{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:29:17Z","timestamp":1767338957588,"version":"3.40.3"},"publisher-location":"Cham","reference-count":74,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031167874"},{"type":"electronic","value":"9783031167881"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-16788-1_35","type":"book-chapter","created":{"date-parts":[[2022,9,22]],"date-time":"2022-09-22T20:35:56Z","timestamp":1663878956000},"page":"577-593","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["GazeTransformer: Gaze Forecasting for\u00a0Virtual Reality Using Transformer Networks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9038-3196","authenticated-orcid":false,"given":"Tim","family":"Rolff","sequence":"first","affiliation":[]},{"given":"H. Matthias","family":"Harms","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9879-7414","authenticated-orcid":false,"given":"Frank","family":"Steinicke","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9475-3593","authenticated-orcid":false,"given":"Simone","family":"Frintrop","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,9,20]]},"reference":[{"issue":"4","key":"35_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3127589","volume":"14","author":"R Albert","year":"2017","unstructured":"Albert, R., Patney, A., Luebke, D., Kim, J.: Latency requirements for foveated rendering in virtual reality. ACM Trans. Appl. Percept. (TAP) 14(4), 1\u201313 (2017)","journal-title":"ACM Trans. Appl. Percept. (TAP)"},{"issue":"5","key":"35_CR2","doi-asserted-by":"publisher","first-page":"2577","DOI":"10.1109\/TVCG.2021.3067784","volume":"27","author":"AN Angelopoulos","year":"2021","unstructured":"Angelopoulos, A.N., Martel, J.N., Kohli, A.P., Conradt, J., Wetzstein, G.: Event-based near-eye gaze tracking beyond 10,000 hz. IEEE Trans. Vis. Comput. Graph. (TVCG) 27(5), 2577\u20132586 (2021)","journal-title":"IEEE Trans. Vis. Comput. Graph. (TVCG)"},{"issue":"2","key":"35_CR3","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TPAMI.2019.2935715","volume":"43","author":"A Borji","year":"2019","unstructured":"Borji, A.: Saliency prediction in the deep learning era: successes and limitations. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 43(2), 679\u2013700 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"35_CR4","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural Inf. Process. Syst. (NeurIPS) 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"unstructured":"Bylinskii, Z., et al.: Mit saliency benchmark (2015)","key":"35_CR5"},{"key":"35_CR6","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"},{"doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9650\u20139660 (2021)","key":"35_CR7","DOI":"10.1109\/ICCV48922.2021.00951"},{"unstructured":"Chen, M., et al.: Generative pretraining from pixels. In: Proceedings of the 37th International Conference on Machine Learning, vol. 119, pp. 1691\u20131703. PMLR (2020)","key":"35_CR8"},{"doi-asserted-by":"crossref","unstructured":"Cheng, R., Wu, N., Chen, S., Han, B.: Reality check of metaverse: a first look at commercial social virtual reality platforms. In: IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), pp. 141\u2013148. IEEE (2022)","key":"35_CR9","DOI":"10.1109\/VRW55335.2022.00040"},{"issue":"19","key":"35_CR10","doi-asserted-by":"publisher","first-page":"R850","DOI":"10.1016\/j.cub.2004.09.041","volume":"14","author":"CE Connor","year":"2004","unstructured":"Connor, C.E., Egeth, H.E., Yantis, S.: Visual attention: bottom-up versus top-down. Curr. Biol. 14(19), R850\u2013R852 (2004)","journal-title":"Curr. Biol."