{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,12]],"date-time":"2026-11-12T12:08:23Z","timestamp":1794485303650,"version":"4.9.1"},"publisher-location":"Cham","reference-count":81,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727504","type":"print"},{"value":"9783031727511","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72751-1_1","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T05:52:13Z","timestamp":1729835533000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4176,"title":["YOLOv9: Learning What You Want to\u00a0Learn Using Programmable Gradient Information"],"prefix":"10.1007","author":[{"given":"Chien-Yao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"I-Hau","family":"Yeh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong-Yuan","family":"Mark Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"1_CR1","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: BEiT: BERT pre-training of image transformers. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"1_CR2","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"1_CR3","unstructured":"Cai, Y., et al.: Reversible column networks. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"1_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Chen, K., Lin, W., Li, J., See, J., Wang, J., Zou, J.: AP-loss for accurate one-stage object detection. IEEE Trans. Pattern Anal. Mach. Intell. 43(11), 3782\u20133798 (2020)","DOI":"10.1109\/TPAMI.2020.2991457"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: SdAE: self-distillated masked autoencoder. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 108\u2013124 (2022)","DOI":"10.1007\/978-3-031-20056-4_7"},{"key":"1_CR7","unstructured":"Chen, Y., Yuan, X., Wu, R., Wang, J., Hou, Q., Cheng, M.M.: YOLO-MS: rethinking multi-scale representation learning for real-time object detection. arXiv preprint arXiv:2308.05480 (2023)"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Ding, M., Xiao, B., Codella, N., Luo, P., Wang, J., Yuan, L.: DaVIT: dual attention vision transformers. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 74\u201392 (2022)","DOI":"10.1007\/978-3-031-20053-3_5"},{"key":"1_CR9","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., Gao, Y., Scott, M.R., Huang, W.: TOOD: task-aligned one-stage object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3490\u20133499 (2021)","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Gao, S.H., Cheng, M.M., Zhao, K., Zhang, X.Y., Yang, M.H., Torr, P.: Res2Net: a new multi-scale backbone architecture. IEEE Trans. Pattern Anal. Mach. Intell. 43(2), 652\u2013662 (2019)","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Ge, Z., Liu, S., Li, Z., Yoshie, O., Sun, J.: OTA: optimal transport assignment for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 303\u2013312 (2021)","DOI":"10.1109\/CVPR46437.2021.00037"},{"key":"1_CR13","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: YOLOX: exceeding YOLO series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"1_CR14","unstructured":"Glenn, J.: YOLOv5 release v7.0 (2022). https:\/\/github.com\/ultralytics\/yolov5\/releases\/tag\/v7.0"},{"key":"1_CR15","unstructured":"Glenn, J.: YOLOv8 release v8.1.0 (2024). https:\/\/github.com\/ultralytics\/ultralytics\/releases\/tag\/v8.1.0"},{"key":"1_CR16","unstructured":"Gomez, A.N., Ren, M., Urtasun, R., Grosse, R.B.: The reversible residual network: backpropagation without storing activations. Adv. Neural Inf. Process. Syst. (2017)"},{"key":"1_CR17","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Guo, C., Fan, B., Zhang, Q., Xiang, S., Pan, C.: AugFPN: improving multi-scale feature learning for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12595\u201312604 (2020)","DOI":"10.1109\/CVPR42600.2020.01261"},{"key":"1_CR19","unstructured":"Han, Q., Cai, Y., Zhang, X.: RevColV2: exploring disentangled representations in masked image modeling. Adv. Neural Inf. Process. Syst. (2023)"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Hayder, Z., He, X., Salzmann, M.: Boundary-aware instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5696\u20135704 (2017)","DOI":"10.1109\/CVPR.2017.70"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"K He","year":"2016","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630\u2013645. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_38"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Huang, K.C., Wu, T.H., Su, H.T., Hsu, W.H.: MonoDTR: monocular 3D object detection with depth-aware transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4012\u20134021 (2022)","DOI":"10.1109\/CVPR52688.2022.00398"},{"key":"1_CR25","unstructured":"Huang, L., Li, W., Shen, L., Fu, H., Xiao, X., Xiao, S.: YOLOCS: object detection based on dense channel compression for feature spatial solidification. arXiv preprint arXiv:2305.04170 (2023)"},{"key":"1_CR26","unstructured":"Jaegle, A., Gimeno, F., Brock, A., Vinyals, O., Zisserman, A., Carreira, J.: Perceiver: general perception with iterative attention. In: International Conference on Machine Learning (ICML), pp. 4651\u20134664 (2021)"},{"key":"1_CR27","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, vol.