{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T04:22:58Z","timestamp":1787372578934,"version":"build-2736575974"},"reference-count":109,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62431004"],"award-info":[{"award-number":["62431004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276046"],"award-info":[{"award-number":["62276046"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1007\/s11263-026-02919-8","type":"journal-article","created":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T07:20:50Z","timestamp":1784704850000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Power Battery Detection"],"prefix":"10.1007","volume":"134","author":[{"given":"Xiaoqi","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peiqian","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenyang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zonglei","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9241-1688","authenticated-orcid":false,"given":"Lihe","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanqi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaming","family":"Zuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youwei","family":"Pang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinsong","family":"Ouyang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weisi","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georges","family":"El Fakhri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,22]]},"reference":[{"key":"2919_CR1","doi-asserted-by":"crossref","unstructured":"Babu\u00a0Sam, D., Surya, S., & Venkatesh\u00a0Babu, R. (2017). Switching convolutional neural network for crowd counting. In Conference on Computer Vision and Pattern Recognition, 5744\u20135752.","DOI":"10.1109\/CVPR.2017.429"},{"key":"2919_CR2","doi-asserted-by":"crossref","unstructured":"Butoi, V.\u00a0I., Ortiz, J.\u00a0J.\u00a0G., Ma, T., Sabuncu, M.\u00a0R., Guttag, J., & Dalca. A.\u00a0V. (2023). Universeg: Universal medical image segmentation. In International Conference on Computer Vision, pages 21438\u201321451.","DOI":"10.1109\/ICCV51070.2023.01960"},{"key":"2919_CR3","doi-asserted-by":"crossref","unstructured":"Cao, H., Wang, Y., Chen, J., Jiang, D., Zhang, X., Tian, Q., & Wang, M. (2022). Swin-unet: Unet-like pure transformer for medical image segmentation. In European Conference on Computer Vision 205\u2013218.","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"2919_CR4","unstructured":"Carion, N., Gustafson, L., Hu, Y.-T., Debnath, S., Hu, R., Suris, D., Ryali, C., Alwala, K.\u00a0V., Khedr, H., Huang, A., & Lei, J. (2025). Sam 3: Segment anything with concepts. arXiv preprint arXiv:2511.16719."},{"key":"2919_CR5","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020). End-to-end object detection with transformers. In European Conference on Computer Vision,, 213\u2013229.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2919_CR6","doi-asserted-by":"crossref","unstructured":"Carrara, A., Nousias, S., & Borrmann, A. (2024). Vectorgraphnet: Graph attention networks for accurate segmentation of complex technical drawings arXiv preprint arXiv:2410.01336.","DOI":"10.1061\/JCCEE5.CPENG-6508"},{"key":"2919_CR7","doi-asserted-by":"crossref","unstructured":"Caruana, R. (1993). Multitask learning: A knowledge-based source of inductive bias. In International Conference on Machine Learning, 41\u201348.","DOI":"10.1016\/B978-1-55860-307-3.50012-5"},{"key":"2919_CR8","unstructured":"Chen, D., & Zhang, G. (2005). A new sub-pixel detector for x-corners in camera calibration targets. International Conference in Central Europe on Computer Graphics and Visualization."},{"key":"2919_CR9","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","unstructured":"Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2017). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40, 834\u2013848.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2919_CR10","doi-asserted-by":"crossref","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. In European Conference on Computer Vision, 801\u2013818.