserted-by":"crossref","unstructured":"Chen Y, Xia R, Yang K, Zou K (2023) Gcam: lightweight image inpainting via group convolution and attention mechanism. Int J Mach Learn Cybern","DOI":"10.1007\/s13042-023-01999-z"},{"issue":"6","key":"5710_CR3","first-page":"101567","volume":"35","author":"Y Chen","year":"2023","unstructured":"Chen Y, Xia R, Yang K, Zou K (2023) Dargs: image inpainting algorithm via deep attention residuals group and semantics. J King Saud Univ - Comput Inf Sci 35(6):101567","journal-title":"J King Saud Univ - Comput Inf Sci"},{"key":"5710_CR4","doi-asserted-by":"crossref","first-page":"123111","DOI":"10.1016\/j.eswa.2023.123111","volume":"245","author":"Y Chen","year":"2024","unstructured":"Chen Y, Xia R, Yang K, Zou K (2024) Micu: image super-resolution via multi-level information compensation and u-net. Expert Syst Appl 245:123111","journal-title":"Expert Syst Appl"},{"key":"5710_CR5","doi-asserted-by":"crossref","first-page":"103883","DOI":"10.1016\/j.cviu.2023.103883","volume":"238","author":"Y Chen","year":"2024","unstructured":"Chen Y, Xia R, Yang K, Zou K (2024) Mfmam: image inpainting via multi-scale feature module with attention module. Comput Vis Image Understand 238:103883","journal-title":"Comput Vis Image Understand"},{"key":"5710_CR6","doi-asserted-by":"crossref","unstructured":"Wu Q, Yang T, Liu Z (2023) DropMAE: masked autoencoders with Spatial-Attention dropout for tracking tasks. IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR52729.2023.01399"},{"key":"5710_CR7","unstructured":"Liu\u00a0Z, Lin Y et al (2021) Swin transformer: hierarchical vision transformer using shifted windows. IEEE\/CVF international conference on computer vision, pp 10012\u201310022"},{"key":"5710_CR8","doi-asserted-by":"crossref","unstructured":"Liao M, Shi B, Bai X, Wang X, Liu W (2017) Textboxes: a fast text detector with a single deep neural network. AAAI Conf. Artif. Intell., pp 4161\u20134167","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"5710_CR9","doi-asserted-by":"crossref","unstructured":"Shi B, Bai X, Belongie S (2017) Detecting oriented text in natural images by linking segments. IEEE conference on computer vision and pattern recognition (CVPR), pp 3482\u20133490","DOI":"10.1109\/CVPR.2017.371"},{"key":"5710_CR10","doi-asserted-by":"crossref","unstructured":"Zhou X, Yao C, Wen H, Wang Y, Zhou S, He W, Liang J (2017) East: An efficient and accurate scene text detector. IEEE conference on computer vision and pattern recognition (CVPR), pp 2642\u20132651","DOI":"10.1109\/CVPR.2017.283"},{"issue":"8","key":"5710_CR11","doi-asserted-by":"crossref","first-page":"3676","DOI":"10.1109\/TIP.2018.2825107","volume":"27","author":"M Liao","year":"2018","unstructured":"Liao M, Shi B, Bai X (2018) Textboxes++: a single-shot oriented scene text detector. IEEE Trans Image Process 27(8):3676\u20133690","journal-title":"IEEE Trans Image Process"},{"key":"5710_CR12","doi-asserted-by":"crossref","unstructured":"Lyu P, Yao C, Wu W, Yan S, Bai X (2018) Multi-oriented scene text detection via corner localization and region segmentation. IEEE\/CVF conference on computer vision and pattern recognition, pp 7553\u20137563","DOI":"10.1109\/CVPR.2018.00788"},{"key":"5710_CR13","doi-asserted-by":"crossref","unstructured":"Wang W, Xie E, Li X, Hou W, Lu T, Yu G, Shao S (2019) Shape robust text detection with progressive scale expansion network. IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 9328\u20139337","DOI":"10.1109\/CVPR.2019.00956"},{"key":"5710_CR14","unstructured":"Liao M, Lyu P, Xiang B (2018) Mask textspotter: an end-to-end trainable neural network for spotting text with arbitrary shapes. European conference on computer vision, pp 71\u201388"},{"key":"5710_CR15","doi-asserted-by":"crossref","unstructured":"Baek Y, Lee B, Han D, Yun S, Lee H (2019) Character region awareness for text detection. IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 9357\u20139366","DOI":"10.1109\/CVPR.2019.00959"},{"key":"5710_CR16","doi-asserted-by":"crossref","unstructured":"Xing L, Tian Z, Huang W, Scott M (2019) Convolutional character networks. IEEE\/CVF international