{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T12:03:34Z","timestamp":1784894614340,"version":"3.55.0"},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T00:00:00Z","timestamp":1782000000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T00:00:00Z","timestamp":1782000000000},"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":["62302329"],"award-info":[{"award-number":["62302329"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Suzhou Planning Project of Science and Technology","award":["SKY2023128"],"award-info":[{"award-number":["SKY2023128"]}]},{"name":"the Open Project Program of State Key Laboratory of Virtual Reality Technology and Systems, Beihang University","award":["No.VRLAB2024B07"],"award-info":[{"award-number":["No.VRLAB2024B07"]}]},{"name":"the Major Projects of Basic Science Research of Jiangsu Higher Education Institutions","award":["25KJA520008"],"award-info":[{"award-number":["25KJA520008"]}]},{"name":"the Priority Academic Program Development of Jiangsu Higher Education Institutions"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1007\/s00371-026-04545-4","type":"journal-article","created":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T08:11:25Z","timestamp":1782029485000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing small object detection: a transformer-based middleware approach"],"prefix":"10.1007","volume":"42","author":[{"given":"Fei","family":"Gu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zijun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,21]]},"reference":[{"key":"4545_CR1","doi-asserted-by":"publisher","first-page":"4297","DOI":"10.1109\/TMM.2020.3040539","volume":"23","author":"L Chen","year":"2021","unstructured":"Chen, L., Zheng, H., Yan, Z., Li, Y.: Discriminative Region Mining for Object Detection. IEEE Trans. Multimedia 23, 4297\u20134310 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"4545_CR2","doi-asserted-by":"publisher","first-page":"2058","DOI":"10.1109\/TMM.2021.3075323","volume":"24","author":"S Wu","year":"2021","unstructured":"Wu, S., Xu, Y., Zhang, B., Yang, J., Zhang, D.: Deformable template network (DTN) for object detection. IEEE Trans. Multimedia 24, 2058\u20132068 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"4545_CR3","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1109\/TIP.2022.3231744","volume":"32","author":"Z Wu","year":"2023","unstructured":"Wu, Z., Liu, C., Wen, J., Xu, Y., Yang, J., Li, X.: Selecting High-Quality Proposals for Weakly Supervised Object Detection With Bottom-Up Aggregated Attention and Phase-Aware Loss. IEEE Trans. Image Process. 32, 682\u2013693 (2023)","journal-title":"IEEE Trans. Image Process."},{"issue":"3","key":"4545_CR4","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/JPROC.2023.3238524","volume":"111","author":"Z Zou","year":"2023","unstructured":"Zou, Z., Chen, K., Shi, Z., Guo, Y., Ye, J.: Object detection in 20 years: A survey. Proc. IEEE 111(3), 257\u2013276 (2023)","journal-title":"Proc. IEEE"},{"key":"4545_CR5","doi-asserted-by":"crossref","unstructured":"Chen, S., Sun, P., Song, Y., Luo, P.: Diffusiondet: Diffusion model for object detection, 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), 19830\u201319843 (2023)","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"4545_CR6","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1109\/TIP.2022.3228497","volume":"32","author":"X Wu","year":"2023","unstructured":"Wu, X., Hong, D., Chanussot, J.: UIU-Net: U-Net in U-Net for Infrared Small Object Detection. IEEE Trans. Image Process. 32, 364\u2013376 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"4545_CR7","doi-asserted-by":"crossref","unstructured":"He, C., Li, K., Zhang, Y., Tang, L., Zhang, Y., Guo, Z., Li, X.: Camouflaged object detection with feature decomposition and edge reconstruction, 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 22046\u201322055 (2023)","DOI":"10.1109\/CVPR52729.2023.02111"},{"issue":"5","key":"4545_CR8","doi-asserted-by":"publisher","first-page":"3509","DOI":"10.1109\/TPAMI.2023.3342120","volume":"46","author":"K Duan","year":"2024","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: CenterNet++ for Object Detection. IEEE Trans. Pattern Anal. Mach. Intell. 