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"2919_CR11","doi-asserted-by":"crossref","unstructured":"Chiu, M. T., Zhang, X., Wei, Z., Zhou, Y., Shechtman, E., Barnes, C., Lin, Z., Kainz, F., Amirghodsi, S., & Shi, H. (2023). Automatic high resolution wire segmentation and removal. In Conference on Computer Vision and Pattern Recognition, 2183\u20132192.","DOI":"10.1109\/CVPR52729.2023.00217"},{"key":"2919_CR12","unstructured":"Dai, J., Li, Y., He, K., & Sun, J. (2016). R-fcn: Object detection via region-based fully convolutional networks. In Conference on Neural Information Processing Systems."},{"key":"2919_CR13","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., & Gelly, S. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. International Conference on Learning Representations."},{"key":"2919_CR14","doi-asserted-by":"crossref","unstructured":"Duong, L., Cohn, T., Bird, S., & Cook, P. (2015). Low resource dependency parsing: Cross-lingual parameter sharing in a neural network parser. In ACL, 845\u2013850.","DOI":"10.3115\/v1\/P15-2139"},{"key":"2919_CR15","doi-asserted-by":"crossref","unstructured":"Fan, D.-P., Ji, G.-P., Zhou, T., Chen, G., Fu, H., Shen, J., & Shao, L. (2020). Pranet: Parallel reverse attention network for polyp segmentation. In Medical Image Computing and Computer Assisted Intervention, 263\u2013273.","DOI":"10.1007\/978-3-030-59725-2_26"},{"issue":"8","key":"2919_CR16","doi-asserted-by":"publisher","first-page":"2626","DOI":"10.1109\/TMI.2020.2996645","volume":"39","author":"D-P Fan","year":"2020","unstructured":"Fan, D.-P., Zhou, T., Ji, G.-P., Zhou, Y., Chen, G., Fu, H., Shen, J., & Shao, L. (2020). Inf-net: Automatic covid-19 lung infection segmentation from ct images. IEEE transactions on medical imaging, 39(8), 2626\u20132637.","journal-title":"IEEE transactions on medical imaging"},{"key":"2919_CR17","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Gu, X., Cui, Y., & Lin, T.-Y.(2022). Scaling open-vocabulary image segmentation with image-level labels. In European Conference on Computer Vision, 40\u2013557. Springer.","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"2919_CR18","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015) Fast r-cnn. In International Conference on Computer Vision, 1440\u20131448.","DOI":"10.1109\/ICCV.2015.169"},{"key":"2919_CR19","doi-asserted-by":"crossref","unstructured":"Go, H., Park, B., Jang, J., Kim, J.-Y., Kwon, S., & Kim, C. (2025). Splatflow: Multi-view rectified flow model for 3d gaussian splatting synthesis. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 21524\u201321536.","DOI":"10.1109\/CVPR52734.2025.02005"},{"key":"2919_CR20","unstructured":"Gu, A., & Dao, T. (2024). Mamba: Linear-time sequence modeling with selective state spaces. COLM"},{"key":"2919_CR21","unstructured":"Gu, A., Goel, K., & R\u00e9, C. (2022). Efficiently modeling long sequences with structured state spaces. International Conference on Learning Representations."},{"key":"2919_CR22","first-page":"572","volume":"34","author":"A Gu","year":"2021","unstructured":"Gu, A., Johnson, I., Goel, K., Saab, K., Dao, T., Rudra, A., & R\u00e9, C. (2021). Combining recurrent, convolutional, and continuous-time models with linear state space layers. Advances in Neural Information Processing Systems, 34, 572\u2013585.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2919_CR23","first-page":"10","volume":"50","author":"C Harris","year":"1988","unstructured":"Harris, C., Stephens, M., et al. (1988). A combined corner and edge detector. In Alvey vision conference, 50, 10\u20135244.","journal-title":"In Alvey vision conference"},{"key":"2919_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"4","key":"2919_CR25","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1016\/j.pneurobio.2007.09.001","volume":"84","author":"J Hegd\u00e9","year":"2008","unstructured":"Hegd\u00e9, J. (2008). Time course of visual perception: coarse-to-fine processing and beyond. Progress in neurobiology, 84(4), 405\u2013439.","journal-title":"Progress in neurobiology"},{"key":"2919_CR26","doi-asserted-by":"crossref","unstructured":"Hu, X., Fu, C.