{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T00:47:17Z","timestamp":1786495637479,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":85,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732416","type":"print"},{"value":"9783031732423","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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\/978-3-031-73242-3_25","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:15:43Z","timestamp":1730106943000},"page":"444-462","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["When Do We Not Need Larger Vision Models?"],"prefix":"10.1007","author":[{"given":"Baifeng","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maolin","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Trevor","family":"Darrell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"25_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"25_CR2","unstructured":"Bai, J., et al.: Qwen-VL: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Bai, Y., et al.: Sequential modeling enables scalable learning for large vision models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22861\u201322872 (2024)","DOI":"10.1109\/CVPR52733.2024.02157"},{"issue":"48","key":"25_CR4","doi-asserted-by":"publisher","first-page":"30063","DOI":"10.1073\/pnas.1907378117","volume":"117","author":"PL Bartlett","year":"2020","unstructured":"Bartlett, P.L., Long, P.M., Lugosi, G., Tsigler, A.: Benign overfitting in linear regression. Proc. Natl. Acad. Sci. 117(48), 30063\u201330070 (2020)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"25_CR5","unstructured":"Bello, I., et al.: Revisiting resnets: improved training and scaling strategies. In: Advances in Neural Information Processing Systems, vol. 34, pp. 22614\u201322627 (2021)"},{"key":"25_CR6","unstructured":"Beyer, L., H\u00e9naff, O.J., Kolesnikov, A., Zhai, X., van den Oord, A.: Are we done with imagenet? arXiv preprint arXiv:2006.07159 (2020)"},{"key":"25_CR7","unstructured":"Bolya, D., Ryali, C., Hoffman, J., Feichtenhofer, C.: Window attention is bugged: how not to interpolate position embeddings. arXiv preprint arXiv:2311.05613 (2023)"},{"key":"25_CR8","unstructured":"Brooks, T., et al.: Video generation models as world simulators (2024). https:\/\/openai.com\/research\/video-generation-models-as-world-simulators"},{"key":"25_CR9","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, vol. 33, pp. 1877\u20131901 (2020)"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Chen, C.F.R., Fan, Q., Panda, R.: CrossViT: cross-attention multi-scale vision transformer for image classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 357\u2013366 (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"25_CR12","unstructured":"Cheng, C., Duchi, J., Kuditipudi, R.: Memorize to generalize: on the necessity of interpolation in high dimensional linear regression. In: Conference on Learning Theory, pp. 5528\u20135560. PMLR (2022)"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132829 (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"25_CR14","unstructured":"Chiang, W.L., et\u00a0al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* chatgpt quality (2023). https:\/\/vicuna.lmsys.org. Accessed 14 Apr 2023"},{"key":"25_CR15","unstructured":"Contributors, M.: MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark (2020). https:\/\/github.com\/open-mmlab\/mmsegmentation"},{"key":"25_CR16","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning (2023)"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol.\u00a01, pp. 886\u2013893. IEEE (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"25_CR18","unstructured":"Dehghani, M., et\u00a0al.: Scaling vision transformers to 22 billion parameters. In: International Conference on Machine Learning, pp. 7480\u20137512. PMLR (2023)"},{"issue":"8","key":"25_CR19","doi-asserted-by":"publisher","first-page":"1532","DOI":"10.1109\/TPAMI.2014.2300479","volume":"36","author":"P Doll\u00e1r","year":"2014","unstructured":"Doll\u00e1r, P., Appel, R., Belongie, S., Perona, P.: Fast feature pyramids for object detection. IEEE Trans. Pattern Anal. Mach. Intell. 36(8), 1532\u20131545 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r, P., Singh, M., Girshick, R.: Fast and accurate model scaling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 924\u2013932 (2021)","DOI":"10.1109\/CVPR46437.2021.00098"},{"key":"25_CR21","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"25_CR22","unstructured":"El-Nouby, A., et al.: Scalable pre-training of large autoregressive image models. arXiv preprint arXiv:2401.08541 (2024)"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6824\u20136835 (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Fang, Y., et al.: Eva: exploring the limits of masked visual representation learning at scale. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19358\u201319369 (2023)","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Feldman, V.: Does learning require memorization? A short tale about a long tail. In: Proceedings of the 52nd Annual ACM SIGACT Symposium on Theory of Computing, pp. 954\u2013959 (2020)","DOI":"10.1145\/3357713.3384290"},{"key":"25_CR26","unstructured":"Feldman, V., Zhang, C.: What neural networks memorize and why: discovering the long tail via influence estimation. In: Advances in Neural Information Processing Systems, vol. 33, pp. 2881\u20132891 (2020)"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Gurari, D., et al.: Vizwiz grand challenge: answering visual questions from blind people. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3608\u20133617 (2018)","DOI":"10.1109\/CVPR.2018.00380"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"25_CR31","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"25_CR32","unstructured":"Hu, R., Debnath, S., Xie, S., Chen, X.: Exploring long-sequence masked autoencoders. arXiv preprint arXiv:2210.07224 (2022)"},{"issue":"3","key":"25_CR33","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1038\/35058500","volume":"2","author":"L Itti","year":"2001","unstructured":"Itti, L., Koch, C.: Computational modelling of visual attention. Nat. Rev. Neurosci. 2(3), 194\u2013203 (2001)","journal-title":"Nat. Rev. Neurosci."},{"key":"25_CR34","unstructured":"Kondratyuk, D., et\u00a0al.: VideoPoet: a large language model for zero-shot video generation. arXiv preprint arXiv:2312.14125 (2023)"},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Lee, Y., Kim, J., Willette, J., Hwang, S.J.: MPViT: multi-path vision transformer for dense prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7287\u20137296 (2022)","DOI":"10.1109\/CVPR52688.2022.00714"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Li, B., Wang, R., Wang, G., Ge, Y., Ge, Y., Shan, Y.: Seed-bench: benchmarking multimodal LLMs with generative comprehension. arXiv preprint arXiv:2307.16125 (2023)","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"25_CR37","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 Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"25_CR38","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"25_CR39","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: MMBench: is your multi-modal model an all-around player? arXiv preprint arXiv:2307.06281 (2023)","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"25_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, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"25_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, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"25_CR43","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60, 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"25_CR44","unstructured":"Lu, P., et al.: MathVista: evaluating mathematical reasoning of foundation models in visual contexts. arXiv preprint arXiv:2310.02255 (2023)"},{"key":"25_CR45","unstructured":"Lukasik, M., Nagarajan, V., Rawat, A.S., Menon, A.K., Kumar, S.: What do larger image classifiers memorise? arXiv preprint arXiv:2310.05337 (2023)"},{"key":"25_CR46","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/j.patrec.2016.01.019","volume":"72","author":"J Malik","year":"2016","unstructured":"Malik, J., et al.: The three r\u2019s of computer vision: recognition, reconstruction and reorganization. Pattern Recogn. Lett. 72, 4\u201314 (2016)","journal-title":"Pattern Recogn. Lett."},{"key":"25_CR47","unstructured":"Northcutt, C.G., Athalye, A., Mueller, J.: Pervasive label errors in test sets destabilize machine learning benchmarks. arXiv preprint arXiv:2103.14749 (2021)"},{"key":"25_CR48","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"25_CR49","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"8","key":"25_CR50","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"25_CR51","unstructured":"Radosavovic, I., Shi, B., Fu, L., Goldberg, K., Darrell, T., Malik, J.: Robot learning with sensorimotor pre-training. arXiv preprint arXiv:2306.10007 (2023)"},{"key":"25_CR52","unstructured":"Radosavovic, I., Xiao, T., James, S., Abbeel, P., Malik, J., Darrell, T.: Real-world robot learning with masked visual pre-training. In: Conference on Robot Learning, pp. 416\u2013426. PMLR (2023)"},{"key":"25_CR53","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, 1(2), 3 (2022)"},{"key":"25_CR54","unstructured":"Riquelme, C., et al.: Scaling vision with sparse mixture of experts. In: Advances in Neural Information Processing Systems, vol. 34, pp. 8583\u20138595 (2021)"},{"key":"25_CR55","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"25_CR56","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"25_CR57","unstructured":"Ryali, C., et\u00a0al.: Hiera: a hierarchical vision transformer without the bells-and-whistles. arXiv preprint arXiv:2306.00989 (2023)"},{"key":"25_CR58","doi-asserted-by":"crossref","unstructured":"Shi, B., Darrell, T., Wang, X.: Top-down visual attention from analysis by synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2102\u20132112 (2023)","DOI":"10.1109\/CVPR52729.2023.00209"},{"key":"25_CR59","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"25_CR60","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"25_CR61","unstructured":"Steiner, A., Kolesnikov, A., Zhai, X., Wightman, R., Uszkoreit, J., Beyer, L.: How to train your ViT? Data, augmentation, and regularization in vision transformers. arXiv preprint arXiv:2106.10270 (2021)"},{"key":"25_CR62","unstructured":"Sun, Q., Fang, Y., Wu, L., Wang, X., Cao, Y.: Eva-clip: improved training techniques for clip at scale. arXiv preprint arXiv:2303.15389 (2023)"},{"key":"25_CR63","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"25_CR64","unstructured":"Tan, M., Le, Q.: EfficientNetv2: smaller models and faster training. In: International Conference on Machine Learning, pp. 10096\u201310106. PMLR (2021)"},{"key":"25_CR65","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"25_CR66","unstructured":"Team, Q.: Introducing Qwen-VL (2024). https:\/\/qwenlm.github.io\/blog\/qwen-vl\/"},{"key":"25_CR67","doi-asserted-by":"crossref","unstructured":"Tompson, J., Goroshin, R., Jain, A., LeCun, Y., Bregler, C.: Efficient object localization using convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 648\u2013656 (2015)","DOI":"10.1109\/CVPR.2015.7298664"},{"key":"25_CR68","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"issue":"10","key":"25_CR69","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2020","unstructured":"Wang, J., et al.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3349\u20133364 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR70","unstructured":"Wang, W., et\u00a0al.: CogVLM: visual expert for pretrained language models. arXiv preprint arXiv:2311.03079 (2023)"},{"key":"25_CR71","unstructured":"Wightman, R., Touvron, H., J\u00e9gou, H.: Resnet strikes back: an improved training procedure in timm. arXiv preprint arXiv:2110.00476 (2021)"},{"key":"25_CR72","doi-asserted-by":"crossref","unstructured":"Wu, P., Xie, S.: V*: Guided visual search as a core mechanism in multimodal LLMs. arXiv preprint arXiv:2312.14135 (2023)","DOI":"10.1109\/CVPR52733.2024.01243"},{"key":"25_CR73","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2 (2019). https:\/\/github.com\/facebookresearch\/detectron2"},{"key":"25_CR74","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3733\u20133742 (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"25_CR75","unstructured":"Xu, Y., Zhao, S., Song, J., Stewart, R., Ermon, S.: A theory of usable information under computational constraints. arXiv preprint arXiv:2002.10689 (2020)"},{"key":"25_CR76","unstructured":"Yang, J., et al.: Focal attention for long-range interactions in vision transformers. In: Advances in Neural Information Processing Systems, vol. 34, pp. 30008\u201330022 (2021)"},{"key":"25_CR77","unstructured":"Yu, J., et\u00a0al.: Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789, 2(3), 5 (2022)"},{"key":"25_CR78","unstructured":"Yu, W., et al.: MM-vet: evaluating large multimodal models for integrated capabilities. arXiv preprint arXiv:2308.02490 (2023)"},{"key":"25_CR79","doi-asserted-by":"crossref","unstructured":"Yue, X., et\u00a0al.: MMMU: a massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI. arXiv preprint arXiv:2311.16502 (2023)","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"25_CR80","doi-asserted-by":"crossref","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N., Beyer, L.: Scaling vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12104\u201312113 (2022)","DOI":"10.1109\/CVPR52688.2022.01179"},{"issue":"3","key":"25_CR81","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/3446776","volume":"64","author":"C Zhang","year":"2021","unstructured":"Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning (still) requires rethinking generalization. Commun. ACM 64(3), 107\u2013115 (2021)","journal-title":"Commun. ACM"},{"key":"25_CR82","doi-asserted-by":"crossref","unstructured":"Zhang, W., et al.: Elf: accelerate high-resolution mobile deep vision with content-aware parallel offloading. In: Proceedings of the 27th Annual International Conference on Mobile Computing and Networking, pp. 201\u2013214 (2021)","DOI":"10.1145\/3447993.3448628"},{"key":"25_CR83","doi-asserted-by":"crossref","unstructured":"Zhao, W., Rao, Y., Liu, Z., Liu, B., Zhou, J., Lu, J.: Unleashing text-to-image diffusion models for visual perception. arXiv preprint arXiv:2303.02153 (2023)","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"25_CR84","doi-asserted-by":"crossref","unstructured":"Zhaoping, L.: Understanding Vision: Theory, Models, and Data. Oxford University Press (UK) (2014)","DOI":"10.1093\/acprof:oso\/9780199564668.001.0001"},{"key":"25_CR85","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"}],"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\/978-3-031-73242-3_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T10:27:24Z","timestamp":1732962444000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73242-3_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031732416","9783031732423"],"references-count":85,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73242-3_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 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"}}]}}