{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:59:43Z","timestamp":1778083183252,"version":"3.51.4"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","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":["Mach Learn"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s10994-024-06676-y","type":"journal-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T11:24:01Z","timestamp":1737026641000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["SA-LfV: self-annotated labeling from videos for object detection"],"prefix":"10.1007","volume":"114","author":[{"given":"Arun Kumar","family":"Sivapuram","sequence":"first","affiliation":[]},{"given":"Prashanth","family":"Komuravelli","sequence":"additional","affiliation":[]},{"given":"Rama Krishna Sai","family":"Gorthi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,1,16]]},"reference":[{"key":"6676_CR1","doi-asserted-by":"crossref","unstructured":"Cubuk, E. D., Zoph, B., Mane, D., Vasudevan, V., & Le, Q. V. (2019). Autoaugment: Learning augmentation policies from data.","DOI":"10.1109\/CVPR.2019.00020"},{"key":"6676_CR2","doi-asserted-by":"crossref","unstructured":"Cubuk, E. D., Zoph, B., Shlens, J., & Le, Q. V. (2020). Randaugment: Practical automated data augmentation with a reduced search space. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops. pp. 702\u2013703.","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"6676_CR3","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jiang, C., Wang, L., & Wu, G. (2022). 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.","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"6676_CR4","doi-asserted-by":"publisher","unstructured":"Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), (Vol. 1, pp. 886\u2013893). https:\/\/doi.org\/10.1109\/CVPR.2005.177.","DOI":"10.1109\/CVPR.2005.177"},{"key":"6676_CR5","doi-asserted-by":"crossref","unstructured":"Dasari, M. M., & Gorthi, R. K. S. S. (2020). Iou\u2013siamtrack: Iou guided siamese network for visual object tracking. In 2020 IEEE International Conference on Image Processing (ICIP) (pp. 2061\u20132065). IEEE.","DOI":"10.1109\/ICIP40778.2020.9191188"},{"key":"6676_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition (pp. 248\u2013255). Ieee.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"6676_CR7","doi-asserted-by":"crossref","unstructured":"Fan, H., Lin, L., Yang, F., Chu, P., Deng, G., Yu, S., Bai, H., Xu, Y., Liao, C., & Ling, H. (2019). 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).","DOI":"10.1109\/CVPR.2019.00552"},{"key":"6676_CR8","doi-asserted-by":"publisher","unstructured":"Felzenszwalb, P., McAllester, D., & Ramanan, D. (2008). A discriminatively trained, multiscale, deformable part model. In 2008 IEEE Conference on Computer Vision and Pattern Recognition (pp.\u00a01\u20138). https:\/\/doi.org\/10.1109\/CVPR.2008.4587597.","DOI":"10.1109\/CVPR.2008.4587597"},{"key":"6676_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation.","DOI":"10.1109\/CVPR.2014.81"},{"key":"6676_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"6676_CR11","doi-asserted-by":"crossref","unstructured":"Hern\u00e1ndez-Garc\u00eda, A., & K\u00f6nig, P. (2018). Further advantages of data augmentation on convolutional neural networks. In International Conference on Artificial Neural Networks (pp. 95\u2013103). Springer.","DOI":"10.1007\/978-3-030-01418-6_10"},{"key":"6676_CR12","first-page":"1","volume":"24","author":"D Hoiem","year":"2009","unstructured":"Hoiem, D., Divvala, S. K., & Hays, J. H. (2009). Pascal voc 2008 challenge. World Literature Today, 24, 1\u20134.","journal-title":"World Literature Today"},{"issue":"3","key":"6676_CR13","doi-asserted-by":"publisher","first-page":"1602","DOI":"10.11591\/ijeecs.v23.i3.pp1602-1610","volume":"23","author":"MZ Hossain","year":"2021","unstructured":"Hossain, M. Z., Islam, M. J., Miah, M. W. R., Rony, J. H., & Begum, M. (2021). Develop a dynamic dbscan algorithm for solving initial parameter selection problem of the dbscan algorithm. Indonesian Journal of Electrical Engineering and Computer Science, 23(3), 1602\u20131610.","journal-title":"Indonesian Journal of Electrical Engineering and Computer Science"},{"key":"6676_CR14","doi-asserted-by":"crossref","unstructured":"Hu, S., Liu, C. H., Dutta, J., Chang, M. C., Lyu, S., & Ramakrishnan, N. (2022). Pseudoprop: Robust pseudo-label generation for semi-supervised object detection in autonomous driving systems. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp. 4390\u20134398.","DOI":"10.1109\/CVPRW56347.2022.00485"},{"issue":"5","key":"6676_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. (2019). Got-10k: A large high-diversity benchmark for generic object tracking in the wild. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(5), 1562\u20131577.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"6676_CR16","unstructured":"Jeong, J., Lee, S., Kim, J., & Kwak, N. (2019). Consistency-based semi-supervised learning for object detection. Advances in Neural Information Processing Systems, 32."},{"key":"6676_CR17","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25."