-W., Zhu, L., Qin, J., & Heng, P.-A. (2019). Direction-aware spatial context features for shadow detection and removal. 42(11), 2795\u20132808.","DOI":"10.1109\/TPAMI.2019.2919616"},{"key":"2919_CR27","unstructured":"International Energy Agency. Global ev outlook 2024, 2024. Accessed: 2025-06-11."},{"issue":"3","key":"2919_CR28","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","volume":"7","author":"J Johnson","year":"2019","unstructured":"Johnson, J., Douze, M., & J\u00e9gou, H. (2019). Billion-scale similarity search with gpus. IEEE Transactions on Big Data, 7(3), 535\u2013547.","journal-title":"IEEE Transactions on Big Data"},{"key":"2919_CR29","unstructured":"Kang, D., & Chan, A. (2018). Crowd counting by adaptively fusing predictions from an image pyramid arXiv preprint arXiv:1805.06115."},{"key":"2919_CR30","doi-asserted-by":"crossref","unstructured":"Ke, L., Ye, M., Danelljan, M., Liu, Y., Tai, Y.-W., Tang, C.-K., & Yu, F. (2024). Segment anything in high quality. In Advances in Neural Information Processing Systems,.","DOI":"10.52202\/075280-1303"},{"issue":"4","key":"2919_CR31","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3592433","volume":"42","author":"B Kerbl","year":"2023","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., & Drettakis, G. (2023). 3d gaussian splatting for real-time radiance field rendering. ACM Trans. Graph., 42(4), 139\u20131.","journal-title":"ACM Trans. Graph."},{"issue":"6","key":"2919_CR32","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1177\/02783649231213117","volume":"43","author":"J Kim","year":"2024","unstructured":"Kim, J., Jeon, M.-H., Jung, S., Yang, W., Jung, M., Shin, J., & Kim, A. (2024). Transpose: Large-scale multispectral dataset for transparent object. The International Journal of Robotics Research, 43(6), 731\u2013738.","journal-title":"The International Journal of Robotics Research"},{"key":"2919_CR33","unstructured":"Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. International Conference on Learning Representations."},{"key":"2919_CR34","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., Lo, W.-Y., et al. (2023). Segment anything. In International Conference on Computer Vision, 4015\u20134026.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2919_CR35","doi-asserted-by":"crossref","unstructured":"Lee, C., Park, S., Song, H., Ryu, J., Kim, S., Kim, H., Pereira, S., & Yoo, D. (2022). Interactive multi-class tiny-object detection. In Conference on Computer Vision and Pattern Recognition, 4136\u201314145.","DOI":"10.1109\/CVPR52688.2022.01374"},{"issue":"4","key":"2919_CR36","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1007\/s11263-022-01734-1","volume":"131","author":"J Li","year":"2023","unstructured":"Li, J., Ji, W., Zhang, M., Piao, Y., Lu, H., & Cheng, L. (2023). Delving into calibrated depth for accurate rgb-d salient object detection. International Journal of Computer Vision, 131(4), 855\u2013876.","journal-title":"International Journal of Computer Vision"},{"key":"2919_CR37","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. In Conference on Computer Vision and Pattern Recognition, 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"2919_CR38","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Doll\u00e1r, P. (2017). Focal loss for dense object detection. In International Conference on Computer Vision, 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"2919_CR39","unstructured":"Liu, L., Lin, K., Huang, S., Li, Z., Li, C., Cao, Y., & Zhou, Q.(2022). Instance segmentation for chinese character stroke extraction, datasets and benchmarks. arXiv preprint arXiv:2210.13826."},{"key":"2919_CR40","unstructured":"Liu, M., Dan, J., Lu, Z., Yu, Y., Li, Y., & Li, X. (2024). Cm-unet: Hybrid cnn-mamba unet for remote sensing image semantic segmentation. arXiv preprint arXiv:2405.10530."