46(5), 3509\u20133521 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4545_CR9","doi-asserted-by":"crossref","unstructured":"Wang, X., Girdhar, R., Yu, S.X., Misra, I.: Cut and learn for unsupervised object detection and instance segmentation, 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 3124\u20133134 (2023)","DOI":"10.1109\/CVPR52729.2023.00305"},{"key":"4545_CR10","doi-asserted-by":"crossref","unstructured":"Li, Y., Hou, Q., Zheng, Z., Cheng, M.-M., Yang, J., Li, X.: Large selective kernel network for remote sensing object detection, 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), 16794\u201316805 (2023)","DOI":"10.1109\/ICCV51070.2023.01540"},{"key":"4545_CR11","doi-asserted-by":"publisher","first-page":"1329","DOI":"10.1109\/TIP.2023.3242775","volume":"32","author":"W Zhou","year":"2023","unstructured":"Zhou, W., Zhu, Y., Lei, J., Yang, R., Yu, L.: LSNet: Lightweight spatial boosting network for detecting salient objects in RGB-thermal images. IEEE Trans. Image Process. 32, 1329\u20131340 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"4545_CR12","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks, 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 11531\u201311539 (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"4545_CR13","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: EfficientDet: Scalable and Efficient Object Detection, 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 10778\u201310787 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"4545_CR14","first-page":"15908","volume":"34","author":"K Han","year":"2021","unstructured":"Han, K., Xiao, A., Wu, E., Guo, J., Xu, C., Wang, Y.: Transformer in transformer. Adv. Neural. Inf. Process. Syst. 34, 15908\u201315919 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4545_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows, 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 9992\u201310002 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"4545_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., Dong, L., and others: Swin transformer v2: Scaling up capacity and resolution, 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12009\u201312019 (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"4545_CR17","doi-asserted-by":"crossref","unstructured":"Lan, M., Zhang, J., He, F., Zhang, L.: Siamese network with interactive transformer for video object segmentation, AAAI Conference on Artificial Intelligence (AAAI) 1228\u20131236 (2022)","DOI":"10.1609\/aaai.v36i2.20009"},{"key":"4545_CR18","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection, 2017 IEEE\/CVF International Conference on Computer Vision (ICCV), 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"4545_CR19","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-End Object Detection with Transformers, European Conference on Computer Vision (ECCV), 213\u2013229, (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"4545_CR20","doi-asserted-by":"crossref","unstructured":"Zong, Z., Song, G., Liu, Y.: DETRs with Collaborative Hybrid Assignments Training, 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), 6725\u20136735 (2023)","DOI":"10.1109\/ICCV51070.2023.00621"},{"issue":"1","key":"4545_CR21","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1007\/s00371-024-03341-2","volume":"41","author":"P Ma","year":"2025","unstructured":"Ma, P., He, X., Chen, Y., Liu, Y.: ISOD: Improved small object detection based on extended scale feature pyramid network. Vis. Comput. 41(1), 465\u2013479 (2025)","journal-title":"Vis. Comput."},{"key":"4545_CR22","doi-asserted-by":"crossref","unstructured":"Wang, S., Liu, Y., Wang, T., Li, Y., Zhang, X.: Exploring object-centric temporal modeling for efficient multi-view 3d object detection, 2023 IEEE\/CVF International Conference on Computer Vision (ICCV) 3621\u20133631 (2023)","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"4545_CR23","doi-asserted-by":"publisher","first-page":"4341","DOI":"10.1109\/TIP.2023.3297408","volume":"32","author":"Yu Quan","year":"2023","unstructured":"Quan, Yu., Zhang, D., Zhang, L., Tang, J.: Centralized Feature Pyramid for Object Detection. IEEE Trans. Image Process. 32, 4341\u20134354 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"4545_CR24","doi-asserted-by":"publisher","first-page":"3778","DOI":"10.1109\/TIP.2024.3411474","volume":"33","author":"L-J Zhao","year":"2024","unstructured":"Zhao, L.-J., Chen, Z.-D., Ma, Z.-X., Luo, X., Xu, X.-S.: Angular Isotonic Loss Guided Multi-Layer Integration for Few-Shot Fine-Grained Image Classification. IEEE Trans. Image Process. 