{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T20:11:34Z","timestamp":1781381494384,"version":"3.54.1"},"publisher-location":"Cham","reference-count":80,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733963","type":"print"},{"value":"9783031733970","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-3-031-73397-0_27","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:07:49Z","timestamp":1730574469000},"page":"464-483","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["UniFS: Universal Few-Shot Instance Perception with\u00a0Point Representations"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5736-7434","authenticated-orcid":false,"given":"Sheng","family":"Jin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4736-9453","authenticated-orcid":false,"given":"Ruijie","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2125-2760","authenticated-orcid":false,"given":"Lumin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6587-9878","authenticated-orcid":false,"given":"Wentao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8761-5563","authenticated-orcid":false,"given":"Chen","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6170-726X","authenticated-orcid":false,"given":"Ji","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6685-7950","authenticated-orcid":false,"given":"Ping","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Bohdal, O., et al.: Meta omnium: a benchmark for general-purpose learning-to-learn. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7693\u20137703 (2023)","DOI":"10.1109\/CVPR52729.2023.00743"},{"key":"27_CR2","unstructured":"Cao, Y., et al.: Few-shot object detection via association and discrimination. In: Advances in Neural Information Processing Systems, vol. 34, pp. 16570\u201316581 (2021)"},{"key":"27_CR3","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":"27_CR4","unstructured":"Chen, T., Saxena, S., Li, L., Fleet, D.J., Hinton, G.: Pix2seq: a language modeling framework for object detection. In: International Conference on Learning Representations (2022)"},{"key":"27_CR5","unstructured":"Chen, T., Saxena, S., Li, L., Lin, T.Y., Fleet, D.J., Hinton, G.E.: A unified sequence interface for vision tasks. In: Advances in Neural Information Processing Systems, vol. 35, pp. 31333\u201331346 (2022)"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Chen, W., et al.: Beyond appearance: a semantic controllable self-supervised learning framework for human-centric visual tasks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 15050\u201315061 (2023)","DOI":"10.1109\/CVPR52729.2023.01445"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Ci, Y., et al.: UniHCP: a unified model for human-centric perceptions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 17840\u201317852 (2023)","DOI":"10.1109\/CVPR52729.2023.01711"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: Centernet: keypoint triplets for object detection. In: International Conference on Computer Vision, pp. 6569\u20136578 (2019)","DOI":"10.1109\/ICCV.2019.00667"},{"issue":"2","key":"27_CR9","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Fan, Q., Zhuo, W., Tang, C.K., Tai, Y.W.: Few-shot object detection with attention-RPN and multi-relation detector. In: IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00407"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Fan, Z., et al.: FGN: fully guided network for few-shot instance segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 9172\u20139181 (2020)","DOI":"10.1109\/CVPR42600.2020.00919"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Ganea, D.A., Boom, B., Poppe, R.: Incremental few-shot instance segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1185\u20131194 (2021)","DOI":"10.1109\/CVPR46437.2021.00124"},{"key":"27_CR13","unstructured":"Gao, B.B., et al.: Decoupling classifier for boosting few-shot object detection and instance segmentation. In: Advances in Neural Information Processing Systems, vol. 35, pp. 18640\u201318652 (2022)"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Zoph, B., Cubuk, E.D., Le, Q.V., Lin, T.Y.: Multi-task self-training for learning general representations. In: International Conference on Computer Vision, pp. 8856\u20138865 (2021)","DOI":"10.1109\/ICCV48922.2021.00873"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Han, G., Ma, J., Huang, S., Chen, L., Chang, S.F.: Few-shot object detection with fully cross-transformer. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5321\u20135330 (2022)","DOI":"10.1109\/CVPR52688.2022.00525"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Hirschorn, O., Avidan, S.: Pose anything: a graph-based approach for category-agnostic pose estimation. arXiv preprint arXiv:2311.17891 (2023)","DOI":"10.1007\/978-3-031-73036-8_27"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Hong, F., Pan, L., Cai, Z., Liu, Z.: Versatile multi-modal pre-training for human-centric perception. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 16156\u201316166 (2022)","DOI":"10.1109\/CVPR52688.2022.01568"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Hu, H., Bai, S., Li, A., Cui, J., Wang, L.: Dense relation distillation with context-aware aggregation for few-shot object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 10185\u201310194 (2021)","DOI":"10.1109\/CVPR46437.2021.01005"},{"key":"27_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1007\/978-3-031-20065-6_37","volume-title":"Computer Vision - ECCV 2022","author":"W Jiang","year":"2022","unstructured":"Jiang, W., Jin, S., Liu, W., Qian, C., Luo, P., Liu, S.: Posetrans: a simple yet effective pose transformation augmentation for human pose estimation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13665, pp. 643\u2013659. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20065-6_37"},{"key":"27_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1007\/978-3-031-72649-1_8","volume-title":"Computer Vision - ECCV 2024","author":"S Jin","year":"2024","unstructured":"Jin, S., Li, S., Li, T., Liu, W., Qian, C., Luo, P.: You only learn one query: learning unified human query for single-stage multi-person multi-task human-centric perception. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024. LNCS, vol. 15076, pp. 126\u2013146. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72649-1_8"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Jin, S., Liu, W., Ouyang, W., Qian, C.: Multi-person articulated tracking with spatial and temporal embeddings. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5664\u20135673 (2019)","DOI":"10.1109\/CVPR.2019.00581"},{"key":"27_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"718","DOI":"10.1007\/978-3-030-58571-6_42","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Jin","year":"2020","unstructured":"Jin, S., et al.: Differentiable hierarchical graph grouping for multi-person pose estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 718\u2013734. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_42"},{"key":"27_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1007\/978-3-030-58545-7_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Jin","year":"2020","unstructured":"Jin, S., et al.: Whole-body human pose estimation in the wild. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 196\u2013214. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_12"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Kang, B., Liu, Z., Wang, X., Yu, F., Feng, J., Darrell, T.: Few-shot object detection via feature reweighting. In: International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00851"},{"key":"27_CR27","unstructured":"Kim, D., Kim, J., Cho, S., Luo, C., Hong, S.: Universal few-shot learning of dense prediction tasks with visual token matching. In: International Conference on Learning Representations (2023)"},{"key":"27_CR28","unstructured":"Koch, G., Zemel, R., Salakhutdinov, R., et\u00a0al.: Siamese neural networks for one-shot image recognition. In: ICML Deep Learning Workshop (2015)"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM (2017)","DOI":"10.1145\/3065386"},{"issue":"6266","key":"27_CR30","doi-asserted-by":"publisher","first-page":"1332","DOI":"10.1126\/science.aab3050","volume":"350","author":"BM Lake","year":"2015","unstructured":"Lake, B.M., Salakhutdinov, R., Tenenbaum, J.B.: Human-level concept learning through probabilistic program induction. Science 350(6266), 1332\u20131338 (2015)","journal-title":"Science"},{"key":"27_CR31","unstructured":"Lake, B.M., Salakhutdinov, R.R., Tenenbaum, J.: One-shot learning by inverting a compositional causal process. In: Advances in Neural Information Processing Systems (2013)"},{"key":"27_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1007\/978-3-030-01264-9_45","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H Law","year":"2018","unstructured":"Law, H., Deng, J.: CornerNet: detecting objects as paired keypoints. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11218, pp. 765\u2013781. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_45"},{"key":"27_CR33","doi-asserted-by":"crossref","unstructured":"Li, A., Li, Z.: Transformation invariant few-shot object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00311"},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Li, B., Yang, B., Liu, C., Liu, F., Ji, R., Ye, Q.: Beyond max-margin: class margin equilibrium for few-shot object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00728"},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"Li, F., et al.: 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 (2023)","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"27_CR36","doi-asserted-by":"crossref","unstructured":"Li, X., Wei, T., Chen, Y.P., Tai, Y.W., Tang, C.K.: FSS-1000: a 1000-class dataset for few-shot segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2869\u20132878 (2020)","DOI":"10.1109\/CVPR42600.2020.00294"},{"key":"27_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"27_CR38","unstructured":"Lu, J., Clark, C., Zellers, R., Mottaghi, R., Kembhavi, A.: Unified-IO: a unified model for vision, language, and multi-modal tasks. In: International Conference on Learning Representations (2022)"},{"key":"27_CR39","unstructured":"Michaelis, C., Ustyuzhaninov, I., Bethge, M., Ecker, A.S.: One-shot instance segmentation. arXiv preprint arXiv:1811.11507 (2018)"},{"key":"27_CR40","doi-asserted-by":"crossref","unstructured":"Nie, X., Feng, J., Zhang, J., Yan, S.: Single-stage multi-person pose machines. In: International Conference on Computer Vision, pp. 6951\u20136960 (2019)","DOI":"10.1109\/ICCV.2019.00705"},{"key":"27_CR41","doi-asserted-by":"crossref","unstructured":"Peng, S., Jiang, W., Pi, H., Li, X., Bao, H., Zhou, X.: Deep snake for real-time instance segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 8533\u20138542 (2020)","DOI":"10.1109\/CVPR42600.2020.00856"},{"key":"27_CR42","doi-asserted-by":"crossref","unstructured":"Qiao, L., Zhao, Y., Li, Z., Qiu, X., Wu, J., Zhang, C.: DeFRCN: decoupled faster R-CNN for few-shot object detection. In: International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00856"},{"key":"27_CR43","doi-asserted-by":"crossref","unstructured":"Ranjan, V., Sharma, U., Nguyen, T., Hoai, M.: Learning to count everything. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3394\u20133403 (2021)","DOI":"10.1109\/CVPR46437.2021.00340"},{"key":"27_CR44","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (2015)"},{"key":"27_CR45","unstructured":"Shao, J., Chen, S., et\u00a0al.: Intern: a new learning paradigm towards general vision. arXiv preprint arXiv:2111.08687 (2021)"},{"key":"27_CR46","unstructured":"Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"27_CR47","doi-asserted-by":"crossref","unstructured":"Sun, B., Li, B., Cai, S., Yuan, Y., Zhang, C.: FSCE: few-shot object detection via contrastive proposal encoding. In: IEEE Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00727"},{"key":"27_CR48","doi-asserted-by":"crossref","unstructured":"Sun, M., et al.: Uniap: towards universal animal perception in vision via few-shot learning. In: AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 5008\u20135016 (2024)","DOI":"10.1609\/aaai.v38i5.28305"},{"key":"27_CR49","doi-asserted-by":"crossref","unstructured":"Sun, Y., et al.: Misc210k: a large-scale dataset for multi-instance semantic correspondence. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7121\u20137130 (2023)","DOI":"10.1109\/CVPR52729.2023.00688"},{"key":"27_CR50","doi-asserted-by":"crossref","unstructured":"Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., Hospedales, T.M.: Learning to compare: Relation network for few-shot learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1199\u20131208 (2018)","DOI":"10.1109\/CVPR.2018.00131"},{"key":"27_CR51","doi-asserted-by":"crossref","unstructured":"Tang, S., et\u00a0al.: Humanbench: towards general human-centric perception with projector assisted pretraining. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 21970\u201321982 (2023)","DOI":"10.1109\/CVPR52729.2023.02104"},{"key":"27_CR52","unstructured":"Tian, Z., Chen, H., Shen, C.: Directpose: direct end-to-end multi-person pose estimation. arXiv preprint arXiv:1911.07451 (2019)"},{"key":"27_CR53","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"27_CR54","unstructured":"Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et\u00a0al.: Matching networks for one shot learning. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"27_CR55","unstructured":"Wang, J., et al.: Omnivl: one foundation model for image-language and video-language tasks. In: Advances in Neural Information Processing Systems, vol. 35, pp. 5696\u20135710 (2022)"},{"key":"27_CR56","unstructured":"Wang, P., et al.: OFA: unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. In: International Conference on Machine Learning, pp. 23318\u201323340 (2022)"},{"key":"27_CR57","unstructured":"Wang, X., Huang, T.E., Darrell, T., Gonzalez, J.E., Yu, F.: Frustratingly simple few-shot object detection. In: International Conference on Machine Learning (2020)"},{"key":"27_CR58","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, W., Cao, Y., Shen, C., Huang, T.: Images speak in images: a generalist painter for in-context visual learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6830\u20136839 (2023)","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"27_CR59","doi-asserted-by":"crossref","unstructured":"Wang, Y.X., Ramanan, D., Hebert, M.: Meta-learning to detect rare objects. In: International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.01002"},{"key":"27_CR60","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1007\/978-3-030-58607-2_31","volume-title":"Computer Vision \u2013 ECCV 2020","author":"F Wei","year":"2020","unstructured":"Wei, F., Sun, X., Li, H., Wang, J., Lin, S.: Point-set anchors for object detection, instance segmentation and pose estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 527\u2013544. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58607-2_31"},{"key":"27_CR61","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1007\/978-3-030-58517-4_27","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Wu","year":"2020","unstructured":"Wu, J., Liu, S., Huang, D., Wang, Y.: Multi-scale positive sample refinement for few-shot object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 456\u2013472. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58517-4_27"},{"key":"27_CR62","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1007\/978-3-030-01231-1_29","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Xiao","year":"2018","unstructured":"Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 472\u2013487. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_29"},{"key":"27_CR63","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1007\/978-3-030-58520-4_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Xiao","year":"2020","unstructured":"Xiao, Y., Marlet, R.: Few-shot object detection and viewpoint estimation for objects in the wild. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 192\u2013210. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_12"},{"key":"27_CR64","doi-asserted-by":"crossref","unstructured":"Xie, E., et al.: Polarmask: single shot instance segmentation with polar representation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 12193\u201312202 (2020)","DOI":"10.1109\/CVPR42600.2020.01221"},{"key":"27_CR65","doi-asserted-by":"crossref","unstructured":"Xu, L., et al.: Vipnas: efficient video pose estimation via neural architecture search. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 16072\u201316081 (2021)","DOI":"10.1109\/CVPR46437.2021.01581"},{"issue":"4","key":"27_CR66","first-page":"5296","volume":"45","author":"L Xu","year":"2022","unstructured":"Xu, L., et al.: Zoomnas: searching for whole-body human pose estimation in the wild. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 5296\u20135313 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"27_CR67","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1007\/978-3-031-20068-7_23","volume-title":"Computer Vision - ECCV 2022","author":"L Xu","year":"2022","unstructured":"Xu, L., et al.: Pose for everything: towards category-agnostic pose estimation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13666, pp. 398\u2013416. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20068-7_23"},{"key":"27_CR68","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1007\/978-3-031-19803-8_43","volume-title":"Computer Vision - ECCV 2022","author":"B Yan","year":"2022","unstructured":"Yan, B., et al.: Towards grand unification of object tracking. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13681, pp. 733\u2013751. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19803-8_43"},{"key":"27_CR69","doi-asserted-by":"crossref","unstructured":"Yan, X., Chen, Z., Xu, A., Wang, X., Liang, X., Lin, L.: Meta R-CNN: towards general solver for instance-level low-shot learning. In: International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00967"},{"key":"27_CR70","doi-asserted-by":"crossref","unstructured":"Yang, S.D., Su, H.T., Hsu, W.H., Chen, W.C.: Class-agnostic few-shot object counting. In: IEEE Winter Conference on Applications of Computer Vision, pp. 870\u2013878 (2021)","DOI":"10.1109\/WACV48630.2021.00091"},{"key":"27_CR71","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1007\/978-3-031-20059-5_30","volume-title":"Computer Vision \u2013 ECCV 2022","author":"Z Yang","year":"2022","unstructured":"Yang, Z., et al.: Unitab: unifying text and box outputs for grounded vision-language modeling. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13696, pp. 521\u2013539. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_30"},{"key":"27_CR72","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/978-3-031-72649-1_6","volume-title":"ECCV 2024","author":"R Yao","year":"2024","unstructured":"Yao, R., et al.: Gkgnet: group k-nearest neighbor based graph convolutional network for multi-label image recognition. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024. LNCS, vol. 15076, pp. 91\u2013107. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72649-1_6"},{"key":"27_CR73","doi-asserted-by":"crossref","unstructured":"You, Z., Yang, K., Luo, W., Lu, X., Cui, L., Le, X.: Few-shot object counting with similarity-aware feature enhancement. In: IEEE Winter Conference on Applications of Computer Vision, pp. 6315\u20136324 (2023)","DOI":"10.1109\/WACV56688.2023.00625"},{"key":"27_CR74","doi-asserted-by":"crossref","unstructured":"Zamir, A.R., Sax, A., Shen, W., Guibas, L.J., Malik, J., Savarese, S.: Taskonomy: disentangling task transfer learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3712\u20133722 (2018)","DOI":"10.1109\/CVPR.2018.00391"},{"key":"27_CR75","doi-asserted-by":"crossref","unstructured":"Zeng, W., et al.: Not all tokens are equal: human-centric visual analysis via token clustering transformer. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 11101\u201311111 (2022)","DOI":"10.1109\/CVPR52688.2022.01082"},{"key":"27_CR76","doi-asserted-by":"crossref","unstructured":"Zhang, G., Luo, Z., Cui, K., Lu, S., Xing, E.P.: Meta-DETR: image-level few-shot detection with inter-class correlation exploitation. IEEE Trans. Pattern Anal. Mach. Intell. (2022)","DOI":"10.1109\/TPAMI.2022.3195735"},{"key":"27_CR77","unstructured":"Zhang, H., et al.: Dino: DETR with improved denoising anchor boxes for end-to-end object detection. In: International Conference on Learning Representations (2023)"},{"key":"27_CR78","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zeng, W., Jin, S., Qian, C., Luo, P., Liu, W.: When pedestrian detection meets multi-modal learning: generalist model and benchmark dataset. In: ECCV 2024. Springer, Cham (2024)","DOI":"10.1007\/978-3-031-73195-2_25"},{"key":"27_CR79","doi-asserted-by":"crossref","unstructured":"Zhu, C., Chen, F., Ahmed, U., Shen, Z., Savvides, M.: Semantic relation reasoning for shot-stable few-shot object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00867"},{"key":"27_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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 16804\u201316815 (2022)","DOI":"10.1109\/CVPR52688.2022.01630"}],"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\/978-3-031-73397-0_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T18:18:09Z","timestamp":1732990689000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73397-0_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031733963","9783031733970"],"references-count":80,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73397-0_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 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"}}]}}