conference on computer vision (ICCV), pp 9125\u20139135","DOI":"10.1109\/ICCV.2019.00922"},{"key":"5710_CR17","unstructured":"Yang X-H, He W, Yin F, Liu C-L (2017) A unified video text detection method with network flow. 14th IAPR international conference on document analysis and recognition (ICDAR), vol 01, pp 331\u2013336"},{"issue":"7","key":"5710_CR18","first-page":"601","volume":"26","author":"H Yu","year":"2019","unstructured":"Yu H, Zhang C, Li X, Han J, Ding E, Wang L (2019) An end-to-end video text detector with online tracking. Int Conf Doc Anal Recognit 26(7):601\u2013606","journal-title":"Int Conf Doc Anal Recognit"},{"key":"5710_CR19","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60:91\u2013110","journal-title":"Int J Comput Vis"},{"key":"5710_CR20","first-page":"886","volume":"1","author":"N Dalal","year":"2005","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. IEEE Comput Soc Conf Comput Vis Pattern Recognit 1:886\u2013893","journal-title":"IEEE Comput Soc Conf Comput Vis Pattern Recognit"},{"key":"5710_CR21","doi-asserted-by":"crossref","first-page":"822","DOI":"10.1109\/TIP.2020.3038520","volume":"30","author":"Z Cheng","year":"2021","unstructured":"Cheng Z, Lu J, Zou B (2021) Free: a fast and robust end-to-end video text spotter. IEEE Trans Image Process 30:822\u2013837","journal-title":"IEEE Trans Image Process"},{"key":"5710_CR22","doi-asserted-by":"crossref","unstructured":"Cheng Z, Lu J, Niu Y, Pu S, Wu F, Zhou S (2019) You only recognize once: towards fast video text spotting. Proceedings of the 27th ACM international conference on multimedia","DOI":"10.1145\/3343031.3351093"},{"key":"5710_CR23","unstructured":"Wu W, Shen C, Cai Y, Zhang D, Ying F, Ping L, Zhou H (2022) End-to-end video text spotting with transformer"},{"key":"5710_CR24","unstructured":"Wu W, Zhuang L, Jiahong L (2022) Real-time end-to-end video text spotter with contrastive representation learning. European conference on computer vision(ECCV), pp 1452\u20131469"},{"key":"5710_CR25","doi-asserted-by":"crossref","unstructured":"Zhao Y, Wu W, Li Z, Li J, Wang W (2023) Flowtext: synthesizing realistic scene text video with optical flow estimation. 2023 IEEE international conference on multimedia and expo (ICME), pp 1517\u20131522","DOI":"10.1109\/ICME55011.2023.00262"},{"key":"5710_CR26","doi-asserted-by":"crossref","unstructured":"Wang W, Dai J, Chen Z, Huang Z, Li Z, Zhu X, Hu X, Lu T, Lu L, Li H, Wang X, Qiao Y (2023) Internimage: exploring large-scale vision foundation models with deformable convolutions. 2023 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 14408\u201314419","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"5710_CR27","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. Proceedings of the 31st international conference on neural information processing systems, pp 6000\u20136010"},{"key":"5710_CR28","unstructured":"Nicolas C, Francisco M, Sergey Z (2020) End-to-end object detection with transformers. European conference on computer vision, pp 213\u2013229"},{"key":"5710_CR29","doi-asserted-by":"crossref","unstructured":"Zheng S, Lu J, Zhao H (2021) Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 6877\u20136886","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"5710_CR30","doi-asserted-by":"crossref","unstructured":"Zhao H, Jiang L, Jia J, Torr P, Koltun V (2021) Point transformer. IEEE\/CVF international conference on computer vision (ICCV), pp 16239\u201316248","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"5710_CR31","doi-asserted-by":"crossref","unstructured":"Wang N, Zhou W, Wang J, Li H (2021) Transformer meets tracker: exploiting temporal context for robust visual tracking. IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 1571\u20131580","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"5710_CR32","doi-asserted-by":"crossref","unstructured":"Wang Y, Xu Z, Xia H (2021) End-to-end video instance segmentation with transformers. IEEE\/CVF conference on computer vision and pattern recognition, pp 8741\u20138750","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"5710_CR33","doi-asserted-by":"crossref","unstructured":"Zeng