},{"doi-asserted-by":"crossref","unstructured":"Crevecoeur, F., Kording, K.P.: Saccadic suppression as a perceptual consequence of efficient sensorimotor estimation. eLife 6, e25073 (2017)","key":"35_CR11","DOI":"10.7554\/eLife.25073"},{"doi-asserted-by":"crossref","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q.V., Salakhutdinov, R.: Transformer-xl: Attentive language models beyond a fixed-length context. arXiv preprint arXiv:1901.02860 (2019)","key":"35_CR12","DOI":"10.18653\/v1\/P19-1285"},{"unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)","key":"35_CR13"},{"unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: 9th International Conference on Learning Representations (ICLR). OpenReview (2021)","key":"35_CR14"},{"key":"35_CR15","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.cag.2018.04.002","volume":"73","author":"AT Duchowski","year":"2018","unstructured":"Duchowski, A.T.: Gaze-based interaction: a 30 year retrospective. Comput. Graph. 73, 59\u201369 (2018)","journal-title":"Comput. Graph."},{"issue":"11","key":"35_CR16","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1167\/16.11.13","volume":"16","author":"W Einh\u00e4user","year":"2016","unstructured":"Einh\u00e4user, W., Nuthmann, A.: Salient in space, salient in time: fixation probability predicts fixation duration during natural scene viewing. J. Vision 16(11), 13\u201313 (2016)","journal-title":"J. Vision"},{"doi-asserted-by":"crossref","unstructured":"Emery, K.J., Zannoli, M., Warren, J., Xiao, L., Talathi, S.S.: OpenNEEDS: a dataset of gaze, head, hand, and scene signals during exploration in open-ended vr environments. In: ACM Symposium on Eye Tracking Research and Applications (ETRA). ACM, New York (2021)","key":"35_CR17","DOI":"10.1145\/3448018.3457996"},{"doi-asserted-by":"crossref","unstructured":"Franke, L., Fink, L., Martschinke, J., Selgrad, K., Stamminger, M.: Time-warped foveated rendering for virtual reality headsets. In: Computer Graphics Forum, vol. 40, pp. 110\u2013123. Wiley Online Library (2021)","key":"35_CR18","DOI":"10.1111\/cgf.14176"},{"key":"35_CR19","doi-asserted-by":"publisher","DOI":"10.1007\/11682110","volume-title":"VOCUS: A Visual Attention System for Object Detection and Goal-Directed search","author":"S Frintrop","year":"2006","unstructured":"Frintrop, S.: VOCUS: A Visual Attention System for Object Detection and Goal-Directed search, vol. 3899. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11682110"},{"doi-asserted-by":"crossref","unstructured":"Fuhl, W., Kasneci, G., Kasneci, E.: TEyeD: over 20 million real-world eye images with pupil, eyelid, and iris 2D and 3D segmentations, 2D and 3D landmarks, 3D eyeball, gaze vector, and eye movement types. In: IEEE International Symposium on Mixed and Augmented Reality (ISMAR), pp. 367\u2013375. IEEE (2021)","key":"35_CR20","DOI":"10.1109\/ISMAR52148.2021.00053"},{"issue":"6","key":"35_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2366145.2366183","volume":"31","author":"B Guenter","year":"2012","unstructured":"Guenter, B., Finch, M., Drucker, S., Tan, D., Snyder, J.: Foveated 3D graphics. ACM Trans. Graph. (TOG) 31(6), 1\u201310 (2012)","journal-title":"ACM Trans. Graph. (TOG)"},{"doi-asserted-by":"crossref","unstructured":"Gurusamy, K.S., Aggarwal, R., Palanivelu, L., Davidson, B.R.: Virtual reality training for surgical trainees in laparoscopic