},{"key":"2919_CR41","doi-asserted-by":"crossref","unstructured":"Liu, W., Shen, X., Pun, C.-M., & Cun, X. (2023). Explicit visual prompting for low-level structure segmentations. In Conference on Computer Vision and Pattern Recognition,, 19434\u201319445.","DOI":"10.1109\/CVPR52729.2023.01862"},{"key":"2919_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.104924","volume":"143","author":"X Liu","year":"2024","unstructured":"Liu, X., Qi, L., Song, Y., & Wen, Q. (2024). Depth awakens: A depth-perceptual attention fusion network for rgb-d camouflaged object detection. Image and Vision Computing, 143, Article 104924.","journal-title":"Image and Vision Computing"},{"key":"2919_CR43","first-page":"03031","volume":"37","author":"Y Liu","year":"2024","unstructured":"Liu, Y., Tian, Y., Zhao, Y., Yu, H., Xie, L., Wang, Y., Ye, Q., Jiao, J., & Liu, Y. (2024). Vmamba: Visual state space model. Advances in neural information processing systemsNeurIPS, 37, 03031\u2013103063.","journal-title":"Advances in neural information processing systemsNeurIPS"},{"key":"2919_CR44","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In Conference on Computer Vision and Pattern Recognition, 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2919_CR45","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., & Xie, S. (2022). A convnet for the 2020s. In Conference on Computer Vision and Pattern Recognition, 11976\u201311986.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"2919_CR46","doi-asserted-by":"crossref","unstructured":"Luo, Z., Liu, N., Zhao, W., Yang, X., Zhang, D., Fan, D.-P., Khan, F., & Han, J. (2024). Vscode: General visual salient and camouflaged object detection with 2d prompt learning. In Conference on Computer Vision and Pattern Recognition, 17169\u201317180.","DOI":"10.1109\/CVPR52733.2024.01625"},{"key":"2919_CR47","unstructured":"Ma, J., Li, F., & Wang, B. (2024). U-mamba: Enhancing long-range dependency for biomedical image segmentation arXiv preprint arXiv:2401.04722."},{"key":"2919_CR48","doi-asserted-by":"crossref","unstructured":"Ma, Z., Wei, X., Hong, X., & Gong, Y. (2019). Bayesian loss for crowd count estimation with point supervision. In International Conference on Computer Vision, 6142\u20136151.","DOI":"10.1109\/ICCV.2019.00624"},{"key":"2919_CR49","unstructured":"Magazine, E.\u00a0C. (2024). Record year for ev sales: 17.1 million sold globally in 2024. Accessed: 2025-06-11."},{"key":"2919_CR50","doi-asserted-by":"crossref","unstructured":"Pang, Y., Zhao, X., Xiang, T.-Z., Zhang, L., & Lu, H. (2022). Zoom in and out: A mixed-scale triplet network for camouflaged object detection. In Conference on Computer Vision and Pattern Recognition, 2160\u20132170.","DOI":"10.1109\/CVPR52688.2022.00220"},{"issue":"12","key":"2919_CR51","doi-asserted-by":"publisher","first-page":"9205","DOI":"10.1109\/TPAMI.2024.3417329","volume":"46","author":"Y Pang","year":"2024","unstructured":"Pang, Y., Zhao, X., Xiang, T.-Z., Zhang, L., & Lu, H. (2024). Zoomnext: A unified collaborative pyramid network for camouflaged object detection. IEEE transactions on pattern analysis and machine intelligence, 46(12), 9205\u20139220.","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"2919_CR52","doi-asserted-by":"crossref","unstructured":"Pang, Y., Zhao, X., Zhang, L., & Lu, H. (2020). Multi-scale interactive network for salient object detection. In Conference on Computer Vision and Pattern Recognition, 9413\u20139422.","DOI":"10.1109\/CVPR42600.2020.00943"},{"key":"2919_CR53","doi-asserted-by":"publisher","first-page":"892","DOI":"10.1109\/TIP.2023.3234702","volume":"32","author":"Y Pang","year":"2023","unstructured":"Pang, Y., Zhao, X., Zhang, L., & Lu, H. (2023). Caver: Cross-modal view-mixed transformer for bi-modal salient object detection. IEEE Transactions on Image Processing, 32, 892\u2013904.