{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T03:17:28Z","timestamp":1783135048407,"version":"3.54.6"},"reference-count":71,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576187"],"award-info":[{"award-number":["62576187"]}],"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":["U2341228"],"award-info":[{"award-number":["U2341228"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.cviu.2026.104827","type":"journal-article","created":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:22:15Z","timestamp":1780676535000},"page":"104827","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A turbo-inference strategy for object detection and instance segmentation"],"prefix":"10.1016","volume":"270","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6522-9330","authenticated-orcid":false,"given":"Zhen","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4907-7354","authenticated-orcid":false,"given":"Xiaolin","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2026.104827_b1","series-title":"YOLOv4: Optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020"},{"key":"10.1016\/j.cviu.2026.104827_b2","doi-asserted-by":"crossref","unstructured":"Bodla, N., Singh, B., Chellappa, R., Davis, L.S., 2017. Soft-NMS: Improving object detection with one line of code. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 5561\u20135569.","DOI":"10.1109\/ICCV.2017.593"},{"key":"10.1016\/j.cviu.2026.104827_b3","doi-asserted-by":"crossref","unstructured":"Bolya, D., Zhou, C., Xiao, F., Lee, Y.J., 2019. YOLACT: Real-time instance segmentation. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 9157\u20139166.","DOI":"10.1109\/ICCV.2019.00925"},{"key":"10.1016\/j.cviu.2026.104827_b4","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N., 2018. Cascade R-CNN: Delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6154\u20136162.","DOI":"10.1109\/CVPR.2018.00644"},{"key":"10.1016\/j.cviu.2026.104827_b5","series-title":"European Conference on Computer Vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.cviu.2026.104827_b6","doi-asserted-by":"crossref","unstructured":"Chen, K., Pang, J., Wang, J., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Shi, J., Ouyang, W., et al., 2019a. Hybrid task cascade for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4974\u20134983.","DOI":"10.1109\/CVPR.2019.00511"},{"key":"10.1016\/j.cviu.2026.104827_b7","series-title":"Lw-detr: A transformer replacement to yolo for real-time detection","author":"Chen","year":"2024"},{"key":"10.1016\/j.cviu.2026.104827_b8","series-title":"MMDetection: Open mmlab detection toolbox and benchmark","author":"Chen","year":"2019"},{"key":"10.1016\/j.cviu.2026.104827_b9","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R., 2022. Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 1290\u20131299.","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"10.1016\/j.cviu.2026.104827_b10","series-title":"YOLO-world: Real-time open-vocabulary object detection","author":"Cheng","year":"2024"},{"key":"10.1016\/j.cviu.2026.104827_b11","doi-asserted-by":"crossref","unstructured":"Cheng, T., Wang, X., Chen, S., Zhang, W., Zhang, Q., Huang, C., Zhang, Z., Liu, W., 2022. Sparse instance activation for real-time instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4433\u20134442.","DOI":"10.1109\/CVPR52688.2022.00439"},{"key":"10.1016\/j.cviu.2026.104827_b12","series-title":"European Conference on Computer Vision","first-page":"660","article-title":"Boundary-preserving Mask R-CNN","author":"Cheng","year":"2020"},{"key":"10.1016\/j.cviu.2026.104827_b13","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., Schiele, B., 2016. The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3213\u20133223.","DOI":"10.1109\/CVPR.2016.350"},{"key":"10.1016\/j.cviu.2026.104827_b14","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.cviu.2026.104827_b15","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.cviu.2026.104827_b16","doi-asserted-by":"crossref","unstructured":"Fang, Y., Yang, S., Wang, X., Li, Y., Fang, C., Shan, Y., Feng, B., Liu, W., 2021. Instances as queries. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 6910\u20136919.","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"10.1016\/j.cviu.2026.104827_b17","first-page":"898","article-title":"Turbo learning framework for human-object interactions recognition and human pose estimation","volume":"vol. 33","author":"Feng","year":"2019"},{"key":"10.1016\/j.cviu.2026.104827_b18","series-title":"YOLOX: Exceeding YOLO series in 2021","author":"Ge","year":"2021"},{"key":"10.1016\/j.cviu.2026.104827_b19","doi-asserted-by":"crossref","unstructured":"Girshick, R., 2015. Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 1440\u20131448.","DOI":"10.1109\/ICCV.2015.169"},{"key":"10.1016\/j.cviu.2026.104827_b20","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J., 2014. Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 580\u2013587.","DOI":"10.1109\/CVPR.2014.81"},{"key":"10.1016\/j.cviu.2026.104827_b21","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R., 2017. Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2961\u20132969.","DOI":"10.1109\/ICCV.2017.322"},{"key":"10.1016\/j.cviu.2026.104827_b22","doi-asserted-by":"crossref","unstructured":"He, J., Li, P., Geng, Y., Xie, X., 2023. FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 23663\u201323672.","DOI":"10.1109\/CVPR52729.2023.02266"},{"key":"10.1016\/j.cviu.2026.104827_b23","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":"10.1016\/j.cviu.2026.104827_b24","doi-asserted-by":"crossref","unstructured":"Huang, Z., Huang, L., Gong, Y., Huang, C., Wang, X., 2019. Mask Scoring R-CNN. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6409\u20136418.","DOI":"10.1109\/CVPR.2019.00657"},{"key":"10.1016\/j.cviu.2026.104827_b25","article-title":"Spatial transformer networks","volume":"28","author":"Jaderberg","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104827_b26","doi-asserted-by":"crossref","unstructured":"Jiang, B., Luo, R., Mao, J., Xiao, T., Jiang, Y., 2018. Acquisition of localization confidence for accurate object detection. In: Proceedings of the European Conference on Computer Vision. pp. 784\u2013799.","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"10.1016\/j.cviu.2026.104827_b27","series-title":"Ultralytics YOLOv8","author":"Jocher","year":"2023"},{"key":"10.1016\/j.cviu.2026.104827_b28","series-title":"Ultralytics YOLO11","author":"Jocher","year":"2024"},{"key":"10.1016\/j.cviu.2026.104827_b29","doi-asserted-by":"crossref","unstructured":"Ke, L., Tai, Y.W., Tang, C.K., 2021. Deep occlusion-aware instance segmentation with overlapping bilayers. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4019\u20134028.","DOI":"10.1109\/CVPR46437.2021.00401"},{"key":"10.1016\/j.cviu.2026.104827_b30","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104827_b31","series-title":"YOLOv6: A single-stage object detection framework for industrial applications","author":"Li","year":"2022"},{"key":"10.1016\/j.cviu.2026.104827_b32","doi-asserted-by":"crossref","unstructured":"Li, X., Liu, Z., Luo, P., Change Loy, C., Tang, X., 2017. Not all pixels are equal: Difficulty-aware semantic segmentation via deep layer cascade. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3193\u20133202.","DOI":"10.1109\/CVPR.2017.684"},{"key":"10.1016\/j.cviu.2026.104827_b33","series-title":"European Conference on Computer Vision","first-page":"280","article-title":"Exploring plain vision transformer backbones for object detection","author":"Li","year":"2022"},{"key":"10.1016\/j.cviu.2026.104827_b34","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Xu, H., Liu, S., Zhang, L., Ni, L.M., Shum, H.Y., 2023. Mask dino: Towards a unified transformer-based framework for object detection and segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 3041\u20133050.","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"10.1016\/j.cviu.2026.104827_b35","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"10.1016\/j.cviu.2026.104827_b36","series-title":"European Conference on Computer Vision","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.cviu.2026.104827_b37","series-title":"DAB-DETR: Dynamic anchor boxes are better queries for detr","author":"Liu","year":"2022"},{"key":"10.1016\/j.cviu.2026.104827_b38","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: Proceedings of the IEEE International Conference on Computer Vision. pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.1016\/j.cviu.2026.104827_b39","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 11976\u201311986.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"10.1016\/j.cviu.2026.104827_b40","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J., 2018. Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 8759\u20138768.","DOI":"10.1109\/CVPR.2018.00913"},{"key":"10.1016\/j.cviu.2026.104827_b41","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T., 2015. Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"10.1016\/j.cviu.2026.104827_b42","series-title":"RTMDet: An empirical study of designing real-time object detectors","author":"Lyu","year":"2022"},{"key":"10.1016\/j.cviu.2026.104827_b43","doi-asserted-by":"crossref","unstructured":"Neven, D., Brabandere, B.D., Proesmans, M., Gool, L.V., 2019. Instance segmentation by jointly optimizing spatial embeddings and clustering bandwidth. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 8837\u20138845.","DOI":"10.1109\/CVPR.2019.00904"},{"key":"10.1016\/j.cviu.2026.104827_b44","series-title":"European Conference on Computer Vision","first-page":"19","article-title":"OSFormer: One-stage camouflaged instance segmentation with transformers","author":"Pei","year":"2022"},{"key":"10.1016\/j.cviu.2026.104827_b45","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A., 2016. You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 779\u2013788.","DOI":"10.1109\/CVPR.2016.91"},{"key":"10.1016\/j.cviu.2026.104827_b46","series-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"10.1016\/j.cviu.2026.104827_b47","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104827_b48","doi-asserted-by":"crossref","unstructured":"Sun, P., Zhang, R., Jiang, Y., Kong, T., Xu, C., Zhan, W., Tomizuka, M., Li, L., Yuan, Z., Wang, C., et al., 2021. Sparse R-CNN: End-to-end object detection with learnable proposals. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 14454\u201314463.","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"10.1016\/j.cviu.2026.104827_b49","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., 2020. Conditional Convolutions for Instance Segmentation. In: European Conference on Computer Vision. pp. 282\u2013298.","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"10.1016\/j.cviu.2026.104827_b50","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T., 2019. FCOS: Fully convolutional one-stage object detection. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 9627\u20139636.","DOI":"10.1109\/ICCV.2019.00972"},{"key":"10.1016\/j.cviu.2026.104827_b51","series-title":"YOLOv12: Attention-centric real-time object detectors","author":"Tian","year":"2025"},{"key":"10.1016\/j.cviu.2026.104827_b52","series-title":"YOLOv12: Attention-centric real-time object detectors","author":"Tian","year":"2025"},{"key":"10.1016\/j.cviu.2026.104827_b53","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104827_b54","first-page":"2701","article-title":"SCNet: Training inference sample consistency for instance segmentation","volume":"vol. 35","author":"Vu","year":"2021"},{"key":"10.1016\/j.cviu.2026.104827_b55","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M., 2023. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7464\u20137475.","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"10.1016\/j.cviu.2026.104827_b56","doi-asserted-by":"crossref","first-page":"107984","DOI":"10.52202\/079017-3429","article-title":"Yolov10: Real-time end-to-end object detection","volume":"37","author":"Wang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104827_b57","unstructured":"Wang, X., Kong, T., Shen, C., Jiang, Y., Li, L., 2019. SOLO: Segmenting Objects by Locations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3124\u20133133."},{"key":"10.1016\/j.cviu.2026.104827_b58","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Liao, H.Y.M., Wu, Y.H., Chen, P.Y., Hsieh, J.W., Yeh, I.H., 2020. CSPNet: A new backbone that can enhance learning capability of CNN. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 390\u2013391.","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"10.1016\/j.cviu.2026.104827_b59","series-title":"Yoloe: Real-time seeing anything","author":"Wang","year":"2025"},{"key":"10.1016\/j.cviu.2026.104827_b60","first-page":"17721","article-title":"SOLOv2: Dynamic and fast instance segmentation","volume":"33","author":"Wang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104827_b61","doi-asserted-by":"crossref","unstructured":"Woo, S., Debnath, S., Hu, R., Chen, X., Liu, Z., Kweon, I.S., Xie, S., 2023. ConvNext v2: Co-designing and scaling convnets with masked autoencoders. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 16133\u201316142.","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"10.1016\/j.cviu.2026.104827_b62","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K., 2017. Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1492\u20131500.","DOI":"10.1109\/CVPR.2017.634"},{"key":"10.1016\/j.cviu.2026.104827_b63","series-title":"PP-YOLOE: An evolved version of YOLO","author":"Xu","year":"2022"},{"key":"10.1016\/j.cviu.2026.104827_b64","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2023.103787","article-title":"3DF-FCOS: Small object detection with 3D features based on FCOS","volume":"235","author":"Yang","year":"2023","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2026.104827_b65","series-title":"DINO: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"},{"key":"10.1016\/j.cviu.2026.104827_b66","doi-asserted-by":"crossref","unstructured":"Zhang, G., Lu, X., Tan, J., Li, J., Zhang, Z., Li, Q., Hu, X., 2021. RefineMask: Towards high-quality instance segmentation with fine-grained features. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6861\u20136869.","DOI":"10.1109\/CVPR46437.2021.00679"},{"key":"10.1016\/j.cviu.2026.104827_b67","doi-asserted-by":"crossref","unstructured":"Zhang, R., Tian, Z., Shen, C., You, M., Yan, Y., 2020. Mask encoding for single shot instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 10226\u201310235.","DOI":"10.1109\/CVPR42600.2020.01024"},{"key":"10.1016\/j.cviu.2026.104827_b68","series-title":"2022 14th International Conference on Advanced Computational Intelligence","first-page":"376","article-title":"The winning solution to the iFLYTEK challenge 2021 cultivated land extraction from high-resolution remote sensing images","author":"Zhao","year":"2022"},{"key":"10.1016\/j.cviu.2026.104827_b69","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2023.103649","article-title":"SSDA-YOLO: Semi-supervised domain adaptive YOLO for cross-domain object detection","volume":"229","author":"Zhou","year":"2023","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2026.104827_b70","series-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"10.1016\/j.cviu.2026.104827_b71","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2019.102795","article-title":"Faster training of mask R-CNN by focusing on instance boundaries","volume":"188","author":"Zimmermann","year":"2019","journal-title":"Comput. Vis. Image Underst."}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226001943?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226001943?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T02:28:57Z","timestamp":1783132137000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314226001943"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":71,"alternative-id":["S1077314226001943"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104827","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A turbo-inference strategy for object detection and instance segmentation","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104827","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104827"}}