{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T20:47:00Z","timestamp":1742935620071,"version":"3.40.3"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031732348"},{"type":"electronic","value":"9783031732355"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-73235-5_15","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T06:01:53Z","timestamp":1727589713000},"page":"264-281","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["NOVUM: Neural Object Volumes for\u00a0Robust Object Classification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4837-8163","authenticated-orcid":false,"given":"Artur","family":"Jesslen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8183-0771","authenticated-orcid":false,"given":"Guofeng","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9189-5277","authenticated-orcid":false,"given":"Angtian","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4696-2833","authenticated-orcid":false,"given":"Wufei","family":"Ma","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5207-9249","authenticated-orcid":false,"given":"Alan","family":"Yuille","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9146-4403","authenticated-orcid":false,"given":"Adam","family":"Kortylewski","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Bai, Y., Wang, A., Kortylewski, A., Yuille, A.: Coke: localized contrastive learning for robust keypoint detection (2022)","DOI":"10.1109\/WACV56688.2023.00015"},{"issue":"7","key":"15_CR2","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/3448250","volume":"64","author":"Y Bengio","year":"2021","unstructured":"Bengio, Y., Lecun, Y., Hinton, G.: Deep learning for AI. Commun. ACM 64(7), 58\u201365 (2021)","journal-title":"Commun. ACM"},{"key":"15_CR3","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations (2020)"},{"key":"15_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/978-3-030-58574-7_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Chen","year":"2020","unstructured":"Chen, X., Dong, Z., Song, J., Geiger, A., Hilliges, O.: Category level object pose estimation via neural analysis-by-synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12371, pp. 139\u2013156. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58574-7_9"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation policies from data. arXiv preprint arXiv:1805.09501 (2018)","DOI":"10.1109\/CVPR.2019.00020"},{"key":"15_CR6","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"George, D., et\u00a0al.: A generative vision model that trains with high data efficiency and breaks text-based captchas. Science 358(6368), eaag2612 (2017)","DOI":"10.1126\/science.aag2612"},{"key":"15_CR8","unstructured":"Goodwin, W., Havoutis, I., Posner, I.: You only look at one: category-level object representations for pose estimation from a single example. arXiv preprint arXiv:2305.12626 (2023)"},{"key":"15_CR9","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1007\/978-3-031-19842-7_30","volume-title":"ECCV 2022","author":"W Goodwin","year":"2022","unstructured":"Goodwin, W., Vaze, S., Havoutis, I., Posner, I.: Zero-shot category-level object pose estimation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13699, pp. 516\u2013532. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19842-7_30"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Grenander, U.: A unified approach to pattern analysis. In: Advances in Computers, vol.\u00a010, pp. 175\u2013216. Elsevier (1970)","DOI":"10.1016\/S0065-2458(08)60436-2"},{"key":"15_CR11","doi-asserted-by":"publisher","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), vol.\u00a02, pp. 1735\u20131742 (2006). https:\/\/doi.org\/10.1109\/CVPR.2006.100","DOI":"10.1109\/CVPR.2006.100"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"15_CR13","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":"15_CR14","unstructured":"Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. In: International Conference on Learning Representations (2019)"},{"key":"15_CR15","unstructured":"Hendrycks, D., Mu, N., Cubuk, E.D., Zoph, B., Gilmer, J., Lakshminarayanan, B.: Augmix: a simple data processing method to improve robustness and uncertainty. arXiv preprint arXiv:1912.02781 (2019)"},{"key":"15_CR16","unstructured":"Hermann, K.L., Lampinen, A.K.: What shapes feature representations? Exploring datasets, architectures, and training (2020)"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Iwase, S., Liu, X., Khirodkar, R., Yokota, R., Kitani, K.M.: Repose: fast 6D object pose refinement via deep texture rendering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3303\u20133312 (2021)","DOI":"10.1109\/ICCV48922.2021.00329"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Jin, Y., Geman, S.: Context and hierarchy in a probabilistic image model. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), vol.\u00a02, pp. 2145\u20132152. IEEE (2006)","DOI":"10.1109\/CVPR.2006.86"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4) (2023)","DOI":"10.1145\/3592433"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Kortylewski, A., He, J., Liu, Q., Yuille, A.L.: Compositional convolutional neural networks: a deep architecture with innate robustness to partial occlusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00896"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Kortylewski, A., Liu, Q., Wang, H., Zhang, Z., Yuille, A.: Combining compositional models and deep networks for robust object classification under occlusion. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1333\u20131341 (2020)","DOI":"10.1109\/WACV45572.2020.9093560"},{"key":"15_CR22","unstructured":"LeCun, Y., Bengio, Y., et al.: Convolutional networks for images, speech, and time series. In: The Handbook of Brain Theory and Neural Networks, vol. 3361, no. 10, p. 1995 (1995)"},{"key":"15_CR23","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":"15_CR24","unstructured":"Locatello, F., et al.: Object-centric learning with slot attention. In: Advances in Neural Information Processing Systems, vol. 33, pp. 11525\u201311538 (2020)"},{"key":"15_CR25","unstructured":"Michaelis, C., et al.: Benchmarking robustness in object detection: autonomous driving when winter is coming. arXiv preprint arXiv:1907.07484 (2019)"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Mousavian, A., Anguelov, D., Flynn, J., Kosecka, J.: 3D bounding box estimation using deep learning and geometry. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7074\u20137082 (2017)","DOI":"10.1109\/CVPR.2017.597"},{"key":"15_CR27","unstructured":"Neisser, U., et\u00a0al.: Cognitive Psychology. Appleton-Century-Crofts (1967)"},{"key":"15_CR28","unstructured":"Nguyen, T., Raghu, M., Kornblith, S.: Do wide and deep networks learn the same things? Uncovering how neural network representations vary with width and depth (2021)"},{"key":"15_CR29","unstructured":"van\u00a0den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding (2019)"},{"key":"15_CR30","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021)"},{"key":"15_CR31","doi-asserted-by":"publisher","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 815\u2013823 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298682","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"15_CR32","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"15_CR33","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/s00180-011-0232-x","volume":"27","author":"S Sra","year":"2012","unstructured":"Sra, S.: A short note on parameter approximation for von mises-fisher distributions: and a fast implementation of i$$_{s}$$ (x). Comput. Stat. 27, 177\u2013190 (2012)","journal-title":"Comput. Stat."},{"key":"15_CR34","doi-asserted-by":"publisher","unstructured":"Stark, M., Goesele, M., Schiele, B.: Back to the future: learning shape models from 3D cad data. In: British Machine Vision Conference (BMVC), pp. 1\u201311 (2010). https:\/\/doi.org\/10.5244\/C.24.106","DOI":"10.5244\/C.24.106"},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Tulsiani, S., Malik, J.: Viewpoints and keypoints. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1510\u20131519 (2015)","DOI":"10.1109\/CVPR.2015.7298758"},{"key":"15_CR36","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"15_CR37","unstructured":"Wang, A., Kortylewski, A., Yuille, A.: Nemo: neural mesh models of contrastive features for robust 3D pose estimation. In: International Conference on Learning Representations (2021)"},{"key":"15_CR38","unstructured":"Wang, A., Mei, S., Yuille, A.L., Kortylewski, A.: Neural view synthesis and matching for semi-supervised few-shot learning of 3D pose. In: Advances in Neural Information Processing Systems, vol. 34, pp. 7207\u20137219 (2021)"},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Wang, A., Sun, Y., Kortylewski, A., Yuille, A.L.: Robust object detection under occlusion with context-aware compositionalnets. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12645\u201312654 (2020)","DOI":"10.1109\/CVPR42600.2020.01266"},{"key":"15_CR40","unstructured":"Wang, A., Wang, P., Sun, J., Kortylewski, A., Yuille, A.: Voge: a differentiable volume renderer using gaussian ellipsoids for analysis-by-synthesis. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Wang, H., Sridhar, S., Huang, J., Valentin, J., Song, S., Guibas, L.J.: Normalized object coordinate space for category-level 6D object pose and size estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2642\u20132651 (2019)","DOI":"10.1109\/CVPR.2019.00275"},{"key":"15_CR42","doi-asserted-by":"crossref","unstructured":"Wang, H., Sridhar, S., Huang, J., Valentin, J., Song, S., Guibas, L.J.: Normalized object coordinate space for category-level 6D object pose and size estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00275"},{"key":"15_CR43","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Mottaghi, R., Savarese, S.: Beyond pascal: a benchmark for 3D object detection in the wild. In: IEEE Winter Conference on Applications of Computer Vision, pp. 75\u201382. IEEE (2014)","DOI":"10.1109\/WACV.2014.6836101"},{"issue":"2","key":"15_CR44","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1109\/TRO.2020.3033695","volume":"37","author":"H Yang","year":"2020","unstructured":"Yang, H., Shi, J., Carlone, L.: TEASER: fast and certifiable point cloud registration. IEEE Trans. Robot. 37(2), 314\u2013333 (2020)","journal-title":"IEEE Trans. Robot."},{"key":"15_CR45","unstructured":"Yi, K., et al.: Clevrer: collision events for video representation and reasoning. arXiv preprint arXiv:1910.01442 (2019)"},{"key":"15_CR46","unstructured":"Yi, K., Wu, J., Gan, C., Torralba, A., Kohli, P., Tenenbaum, J.: Neural-symbolic VQA: disentangling reasoning from vision and language understanding. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"issue":"7","key":"15_CR47","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1016\/j.tics.2006.05.002","volume":"10","author":"A Yuille","year":"2006","unstructured":"Yuille, A., Kersten, D.: Vision as Bayesian inference: analysis by synthesis? Trends Cogn. Sci. 10(7), 301\u2013308 (2006)","journal-title":"Trends Cogn. Sci."},{"key":"15_CR48","doi-asserted-by":"crossref","unstructured":"Zhao, B., et al.: OOD-CV-v2: an extended benchmark for robustness to out-of-distribution shifts of individual nuisances in natural images. arXiv preprint arXiv:2304.10266 (2023)","DOI":"10.1109\/TPAMI.2024.3462293"},{"key":"15_CR49","unstructured":"Zhao, B., et al.: OOD-CV: a benchmark for robustness to individual nuisances in real-world out-of-distribution shifts. In: Proceedings of the European Conference on Computer Vision (ECCV) (2022)"},{"key":"15_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, X., Karpur, A., Luo, L., Huang, Q.: Starmap for category-agnostic keypoint and viewpoint estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 318\u2013334 (2018)","DOI":"10.1007\/978-3-030-01246-5_20"}],"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\/978-3-031-73235-5_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T06:15:01Z","timestamp":1727590501000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73235-5_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031732348","9783031732355"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73235-5_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 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"}}]}}