\u00a01, p.\u00a02 (2019)"},{"key":"1_CR28","unstructured":"Lee, C.Y., Xie, S., Gallagher, P., Zhang, Z., Tu, Z.: Deeply-supervised nets. In: Artificial Intelligence and Statistics, pp. 562\u2013570 (2015)"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Levinshtein, A., Sereshkeh, A.R., Derpanis, K.: DATNet: dense auxiliary tasks for object detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1419\u20131427 (2020)","DOI":"10.1109\/WACV45572.2020.9093325"},{"key":"1_CR30","unstructured":"Li, C., et al.: YOLOv6 v3.0: a full-scale reloading. arXiv preprint arXiv:2301.05586 (2023)"},{"key":"1_CR31","unstructured":"Li, C., et\u00a0al.: YOLOv6: a single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976 (2022)"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Li, H., et\u00a0al.: Uni-perceiver v2: a generalist model for large-scale vision and vision-language tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2691\u20132700 (2023)","DOI":"10.1109\/CVPR52729.2023.00264"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Li, S., He, C., Li, R., Zhang, L.: A dual weighting label assignment scheme for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9387\u20139396 (2022)","DOI":"10.1109\/CVPR52688.2022.00917"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Liang, T., et al.: CBNet: a composite backbone network architecture for object detection. IEEE Trans. Image Process. (2022)","DOI":"10.1109\/TIP.2022.3216771"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Lin, Z., Wang, Y., Zhang, J., Chu, X.: DynamicDet: a unified dynamic architecture for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6282\u20136291 (2023)","DOI":"10.1109\/CVPR52729.2023.00608"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"1_CR38","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: CBNet: a novel composite backbone network architecture for object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp. 11653\u201311660 (2020)","DOI":"10.1609\/aaai.v34i07.6834"},{"key":"1_CR39","unstructured":"Liu, Y., et al.: Vmamba: visual state space model. arXiv preprint arXiv:2401.10166 (2024)"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Z., et\u00a0al.: Swin transformer v2: scaling up capacity and resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A ConvNet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Lv, W., et al.: DETRs beat YOLOs on real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16965\u201316974 (2024)","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"1_CR44","unstructured":"Lyu, C., et al.: RTMDet: an empirical study of designing real-time object detectors. arXiv preprint arXiv:2212.07784 (2022)"},{"key":"1_CR45","unstructured":"Oksuz, K., Cam, B.C., Akbas, E., Kalkan, S.: A ranking-based, balanced loss function unifying classification and localisation in object detection. Adv. Neural Inf. Process. Syst. 33, 15534\u201315545 (2020)"},{"key":"1_CR46","doi-asserted-by":"crossref","unstructured":"Oksuz, K., Cam, B.C., Akbas, E., Kalkan, S.: Rank & sort loss for object detection and instance segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3009\u20133018 (2021)","DOI":"10.1109\/ICCV48922.2021.00300"},{"key":"1_CR47","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"1_CR48","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"1_CR49","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"1_CR50","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"1_CR51","doi-asserted-by":"crossref","unstructured":"Shen, Z., Liu, Z., Li, J., Jiang, Y.G., Chen, Y., Xue, X.: Object detection from scratch with deep supervision. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 398\u2013412 (2019)","DOI":"10.1109\/TPAMI.2019.2922181"},{"key":"1_CR52","unstructured":"Shridhar, M., Manuelli, L., Fox, D.: Perceiver-actor: a multi-task transformer for robotic manipulation. In: Conference on Robot Learning (CoRL), pp. 785\u2013799 (2023)"},{"key":"1_CR53","unstructured":"Sun, P., et al.: What makes for end-to-end object detection? In: International Conference on Machine Learning (ICML), pp. 9934\u20139944 (2021)"},{"key":"1_CR54","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.\u00a01\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1_CR55","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"1_CR56","doi-asserted-by":"crossref","unstructured":"Tang, Z., Cho, J., Lei, J., Bansal, M.: Perceiver-VL: efficient vision-and-language modeling with iterative latent attention. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 4410\u20134420 (2023)","DOI":"10.1109\/WACV56688.2023.00439"},{"key":"1_CR57","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"1_CR58","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: a simple and strong anchor-free object detector. IEEE Trans. Pattern Anal. Mach. Intell. 44(4), 1922\u20131933 (2022)"},{"key":"1_CR59","doi-asserted-by":"crossref","unstructured":"Tishby, N., Zaslavsky, N.: Deep learning and the information bottleneck principle. In: IEEE Information Theory Workshop (ITW), pp.