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2919_CR54","doi-asserted-by":"crossref","unstructured":"Pang, Y., Zhao, X., Zuo, J., Zhang, L., & Lu, H. (2024). Open-vocabulary camouflaged object segmentation. In European Conference on Computer Vision, 476\u2013495.","DOI":"10.1007\/978-3-031-72970-6_27"},{"key":"2919_CR55","unstructured":"Qian, Y., Zhang, L., Hong, X., Donovan, C. R., Arandjelovic, O., Fife, U., & Harbin, P. (2022). Segmentation assisted u-shaped multi-scale transformer for crowd counting"},{"key":"2919_CR56","unstructured":"Radford, A., Kim, J.\u00a0W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., & Krueger, G. (2021). Learning transferable visual models from natural language supervision. In In International conference on machine learning, 8748\u20138763."},{"key":"2919_CR57","doi-asserted-by":"crossref","unstructured":"Ranjan, V., Le, H., & Hoai, M. (2018). Iterative crowd counting. In European Conference on Computer Vision, 270\u2013285.","DOI":"10.1007\/978-3-030-01234-2_17"},{"key":"2919_CR58","unstructured":"Ravi, N., Gabeur, V., Hu, Y.-T., Hu, R., Ryali, C., Ma, T., Khedr, H., R\u00e4dle, R., Rolland, C., Gustafson, L., & Mintun, E. (2025). Sam 2: Segment anything in images and videos. In International Conference on Learning Representations."},{"key":"2919_CR59","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems,."},{"key":"2919_CR60","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In Conference on Computer Vision and Pattern Recognition, 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2919_CR61","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation.  In International Conference on Medical image computing and computer-assisted intervention, 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2919_CR62","unstructured":"Ryali, C., Hu, Y.-T., Bolya, D., Wei, C., Fan, H., Huang, P.-Y., Aggarwal, V., Chowdhury, A., Poursaeed, O., Hoffman, J., & Malik, J. (2023). Hiera: A hierarchical vision transformer without the bells-and-whistles. In International conference on machine learning29441\u201329454."},{"key":"2919_CR63","unstructured":"Sam, D.\u00a0B., & Babu, R.\u00a0V. (2018). Top-down feedback for crowd counting convolutional neural network. In Proceedings of the AAAI conference on artificial intelligence, number\u00a01."},{"key":"2919_CR64","doi-asserted-by":"crossref","unstructured":"Shi, J. et\u00a0al. (1994). Good features to track. In Conference on Computer Vision and Pattern Recognition, 593\u2013600.","DOI":"10.1109\/CVPR.1994.323794"},{"key":"2919_CR65","doi-asserted-by":"publisher","first-page":"6896","DOI":"10.1609\/aaai.v39i7.32740","volume":"39","author":"Z Shi","year":"2025","unstructured":"Shi, Z., Hu, J., Ren, J., Ye, H., Yuan, X., Ouyang, Y., He, J., Ji, B., & Guo, J. (2025). Hs-fpn: High frequency and spatial perception fpn for tiny object detection. In Proceedings of the AAAI conference on artificial intelligence, 39, 6896\u20136904.","journal-title":"In Proceedings of the AAAI conference on artificial intelligence"},{"key":"2919_CR66","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition arXiv preprint arXiv:1409.1556."},{"key":"2919_CR67","doi-asserted-by":"crossref","unstructured":"Sindagi, V. A., & Patel, V. M. (2017). Generating high-quality crowd density maps using contextual pyramid cnns. In International Conference on Computer Vision, 1861\u20131870.","DOI":"10.1109\/ICCV.2017.206"},{"key":"2919_CR68","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., & Schmid, C. (2021). Segmenter: Transformer for semantic segmentation. In International Conference on Computer Vision,7262\u20137272.","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"2919_CR69","doi-asserted-by":"crossref","unstructured":"Sun, G., An, Z., Liu, Y., Liu, C., Sakaridis, C., Fan, D.-P., & Van Gool, L. (2023). Indiscernible object counting in underwater scenes. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 13791\u201313801.","DOI":"10.1109\/CVPR52729.2023.01325"},{"key":"2919_CR70","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., & He, T. (2019). Fcos: Fully convolutional one-stage object detection. In International Conference on Computer Vision, 9627\u20139636.","DOI":"10.1109\/ICCV.2019.00972"},{"key":"2919_CR71","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. In Advances in neural information processing systems, 5998\u20136008."},{"key":"2919_CR72","doi-asserted-by":"crossref","unstructured":"Wan, J., & Chan, A. (2019). Adaptive density map generation for crowd counting. In International Conference on Computer Vision, 1130\u20131139.","DOI":"10.1109\/ICCV.2019.00122"},{"key":"2919_CR73","doi-asserted-by":"crossref","unstructured":"Wan, Z., Zhang, P., Wang, Y., Yong, S., Stepputtis, S., Sycara, K., & Xie. Y. (2025). Sigma: Siamese mamba network for multi-modal semantic segmentation. 1734\u20131744.","DOI":"10.1109\/WACV61041.2025.00176"},{"key":"2919_CR74","doi-asserted-by":"publisher","first-page":"107984","DOI":"10.52202\/079017-3429","volume":"37","author":"A Wang","year":"2024","unstructured":"Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., et al. (2024). Yolov10: Real-time end-to-end object detection. Advances in neural information processing systems, 37, 107984\u2013108011.","journal-title":"Advances in neural information processing systems"},{"key":"2919_CR75","unstructured":"Wang, B., Liu, H., Samaras, D., & Nguyen, M. H. (2020). Distribution matching for crowd counting. In Advances in neural information processing systems,, 1595\u20131607."},{"key":"2919_CR76","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., & Novotny, D. (2025). Vggt: Visual geometry grounded transformer. In Conference on Computer Vision and Pattern Recognition, 5294\u20135306.","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"2919_CR77","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, X., Cao, Y., Wang, W., Shen, C., & Huang, T. (2023). Seggpt: Towards segmenting everything in context. In International Conference on Computer Vision, 1130\u20131140.","DOI":"10.1109\/ICCV51070.2023.00110"},{"issue":"10","key":"2919_CR78","doi-asserted-by":"publisher","first-page":"2006","DOI":"10.1364\/JOSAA.4.002006","volume":"4","author":"R Watt","year":"1987","unstructured":"Watt, R. (1987). Scanning from coarse to fine spatial scales in the human visual system after the onset of a stimulus. Journal of the Optical Society of America A, 4(10), 2006\u20132021.","journal-title":"Journal of the Optical Society of America A"},{"key":"2919_CR79","doi-asserted-by":"crossref","unstructured":"Wei, H., Zhao, X., Lv, L., Zhang, L., Sun, W., & Lu, H. (2023). Growth simulation network for polyp segmentation 3\u201315.","DOI":"10.1007\/978-981-99-8558-6_1"},{"key":"2919_CR80","doi-asserted-by":"crossref","unstructured":"Wei, J., Wang, S., & Huang, Q. (2020). F$$^3$$net: Fusion, feedback and focus for salient object detection. In Proceedings of the AAAI conference on artificial intelligence, 12321\u201312328.","DOI":"10.1609\/aaai.v34i07.6916"},{"key":"2919_CR81","doi-asserted-by":"crossref","unstructured":"Wei, X., Wang, H., Ye, S., Luo,R., Zhang, Y., Gu, L., Dai, J., Qiao, Y., Wang, W., & Zhang. H. (2025). Point or line? using line-based representation for panoptic symbol spotting in cad drawings. arXiv preprint arXiv:2505.23395.","DOI":"10.52202\/085713-1668"},{"key":"2919_CR82","doi-asserted-by":"crossref","unstructured":"Xie, E., Wang, W., Wang, W., Sun, P., Xu, H., Liang, D., & Luo, P. (2021). Segmenting transparent objects in the wild with transformer. In International Joint Conference on Artificial Intelligence, 1194\u20131200.","DOI":"10.24963\/ijcai.2021\/165"},{"key":"2919_CR83","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J. M., & Luo, P. (2021). Segformer: Simple and efficient design for semantic segmentation with transformers. In Advances in neural information processing systems, 12077\u201312090."},{"key":"2919_CR84","doi-asserted-by":"crossref","unstructured":"Xing, Z., Ye, T., Yang, Y., Liu, G., & Zhu, L. (2024). Segmamba: Long-range sequential modeling mamba for 3d medical image segmentation. In IEEE Transactions on Medical Imaging, 578\u2013588.","DOI":"10.1007\/978-3-031-72111-3_54"},{"key":"2919_CR85","doi-asserted-by":"crossref","unstructured":"Xiong, F., Shi, X., & Yeung, D.