F, Dong B, Zhang Y, Wang T, Zhang X, Wei Y (2022) Motr: end-to-end multiple-object tracking with transformer. European conference on computer vision (ECCV)","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"5710_CR34","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. IEEE conference on computer vision and pattern recognition (CVPR), pp 936\u2013944"},{"key":"5710_CR35","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"5710_CR36","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask r-cnn. 2017 IEEE international conference on computer vision (ICCV), pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.322"},{"key":"5710_CR37","unstructured":"O\u00a0Pinheiro PO, Collobert R, Dollar P (2015) Learning to segment object candidates. Advances in Neural Information Processing Systems, vol 28"},{"key":"5710_CR38","first-page":"75","volume":"2016","author":"PO Pinheiro","year":"2016","unstructured":"Pinheiro PO, Lin T-Y, Collobert R, Doll\u00e1r P (2016) Learning to refine object segments. Comput Vis - ECCV 2016:75\u201391","journal-title":"Comput Vis - ECCV"},{"issue":"12","key":"5710_CR39","doi-asserted-by":"crossref","first-page":"1997","DOI":"10.1049\/rsn2.12312","volume":"16","author":"Q Xiang","year":"2022","unstructured":"Xiang Q, Wang X, Lai J, Song Y, Li R, Lei L (2022) Multi-scale group-fusion convolutional neural network for high-resolution range profile target recognition. IET Radar Sonar Navig 16(12):1997\u20132016","journal-title":"IET Radar Sonar Navig"},{"key":"5710_CR40","unstructured":"Olaf R, Philipp F, Thomas B (2015) U-Net: convolutional networks for biomedical image segmentation. International conference on medical image computing and computer-assisted intervention, pp 234\u2013241"},{"issue":"8","key":"5710_CR41","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"H Sepp","year":"1997","unstructured":"Sepp H, Jurgen S (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"5710_CR42","doi-asserted-by":"crossref","unstructured":"Karatzas D, Shafait F, Uchida S et al (2013) Icdar 2013 robust reading competition. Document analysis and recognition - ICDAR 2013","DOI":"10.1109\/ICDAR.2013.221"},{"key":"5710_CR43","doi-asserted-by":"crossref","unstructured":"Karatzas D, Gomez-Bigorda L, Nicolaou A et al (2015) Icdar 2015 competition on robust reading. Document analysis and recognition - ICDAR 2015, pp 1156\u20131160","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"5710_CR44","doi-asserted-by":"crossref","unstructured":"Minetto R, Thome N, Cord M, Leite NJ, Stolfi J (2011) Snoopertrack: text detection and tracking for outdoor videos. IEEE international conference on image processing, pp 505\u2013508","DOI":"10.1109\/ICIP.2011.6116563"},{"key":"5710_CR45","first-page":"405","volume":"2023","author":"W Wu","year":"2023","unstructured":"Wu W, Zhao Y, Li Z, Li J, Shou MZ, Pal U, Karatzas D, Bai X (2023) Icdar 2023 competition on video text reading for dense and small text. Doc Anal Recognit - ICDAR 2023:405\u2013419","journal-title":"Doc Anal Recognit - ICDAR"},{"key":"5710_CR46","doi-asserted-by":"crossref","unstructured":"Bernardin K, Stiefelhagen R (2008) Evaluating multiple object tracking performance: The clear MOT metrics. EURASIP J Image Video Process","DOI":"10.1155\/2008\/246309"},{"key":"5710_CR47","unstructured":"Wu W, Cai Y, Zhang D (2021) A bilingual, openworld video text dataset and end-to-end video text spotter with transformer. Conference on neural information processing systems (NeurIPS)"},{"key":"5710_CR48","doi-asserted-by":"crossref","unstructured":"Epshtein B, Ofek E, Wexler Y (2010) Detecting text in natural scenes with stroke width transform. IEEE computer society conference on computer vision and pattern recognition, pp 2963\u20132970","DOI":"10.1109\/CVPR.2010.5540041"},{"issue":"3","key":"5710_CR49","doi-asserted-by":"crossref","first-page":"790","DOI":"10.1109\/TIP.2010.2068553","volume":"20","author":"X Zhao","year":"2010","unstructured":"Zhao X, Lin K-H, Fu Y, Hu Y, Liu Y, Huang TS (2010) Text from corners: a novel approach to detect text and caption in videos. IEEE Trans Image Process (TIP) 20(3):790\u2013799","journal-title":"IEEE