\u00a01\u20135 (2015)","DOI":"10.1109\/ITW.2015.7133169"},{"key":"1_CR60","doi-asserted-by":"crossref","unstructured":"Tu, Z., et al.: MaxVIT: Multi-axis vision transformer. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 459\u2013479 (2022)","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"1_CR61","unstructured":"Wang, C., et al.: Gold-YOLO: efficient object detector via gather-and-distribute mechanism. Adv. Neural Inf. Process. Syst. (2023)"},{"key":"1_CR62","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: Scaled-YOLOv4: scaling cross stage partial network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13029\u201313038 (2021)","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"1_CR63","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7464\u20137475 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"1_CR64","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Liao, H.Y.M., Wu, Y.H., Chen, P.Y., Hsieh, J.W., Yeh, I.H.: CSPNet: a new backbone that can enhance learning capability of CNN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 390\u2013391 (2020)","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"1_CR65","unstructured":"Wang, C.Y., Liao, H.Y.M., Yeh, I.H.: Designing network design strategies through gradient path analysis. J. Inf. Sci. Eng. (2023)"},{"key":"1_CR66","doi-asserted-by":"crossref","unstructured":"Wang, J., Song, L., Li, Z., Sun, H., Sun, J., Zheng, N.: End-to-end object detection with fully convolutional network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15849\u201315858 (2021)","DOI":"10.1109\/CVPR46437.2021.01559"},{"key":"1_CR67","unstructured":"Wang, L., Lee, C.Y., Tu, Z., Lazebnik, S.: Training deeper convolutional networks with deep supervision. arXiv preprint arXiv:1505.02496 (2015)"},{"key":"1_CR68","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"1_CR69","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: PVT v2: improved baselines with pyramid vision transformer. Comput. Visual Media 8(3), 415\u2013424 (2022)","DOI":"10.1007\/s41095-022-0274-8"},{"key":"1_CR70","doi-asserted-by":"crossref","unstructured":"Woo, S., et al.: ConvNeXt v2: co-designing and scaling convnets with masked autoencoders. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16133\u201316142 (2023)","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"1_CR71","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"1_CR72","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: SimMIM: a simple framework for masked image modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9653\u20139663 (2022)","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"1_CR73","unstructured":"Xu, S., et\u00a0al.: PP-YOLOE: an evolved version of YOLO. arXiv preprint arXiv:2203.16250 (2022)"},{"key":"1_CR74","unstructured":"Xu, X., Jiang, Y., Chen, W., Huang, Y., Zhang, Y., Sun, X.: DAMO-YOLO: a report on real-time object detection design. arXiv preprint arXiv:2211.15444 (2022)"},{"key":"1_CR75","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: MonoDETR: depth-guided transformer for monocular 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9155\u20139166 (2023)","DOI":"10.1109\/ICCV51070.2023.00840"},{"key":"1_CR76","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-IoU loss: faster and better learning for bounding box regression. Proc. AAAI Conf. Artif. Intell. 34, 12993\u201313000 (2020)","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"1_CR77","doi-asserted-by":"crossref","unstructured":"Zhou, D., et al.: IoU loss for 2D\/3D object detection. In: International Conference on 3D Vision (3DV), pp. 85\u201394 (2019)","DOI":"10.1109\/3DV.2019.00019"},{"key":"1_CR78","unstructured":"Zhu, B., et al.: AutoAssign: differentiable label assignment for dense object detection. arXiv preprint arXiv:2007.03496 (2020)"},{"key":"1_CR79","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., Wang, X.: Vision mamba: efficient visual representation learning with bidirectional state space model. arXiv preprint arXiv:2401.09417 (2024)"},{"key":"1_CR80","doi-asserted-by":"crossref","unstructured":"Zhu, X., et al.: Uni-perceiver: pre-training unified architecture for generic perception for zero-shot and few-shot tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16804\u201316815 (2022)","DOI":"10.1109\/CVPR52688.2022.01630"},{"key":"1_CR81","doi-asserted-by":"crossref","unstructured":"Zong, Z., Song, G., Liu, Y.: DETRs with collaborative hybrid assignments training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6748\u20136758 (2023)","DOI":"10.1109\/ICCV51070.2023.00621"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72751-1_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T06:11:43Z","timestamp":1729836703000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72751-1_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031727504","9783031727511"],"references-count":81,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72751-1_1","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/978-3-031-72751-1","asserted-by":"object"}]},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}