-Y. (2017). Spatiotemporal modeling for crowd counting in videos. In International Conference on Computer Vision, 5151\u20135159.","DOI":"10.1109\/ICCV.2017.551"},{"issue":"18","key":"2919_CR86","doi-asserted-by":"publisher","first-page":"4636","DOI":"10.3390\/en13184636","volume":"13","author":"J Xu","year":"2020","unstructured":"Xu, J., Ma, J., Zhao, X., Chen, H., Xu, B., & Wu, X. (2020). Detection technology for battery safety in electric vehicles: A review. Energies, 13(18), 4636.","journal-title":"Energies"},{"key":"2919_CR87","unstructured":"Yang, C., Zhuang, K., Chen, M., Ma, H., Han, X., Han,T., Guo,C., Han, H., Zhao, B., & Wang, Q. (2023). Traffic sign interpretation in real road scene. arXiv preprint arXiv:2311.10793."},{"key":"2919_CR88","doi-asserted-by":"crossref","unstructured":"Yang, M., Yu, K., Zhang, C., Li, Z., & Yang, K. (2018). Denseaspp for semantic segmentation in street scenes. In Conference on Computer Vision and Pattern Recognition, 3684\u20133692.","DOI":"10.1109\/CVPR.2018.00388"},{"key":"2919_CR89","doi-asserted-by":"crossref","unstructured":"Yu, Q., Zhao, X., Pang, Y., Zhang, L., & Lu, H. (2024). Multi-view aggregation network for dichotomous image segmentation. In Conference on Computer Vision and Pattern Recognition, 3921\u20133930.","DOI":"10.1109\/CVPR52733.2024.00376"},{"key":"2919_CR90","doi-asserted-by":"crossref","unstructured":"Yuan, X., Cheng, G., Yan, K., Zeng, Q., & Han, J. (2023). Small object detection via coarse-to-fine proposal generation and imitation learning. In International Conference on Computer Vision 6317\u20136327.","DOI":"10.1109\/ICCV51070.2023.00581"},{"key":"2919_CR91","doi-asserted-by":"crossref","unstructured":"Zareian, A., Rosa, K. D., Hu, D. H., & Chang, S.-F. (2021). Open-vocabulary object detection using captions. In Conference on Computer Vision and Pattern Recognition, 14393\u201314402.","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"2919_CR92","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., & Agrawala, M. (2023). Adding conditional control to text-to-image diffusion models. In International Conference on Computer Vision, 3836\u20133847.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"2919_CR93","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhou, D., Chen, S., Gao, S., & Ma, Y. (2016). Single-image crowd counting via multi-column convolutional neural network. In Conference on Computer Vision and Pattern Recognition, 589\u2013597.","DOI":"10.1109\/CVPR.2016.70"},{"key":"2919_CR94","doi-asserted-by":"crossref","unstructured":"Zhao, J.-X., Liu, J.-J., Fan, D.-P., Cao, Y., Yang, J., & Cheng, M.-M. (2019). Egnet: Edge guidance network for salient object detection. In International Conference on Computer Vision, 8779\u20138788.","DOI":"10.1109\/ICCV.2019.00887"},{"key":"2919_CR95","doi-asserted-by":"crossref","unstructured":"Zhao, X., Chang, S., Pang, Y., Yang, J., Zhang, L., & Lu, H. (2024). Adaptive multi-source predictor for zero-shot video object segmentation. International Journal of Computer Vision, 1\u201319.","DOI":"10.1007\/s11263-024-02024-8"},{"key":"2919_CR96","unstructured":"Zhao, X., Jia, H., Pang, Y., Lv, L., Tian, F., Zhang, L., Sun, W., & Lu, H. (2023). M2snet: Multi-scale in multi-scale subtraction network for medical image segmentation arXiv preprint arXiv:2303.10894."},{"key":"2919_CR97","doi-asserted-by":"crossref","unstructured":"Zhao, X., Pang, Y., Chen, Z., Yu, Q., Zhang, L., Liu, H., Zuo, J., & Lu, H. (2024). Towards automatic power battery detection: New challenge benchmark dataset and baseline. In Conference on Computer Vision and Pattern Recognition, 22020\u201322029.","DOI":"10.1109\/CVPR52733.2024.02079"},{"key":"2919_CR98","unstructured":"Zhao, X., Pang, Y., Ji, W., Sheng, B., Zuo, J., Zhang, L., & Lu, H. (2024). Spider: A unified framework for context-dependent concept segmentation. In International Conference on Machine Learning, 60906\u201360926."