33, 3778\u20133792 (2024)","journal-title":"IEEE Trans. Image Process."},{"key":"4545_CR25","doi-asserted-by":"crossref","unstructured":"Zuo, F., Liu, J., Chen, Z., Zhang, H., Fu, M., Wang, L.: Multilevel Fine-Grained Features-Based General Framework for Object Detection, IEEE Transactions on Cybernetics 1-13, (2024)","DOI":"10.1109\/TCYB.2024.3424430"},{"issue":"1","key":"4545_CR26","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.vrih.2022.07.006","volume":"5","author":"M Zhang","year":"2023","unstructured":"Zhang, M., Tian, X.: Transformer architecture based on mutual attention for image-anomaly detection. Virtual Reality & Intelligent Hardware 5(1), 57\u201367 (2023)","journal-title":"Virtual Reality & Intelligent Hardware"},{"issue":"3","key":"4545_CR27","doi-asserted-by":"publisher","DOI":"10.1002\/cav.70030","volume":"36","author":"C Lin","year":"2025","unstructured":"Lin, C., Zou, C., Xu, H.: SCNet: A Dual-Branch Network for Strong Noisy Image Denoising Based on Swin Transformer and ConvNeXt. Computer Animation and Virtual Worlds 36(3), e70030 (2025)","journal-title":"Computer Animation and Virtual Worlds"},{"issue":"4","key":"4545_CR28","doi-asserted-by":"publisher","DOI":"10.1002\/cav.70021","volume":"36","author":"H Xue","year":"2025","unstructured":"Xue, H., Wang, M.: LGNet: Local-And-Global Feature Adaptive Network for Single Image Two-Hand Reconstruction. Computer Animation and Virtual Worlds 36(4), e70021 (2025)","journal-title":"Computer Animation and Virtual Worlds"},{"key":"4545_CR29","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2021","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: EAPT: efficient attention pyramid transformer for image processing. IEEE Trans. Multimedia 25, 50\u201361 (2021)","journal-title":"IEEE Trans. Multimedia"},{"issue":"8","key":"4545_CR30","doi-asserted-by":"publisher","first-page":"4499","DOI":"10.1109\/TNNLS.2021.3116209","volume":"34","author":"Z Xie","year":"2021","unstructured":"Xie, Z., Zhang, W., Sheng, B., Li, P., Chen, C.L.P.: Bagfn: broad attentive graph fusion network for high-order feature interactions. IEEE transactions on neural networks and learning systems 34(8), 4499\u20134513 (2021)","journal-title":"IEEE transactions on neural networks and learning systems"},{"key":"4545_CR31","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141, Polosukhin, I.: Attention is all you need. Adv. Neural. Inf. Process. Syst. 30, 5998\u20136008 (2017)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4545_CR32","unstructured":"Dehghani, M., Djolonga, J., Mustafa, B., Padlewski, P., Heek, J., Gilmer, J., Steiner, A.P., Caron, M., Geirhos, R., Alabdulmohsin, I., others.: Scaling vision transformers to 22 billion parameters, International Conference on Machine Learning, 7480\u20137512 (2023)"},{"key":"4545_CR33","doi-asserted-by":"crossref","unstructured":"Vasu, P.K.A., Gabriel, J., Zhu, J., Tuzel, O., Ranjan, A.: FastViT: A Fast Hybrid Vision Transformer Using Structural Reparameterization, 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), 5762\u20135772 (2023)","DOI":"10.1109\/ICCV51070.2023.00532"},{"key":"4545_CR34","doi-asserted-by":"crossref","unstructured":"Chen, Z., Xie, L., Niu, J., Liu, X., Wei, L., Tian, Q.: Visformer: The Vision-Friendly Transformer, 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 569\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00063"},{"key":"4545_CR35","doi-asserted-by":"crossref","unstructured":"Pu, Y., Liang, W., Hao, Y., Yuan, Y., Yang, Y., Zhang, C., Hu, H., Huang, G.: Rank-DETR for high quality object detection, Advances in Neural Information Processing Systems, 36 (2024)","DOI":"10.52202\/075280-0708"},{"key":"4545_CR36","doi-asserted-by":"crossref","unstructured":"Jia, D., Yuan, Y., He, H., Wu, X., Yu, H., Lin, W., Sun, L., Zhang, C., Hu, H.: DETRs with Hybrid Matching, 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 19702\u201319712 (2023)","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"4545_CR37","doi-asserted-by":"crossref","unstructured":"Chen, Y., Dai, X., Chen, D., Liu, M., Dong, X., Yuan, L., Liu, Z.: Mobile-Former: Bridging MobileNet and Transformer, 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 5260\u20135269 (2022)","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"4545_CR38","doi-asserted-by":"crossref","unstructured":"Liu, H., Jiang, X., Li, X., Bao, Z., Jiang, D., Ren, B.: NomMer: Nominate Synergistic Context in Vision Transformer for Visual Recognition, 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12063\u201312072 (2022)","DOI":"10.1109\/CVPR52688.2022.01176"},{"key":"4545_CR39","doi-asserted-by":"publisher","first-page":"4595","DOI":"10.1109\/TIP.2023.3302521","volume":"32","author":"Y Zheng","year":"2023","unstructured":"Zheng, Y., Xie, J., Sain, A., Song, Y.