{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T04:09:23Z","timestamp":1748664563705,"version":"3.41.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031926471","type":"print"},{"value":"9783031926488","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-92648-8_11","type":"book-chapter","created":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T16:29:26Z","timestamp":1748622566000},"page":"170-182","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An Investigation on\u00a0The Position Encoding in\u00a0Vision-Based Dynamics Prediction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0162-6534","authenticated-orcid":false,"given":"Jiageng","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4474-4877","authenticated-orcid":false,"given":"Hanchen","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3938-7989","authenticated-orcid":false,"given":"Jiazhi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7326-861X","authenticated-orcid":false,"given":"Mahyar","family":"Khayatkhoei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8320-8530","authenticated-orcid":false,"given":"Wael","family":"AbdAlmageed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"11_CR1","unstructured":"de\u00a0Avila Belbute-Peres, F., Smith, K., Allen, K., Tenenbaum, J., Kolter, J.Z.: End-to-end differentiable physics for learning and control. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a031. Curran Associates, Inc. (2018)"},{"key":"11_CR2","unstructured":"Battaglia, P., Pascanu, R., Lai, M., Jimenez\u00a0Rezende, D., kavukcuoglu, k.: Interaction networks for learning about objects, relations and physics. In: Lee, D., Sugiyama, M., Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a029. Curran Associates, Inc. (2016)"},{"key":"11_CR3","unstructured":"Chang, M., Ullman, T.D., Torralba, A., Tenenbaum, J.B.: A compositional object-based approach to learning physical dynamics. In: ICLR (Poster). OpenReview.net (2017)"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"11_CR5","unstructured":"Ding, M., Chen, Z., Du, T., Luo, P., Tenenbaum, J., Gan, C.: Dynamic visual reasoning by learning differentiable physics models from video and language. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems, vol.\u00a034, pp. 887\u2013899. Curran Associates, Inc. (2021)"},{"key":"11_CR6","doi-asserted-by":"publisher","unstructured":"Girshick, R.: Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1440\u20131448 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), October 2017","DOI":"10.1109\/ICCV.2017.322"},{"key":"11_CR8","unstructured":"Islam, M.A., Jia, S., Bruce, N.D.B.: How much position information do convolutional neural networks encode? In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=rJeB36NKvB"},{"key":"11_CR9","doi-asserted-by":"publisher","first-page":"3889","DOI":"10.1007\/s11263-024-02069-9","volume":"132","author":"MA Islam","year":"2024","unstructured":"Islam, M.A., Kowal, M., Jia, S., Derpanis, K.G., Bruce, N.: Position, padding and predictions: a deeper look at position information in CNNs. Int. J. Comput. Vision. 132, 3889\u20133910 (2024)","journal-title":"Int. J. Comput. Vision."},{"key":"11_CR10","unstructured":"Janner, M., Levine, S., Freeman, W.T., Tenenbaum, J.B., Finn, C., Wu, J.: Reasoning about physical interactions with object-centric models. In: International Conference on Learning Representations (2019)"},{"key":"11_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"11_CR12","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9 Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems 32, pp. 8024\u20138035. Curran Associates, Inc. (2019). http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"11_CR13","unstructured":"Qi, H., Wang, X., Pathak, D., Ma, Y., Malik, J.: Learning long-term visual dynamics with region proposal interaction networks. In: ICLR (2021)"},{"key":"11_CR14","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a028. Curran Associates, Inc. (2015)"},{"key":"11_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/978-3-319-46475-6_7","volume-title":"Computer Vision \u2013 ECCV 2016","author":"SR Richter","year":"2016","unstructured":"Richter, S.R., Vineet, V., Roth, S., Koltun, V.: Playing for data: ground truth from computer games. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 102\u2013118. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_7"},{"key":"11_CR16","unstructured":"Ullman, T., Stuhlm\u00fcller, A., Goodman, N., Tenenbaum, J.B.: Learning physics from dynamical scenes. In: Proceedings of the 36th Annual Conference of the Cognitive Science Society, pp. 1640\u20131645 (2014)"},{"key":"11_CR17","unstructured":"Wu, J., Lu, E., Kohli, P., Freeman, B., Tenenbaum, J.: Learning to see physics via visual de-animation. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a030. Curran Associates, Inc. (2017)"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Wu, Q., Teney, D., Wang, P., Shen, C., Dick, A., van den Hengel, A.: Visual question answering: a survey of methods and datasets. Comput. Vis. Image Underst. 163, 21\u201340 (2017)","DOI":"10.1016\/j.cviu.2017.05.001"},{"key":"11_CR19","unstructured":"Xie, H., Zhu, J., Khayatkhoei, M., Li, J., Hussein, M.E., Abdalmageed, W.: A critical view of vision-based long-term dynamics prediction under environment misalignment. In: Proceedings of the 40th International Conference on Machine Learning (2023)"},{"key":"11_CR20","unstructured":"Yurtsever, E., Lambert, J., Carballo, A., Takeda, K.: A survey of autonomous driving: Common practices and emerging technologies. CoRR abs\/1906.05113 (2019). http:\/\/arxiv.org\/abs\/1906.05113"},{"key":"11_CR21","unstructured":"Zhu, J., Xie, H., Li, J., Abd-Almageed, W.: Diffusioncounterfactuals: inferring high-dimensional counterfactuals with guidance of causal representations (2024). https:\/\/arxiv.org\/abs\/2407.20553"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-92648-8_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T16:29:32Z","timestamp":1748622572000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-92648-8_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031926471","9783031926488"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-92648-8_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}