},{"key":"6676_CR18","doi-asserted-by":"crossref","unstructured":"Kumar, A., Pal, A., Mopuri, K. R., & Gorthi, R. K. (2022). Adv-cut paste: Semantic adversarial class specific data augmentation technique for object detection. In 2022 26th International Conference on Pattern Recognition (ICPR) (pp. 3632\u20133638). IEEE.","DOI":"10.1109\/ICPR56361.2022.9956409"},{"key":"6676_CR19","doi-asserted-by":"publisher","unstructured":"Li, H., Wu, Z., Shrivastava, A., & Davis, L. S. (2022). Rethinking pseudo labels for semi-supervised object detection. Proceedings of the AAAI Conference on Artificial Intelligence, (Vol. 36(2), pp. 1314\u20131322). https:\/\/doi.org\/10.1609\/aaai.v36i2.20019, https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/20019.","DOI":"10.1609\/aaai.v36i2.20019"},{"key":"6676_CR20","doi-asserted-by":"crossref","unstructured":"Li, B., Wu, W., Wang, Q., Zhang, F., Xing, J., & Yan, J. (2019). Siamrpn++: Evolution of siamese visual tracking with very deep networks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4282\u20134291.","DOI":"10.1109\/CVPR.2019.00441"},{"key":"6676_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In: European conference on computer vision (pp. 740\u2013755). Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"6676_CR22","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., & Berg, A. C. (2016). Ssd: Single shot multibox detector. In European conference on computer vision (pp. 21\u201337). Springer.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"6676_CR23","doi-asserted-by":"publisher","unstructured":"Miko\u0142ajczyk, A., & Grochowski, M. (2018). Data augmentation for improving deep learning in image classification problem. In: 2018 International Interdisciplinary PhD Workshop (IIPhDW) pp. 117\u2013122. https:\/\/doi.org\/10.1109\/IIPHDW.2018.8388338.","DOI":"10.1109\/IIPHDW.2018.8388338"},{"issue":"1","key":"6676_CR24","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1007\/s42979-022-01408-2","volume":"4","author":"K Prashanth","year":"2022","unstructured":"Prashanth, K., Kalra, L., Kalidas, Y., Kumar, J. R. B., Ayyagari, S. P. K., & Deep, A. (2022). An algorithm for semantic vectorization of video scenes: applications to retrieval and anomaly detection. SN Computer Science, 4(1), 24.","journal-title":"SN Computer Science"},{"key":"6676_CR25","unstructured":"Qin, H., Ma, X., Zheng, X., Li, X., Zhang, Y., Liu, S., Luo, J., Liu, X., & Magno, M. (2024). Accurate lora-finetuning quantization of llms via information retention. arXiv preprint arXiv:2402.05445."},{"key":"6676_CR26","unstructured":"Qin, H., Zhang, Y., Ding, Y., Liu, X., Danelljan, M., Yu, F., et\u00a0al. (2024). Quantsr: accurate low-bit quantization for efficient image super-resolution. Advances in Neural Information Processing Systems 36."},{"key":"6676_CR27","unstructured":"Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement."},{"key":"6676_CR28","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems, 28, 91\u201399.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6676_CR29","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556."},{"key":"6676_CR30","unstructured":"Sohn, K., Zhang, Z., Li, C. L., Zhang, H., Lee, C. Y., Pfister, T. (2020). A simple semi-supervised learning framework for object detection. arXiv preprint arXiv:2005.04757."},{"key":"6676_CR31","doi-asserted-by":"publisher","unstructured":"Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 (Vol.\u00a01, pp.\u00a0I\u2013I). https:\/\/doi.org\/10.1109\/CVPR.2001.990517.","DOI":"10.1109\/CVPR.2001.990517"},{"key":"6676_CR32","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Hu, H., Wang, J., Wang, L., Wei, F., Bai, X., & Liu, Z. (2021). End-to-end semi-supervised object detection with soft teacher. In Proceedings of the IEEE\/CVF International Conference on Computer Vision pp. 3060\u20133069.","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"6676_CR33","doi-asserted-by":"crossref","unstructured":"Zoph, B., Cubuk, E. D., Ghiasi, G., Lin, T. Y., Shlens, J., & Le, Q. V. (2020). Learning data augmentation strategies for object detection. In: European Conference on Computer Vision (pp. 566\u2013583). Springer.","DOI":"10.1007\/978-3-030-58583-9_34"},{"key":"6676_CR34","doi-asserted-by":"crossref","unstructured":"Zou, Z., Chen, K., Shi, Z., Guo, Y., & Ye, J. (2023). Object detection in 20 years: A survey. In Proceedings of the IEEE.","DOI":"10.1109\/JPROC.2023.3238524"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-024-06676-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-024-06676-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-024-06676-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T01:02:22Z","timestamp":1768525342000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-024-06676-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["6676"],"URL":"https:\/\/doi.org\/10.1007\/s10994-024-06676-y","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"12 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 August 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 December 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 January 2025","order":4,"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 no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}],"article-number":"21"}}