-Z., Ma, Z.: Sketch-Segformer: Transformer-Based Segmentation for Figurative and Creative Sketches. IEEE Trans. Image Process. 32, 4595\u20134609 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"4545_CR40","doi-asserted-by":"crossref","unstructured":"Zheng, S., Lu, J., Zhao, H., Zhu, X., Luo, Z., Wang, Y., Fu, Y., Feng, J., Xiang, T., Torr, P.H.S., Zhang, L.: Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 6877\u20136886 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"4545_CR41","doi-asserted-by":"crossref","unstructured":"Chen, Q., Chen, X., Wang, J., Zhang, S., Yao, K., Feng, H., Han, J., Ding, E., Zeng, G., Wang, J.: Group detr: Fast detr training with group-wise one-to-many assignment 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 6633\u20136642 (2023)","DOI":"10.1109\/ICCV51070.2023.00610"},{"key":"4545_CR42","doi-asserted-by":"crossref","unstructured":"Zheng, D., Dong, W., Hu, H., Chen, X., Wang, Y.: Less is more: Focus attention for efficient detr, 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 6674\u20136683 (2023)","DOI":"10.1109\/ICCV51070.2023.00614"},{"key":"4545_CR43","doi-asserted-by":"publisher","first-page":"9099","DOI":"10.1109\/TIP.2021.3118953","volume":"30","author":"P-Y Chen","year":"2021","unstructured":"Chen, P.-Y., Chang, M.-C., Hsieh, J.-W., Chen, Y.-S.: Parallel Residual Bi-Fusion Feature Pyramid Network for Accurate Single-Shot Object Detection. IEEE Trans. Image Process. 30, 9099\u20139111 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"4545_CR44","doi-asserted-by":"crossref","unstructured":"Hu, H., Zhang, Z., Xie, Z., Lin, S.: Local Relation Networks for Image Recognition, 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), 3463-3472 (2019)","DOI":"10.1109\/ICCV.2019.00356"},{"key":"4545_CR45","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","volume":"32","author":"Z Wu","year":"2021","unstructured":"Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., Philip, S.Y.: A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems 32, 4\u201324 (2021)","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"4545_CR46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIP.2023.3334954","volume":"33","author":"X Wang","year":"2024","unstructured":"Wang, X., Zhang, W., Wang, C., Gao, Y., Liu, M.: Dynamic Dense Graph Convolutional Network for Skeleton-Based Human Motion Prediction. IEEE Trans. Image Process. 33, 1\u201315 (2024)","journal-title":"IEEE Trans. Image Process."},{"key":"4545_CR47","doi-asserted-by":"publisher","first-page":"8291","DOI":"10.52202\/068431-0603","volume":"35","author":"K Han","year":"2022","unstructured":"Han, K., Wang, Y., Guo, J., Tang, Y., Wu, E.: Vision gnn: An image is worth graph of nodes. Adv. Neural. Inf. Process. Syst. 35, 8291\u20138303 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"4545_CR48","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1007\/s00371-024-03354-x","volume":"41","author":"L Wang","year":"2025","unstructured":"Wang, L., Li, J., Guo, S., Han, S.: A cascaded graph convolutional network for point cloud completion. Vis. Comput. 41(1), 659\u2013674 (2025)","journal-title":"Vis. Comput."},{"issue":"8","key":"4545_CR49","doi-asserted-by":"publisher","first-page":"7719","DOI":"10.1109\/TCYB.2022.3143798","volume":"52","author":"M Shi","year":"2022","unstructured":"Shi, M., Tang, Y., Zhu, X., Zhuang, Y., Lin, M., Liu, J.: Feature-Attention Graph Convolutional Networks for Noise Resilient Learning. IEEE Transactions on Cybernetics 52(8), 7719\u20137731 (2022)","journal-title":"IEEE Transactions on Cybernetics"},{"key":"4545_CR50","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1109\/TETCI.2023.3300303","volume":"8","author":"B Yu","year":"2024","unstructured":"Yu, B., Xie, H., Cai, M., Ding, W.: MG-GCN: Multi-Granularity Graph Convolutional Neural Network for Multi-Label Classification in Multi-Label Information System. IEEE Transactions on Emerging Topics in Computational Intelligence 