},{"key":"2919_CR99","doi-asserted-by":"crossref","unstructured":"Zhao, X., Pang, Y., Zhang, L., & Lu, H. (2022). Joint learning of salient object detection, depth estimation and contour extraction. IEEE Transactions on Image Processing,31, 7350\u20137362.","DOI":"10.1109\/TIP.2022.3222641"},{"key":"2919_CR100","doi-asserted-by":"crossref","unstructured":"Zhao, X., Pang, Y., Zhang, L., Lu, H., & Zhang, L. (2020). Suppress and balance: A simple gated network for salient object detection. In European Conference on Computer Vision, 35\u201351.","DOI":"10.1007\/978-3-030-58536-5_3"},{"key":"2919_CR101","doi-asserted-by":"crossref","unstructured":"Zhao, X., Pang, Y., Zhang, L., Lu, H., & Zhang, L.(2023).Towards diverse binary segmentation via a simple yet general gated network. arXiv preprint arXiv:2303.10396.","DOI":"10.1007\/s11263-024-02058-y"},{"key":"2919_CR102","doi-asserted-by":"crossref","unstructured":"Zhao, X., Zhang, L., & Lu, H. (2021). Automatic polyp segmentation via multi-scale subtraction network.  In International Conference on Medical Image Computing and Computer-Assisted Intervention  120\u2013130.","DOI":"10.1007\/978-3-030-87193-2_12"},{"key":"2919_CR103","unstructured":"Zhou, H., Chang, Y., Liu, H., Yan, W., Duan, Y., Shi, Z., Yan, L. (2024). Exploring the common appearance-boundary adaptation for nighttime optical flow. arXiv preprint arXiv:2401.17642"},{"key":"2919_CR104","doi-asserted-by":"crossref","unstructured":"Zhou, K., Wang, Y., Lv, T., Li, Y., Chen, L., Shen, Q., & Cao, X. (2022). Explore spatio-temporal aggregation for insubstantial object detection: benchmark dataset and baseline. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition., 3104\u20133115.","DOI":"10.1109\/CVPR52688.2022.00311"},{"key":"2919_CR105","doi-asserted-by":"crossref","unstructured":"Zhou, K., Wang, Y., Lv, T., Shen, Q., & Cao, X. (2024). Gaseous object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence.","DOI":"10.1109\/TPAMI.2024.3449994"},{"key":"2919_CR106","doi-asserted-by":"crossref","unstructured":"Zhou, T., Fu, H., Chen, G., Zhou, Y., Fan, D.-P., & Shao, L. (2021). Specificity-preserving rgb-d saliency detection In CVPR 4681\u20134691.","DOI":"10.1109\/ICCV48922.2021.00464"},{"key":"2919_CR107","doi-asserted-by":"publisher","DOI":"10.1016\/j.array.2019.100004","volume":"3","author":"T Zhou","year":"2019","unstructured":"Zhou, T., Ruan, S., & Canu, S. (2019). A review: Deep learning for medical image segmentation using multi-modality fusion. Array, 3, Article 100004.","journal-title":"Array"},{"key":"2919_CR108","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109555","volume":"140","author":"T Zhou","year":"2023","unstructured":"Zhou, T., Zhou, Y., He, K., Gong, C., Yang, J., Fu, H., & Shen, D. (2023). Cross-level feature aggregation network for polyp segmentation. Pattern Recognition, 140, Article 109555.","journal-title":"Pattern Recognition"},{"key":"2919_CR109","doi-asserted-by":"crossref","unstructured":"Zhu, L., Deng, Z., Hu, X., Fu, C.-W., Xu, X., Qin, J., & Heng, P.-A. (2018). Bidirectional feature pyramid network with recurrent attention residual modules for shadow detection. In European Conference on Computer Vision, 121\u2013136.","DOI":"10.1007\/978-3-030-01231-1_8"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02919-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02919-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02919-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T03:24:03Z","timestamp":1787369043000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02919-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,22]]},"references-count":109,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["2919"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02919-8","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,22]]},"assertion":[{"value":"25 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"356"}}