Trans Image Process (TIP)"},{"key":"5710_CR50","unstructured":"Yin X-C, Yin X, Huang K, Hao H-W (2013) Robust text detection in natural scene images. IEEE Trans Pattern Anal Mach Intell (TPAMI) 36(5):970\u2013983"},{"issue":"15","key":"5710_CR51","first-page":"16625","volume":"76","author":"V Khare","year":"2017","unstructured":"Khare V, Shivakumara P, Paramesran R, Blumenstein M (2017) Arbitrarily-oriented multi-lingual text detection in video. MTA 76(15):16625\u201316655","journal-title":"MTA"},{"key":"5710_CR52","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/j.patcog.2017.03.018","volume":"68","author":"P Shivakumara","year":"2017","unstructured":"Shivakumara P, Wu L, Lu T, Tan CL, Blumenstein M, Anami BS (2017) Fractals based multi-oriented text detection system for recognition in mobile video images. Pattern Recognit 68:158\u2013174","journal-title":"Pattern Recognit"},{"key":"5710_CR53","doi-asserted-by":"crossref","unstructured":"Chen L, Su F (2022) Towards robust video text detection with spatio-temporal attention modeling and text cues fusion. IEEE international conference on multimedia and expo (ICME), pp 1\u20136","DOI":"10.1109\/ICME52920.2022.9859582"},{"key":"5710_CR54","doi-asserted-by":"crossref","unstructured":"Feng W, Yin F, Zhang XY, Liu CL (2021) Semantic-aware video text detection. IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 1695\u20131705","DOI":"10.1109\/CVPR46437.2021.00174"},{"key":"5710_CR55","unstructured":"Zuo Z-Y, Tian S, Pei W-y, Yin X-C (2015) Multi-strategy tracking based text detection in scene videos. 13th International conference on document analysis and recognition (ICDAR), pp 66\u201370"},{"key":"5710_CR56","doi-asserted-by":"crossref","first-page":"19419","DOI":"10.1109\/ACCESS.2018.2797181","volume":"6","author":"W-Y Pei","year":"2018","unstructured":"Pei W-Y, Yang C, Meng L-Y, Hou J-B, Tian S, Yin X-C (2018) Scene video text tracking with graph matching. IEEE Access 6:19419\u201319426","journal-title":"IEEE Access"},{"key":"5710_CR57","doi-asserted-by":"crossref","first-page":"107791","DOI":"10.1016\/j.patcog.2020.107791","volume":"113","author":"H Yu","year":"2021","unstructured":"Yu H, Zhang C (2021) End-to-end video text detection with online tracking. Pattern Recognit 113:107791","journal-title":"Pattern Recognit"},{"key":"5710_CR58","unstructured":"Li Z, Wu W, Shou MZ, Li J, Li S, Wang Z, Zhou H (2021) Contrastive learning of semantic and visual representations for text tracking"},{"issue":"6","key":"5710_CR59","doi-asserted-by":"crossref","first-page":"2752","DOI":"10.1109\/TIP.2016.2554321","volume":"25","author":"H Liu","year":"2016","unstructured":"Liu H (2016) Video text tracking for dense and small text based on pp-yoloe-r and sort algorithm. IEEE Trans Image Process 25(6):2752\u20132773","journal-title":"IEEE Trans Image Process"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05710-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-024-05710-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05710-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T21:25:44Z","timestamp":1732656344000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-024-05710-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,20]]},"references-count":59,"journal-issue":{"issue":"21","published-print":{"date-parts":[[2024,11]]}},"alternative-id":["5710"],"URL":"https:\/\/doi.org\/10.1007\/s10489-024-05710-9","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,20]]},"assertion":[{"value":"27 July 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there are no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}},{"value":"Ethical considerations and informed consent were prioritized throughout the data collection and usage process. All data used in this study were obtained in accordance with applicable laws, regulations, and ethical guidelines. The data did not necessitate addressing privacy issues. This study adheres to ethical principles and respects the rights and privacy of individuals involved in the data collection process.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and Informed Consent for the Data Used"}}]}}