8, 288\u2013299 (2024)","journal-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"key":"4545_CR51","doi-asserted-by":"crossref","unstructured":"Wang, J., Wang, Y., Yang, Z., Yang, L., Guo, Y.: Bi-gcn: Binary graph convolutional network, 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 1561\u20131570 (2021)","DOI":"10.1109\/CVPR46437.2021.00161"},{"key":"4545_CR52","doi-asserted-by":"crossref","unstructured":"Chatzianastasis, M., Lutzeyer, J., Dasoulas, G., Vazirgiannis, M.: Graph Ordering Attention Networks, AAAI Conference on Artificial Intelligence (AAAI), 7006\u20137014 (2023)","DOI":"10.1609\/aaai.v37i6.25856"},{"key":"4545_CR53","doi-asserted-by":"crossref","unstructured":"Schaefer, S., Gehrig, D., Scaramuzza, D.: AEGNN: Asynchronous Event-Based Graph Neural Networks, 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12361\u201312371 (2022)","DOI":"10.1109\/CVPR52688.2022.01205"},{"key":"4545_CR54","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path Aggregation Network for Instance Segmentation, 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 8759-8768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"4545_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, D., Zhang, H., Tang, J., Wang, M., Hua, X., Sun, Q.: Feature Pyramid Transformer, European Conference on Computer Vision (ECCV), 323\u2013339 (2020)","DOI":"10.1007\/978-3-030-58604-1_20"},{"key":"4545_CR56","doi-asserted-by":"crossref","unstructured":"Guo, C., Fan, B., Zhang, Q., Xiang, S., Pan, C.: Augfpn: Improving multi-scale feature learning for object detection, 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12595\u201312604 (2020)","DOI":"10.1109\/CVPR42600.2020.01261"},{"key":"4545_CR57","doi-asserted-by":"crossref","unstructured":"Qin, X., Wang, Z., Bai, Y., Xie, X., Jia, H.: FFA-Net: Feature fusion attention network for single image dehazing, AAAI Conference on Artificial Intelligence (AAAI), 11908\u201311915 (2020)","DOI":"10.1609\/aaai.v34i07.6865"},{"key":"4545_CR58","doi-asserted-by":"crossref","unstructured":"Dong, H., Pan, J., Xiang, L., Hu, Z., Zhang, X., Wang, F., Yang, M.-H.: Multi-scale boosted dehazing network with dense feature fusion, 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2157\u20132167 (2020)","DOI":"10.1109\/CVPR42600.2020.00223"},{"key":"4545_CR59","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature Pyramid Networks for Object Detection, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 936\u2013944, (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"4545_CR60","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep Residual Learning for Image Recognition, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770-778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"4545_CR61","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: Common objects in context, European Conference on Computer Vision (ECCV), 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"7","key":"4545_CR62","doi-asserted-by":"publisher","first-page":"4623","DOI":"10.1007\/s11263-025-02401-x","volume":"133","author":"Z Cai","year":"2025","unstructured":"Cai, Z., Huang, Y., Zhang, T., Zheng, Y., Yue, D.: Multi-source domain adaptation by causal-guided adaptive multimodal diffusion networks. Int. J. Comput. Vision 133(7), 4623\u20134645 (2025)","journal-title":"Int. J. Comput. Vision"},{"key":"4545_CR63","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110109","volume":"147","author":"Z Cai","year":"2024","unstructured":"Cai, Z., Huang, Y., Zhang, T., Jing, X.-Y., Zheng, Y., Shao, L.: Attention cycle-consistent universal network for more universal domain adaptation. Pattern Recogn. 147, 110109 (2024)","journal-title":"Pattern Recogn."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-026-04545-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-026-04545-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-026-04545-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T11:38:47Z","timestamp":1784893127000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-026-04545-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,21]]},"references-count":63,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["4545"],"URL":"https:\/\/doi.org\/10.1007\/s00371-026-04545-4","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,21]]},"assertion":[{"value":"19 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"349"}}