surgery. Cochrane Database Syst. Revi. (CDSR) (1) (2009)","key":"35_CR22","DOI":"10.1002\/14651858.CD006575.pub2"},{"doi-asserted-by":"crossref","unstructured":"Han, D.I.D., Bergs, Y., Moorhouse, N.: Virtual reality consumer experience escapes: preparing for the metaverse. In: Virtual Reality, pp. 1\u201316 (2022)","key":"35_CR23","DOI":"10.1007\/s10055-022-00641-7"},{"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 (CVPR), pp. 770\u2013778 (2016)","key":"35_CR24","DOI":"10.1109\/CVPR.2016.90"},{"issue":"1","key":"35_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.291","volume":"5","author":"N Hollenstein","year":"2018","unstructured":"Hollenstein, N., Rotsztejn, J., Troendle, M., Pedroni, A., Zhang, C., Langer, N.: ZuCo, a simultaneous EEG and eye-tracking resource for natural sentence reading. Sci. Data 5(1), 1\u201313 (2018)","journal-title":"Sci. Data"},{"key":"35_CR26","volume-title":"Eye Tracking: A Comprehensive Guide to Methods and Measures","author":"K Holmqvist","year":"2011","unstructured":"Holmqvist, K., Nystr\u00f6m, M., Andersson, R., Dewhurst, R., Jarodzka, H., Van de Weijer, J.: Eye Tracking: A Comprehensive Guide to Methods and Measures. OUP Oxford, Oxford (2011)"},{"issue":"5","key":"35_CR27","doi-asserted-by":"publisher","first-page":"2681","DOI":"10.1109\/TVCG.2021.3067779","volume":"27","author":"Z Hu","year":"2021","unstructured":"Hu, Z., Bulling, A., Li, S., Wang, G.: FixationNet: forecasting eye fixations in task-oriented virtual environments. IEEE Trans. Vis. Comput. Graph. (TVCG) 27(5), 2681\u20132690 (2021)","journal-title":"IEEE Trans. Vis. Comput. Graph. (TVCG)"},{"doi-asserted-by":"crossref","unstructured":"Hu, Z., Bulling, A., Li, S., Wang, G.: EHTask: recognizing user tasks from eye and head movements in immersive virtual reality. IEEE Trans. Vis. Comput. Graph. (TVCG) (2022)","key":"35_CR28","DOI":"10.1109\/TVCG.2021.3138902"},{"issue":"5","key":"35_CR29","doi-asserted-by":"publisher","first-page":"1902","DOI":"10.1109\/TVCG.2020.2973473","volume":"26","author":"Z Hu","year":"2020","unstructured":"Hu, Z., Li, S., Zhang, C., Yi, K., Wang, G., Manocha, D.: DGaze: CNN-based gaze prediction in dynamic scenes. IEEE Trans. Vis. Comput. Graph. (TVCG) 26(5), 1902\u20131911 (2020)","journal-title":"IEEE Trans. Vis. Comput. Graph. (TVCG)"},{"issue":"5","key":"35_CR30","doi-asserted-by":"publisher","first-page":"2002","DOI":"10.1109\/TVCG.2019.2899187","volume":"25","author":"Z Hu","year":"2019","unstructured":"Hu, Z., Zhang, C., Li, S., Wang, G., Manocha, D.: SGaze: a data-driven eye-head coordination model for realtime gaze prediction. IEEE Trans. Vis. Comput. Graph. (TVCG) 25(5), 2002\u20132010 (2019)","journal-title":"IEEE Trans. Vis. Comput. Graph. (TVCG)"},{"key":"35_CR31","doi-asserted-by":"publisher","first-page":"7795","DOI":"10.1109\/TIP.2020.3007841","volume":"29","author":"Y Huang","year":"2020","unstructured":"Huang, Y., Cai, M., Li, Z., Lu, F., Sato, Y.: Mutual context network for jointly estimating egocentric gaze and action. IEEE Trans. Image Process. (TIP) 29, 7795\u20137806 (2020)","journal-title":"IEEE Trans. Image Process. (TIP)"},{"issue":"10\u201312","key":"35_CR32","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1016\/S0042-6989(99)00163-7","volume":"40","author":"L Itti","year":"2000","unstructured":"Itti, L., Koch, C.: A saliency-based search mechanism for overt and covert shifts of visual attention. Vision Res. 40(10\u201312), 1489\u20131506 (2000)","journal-title":"Vision Res."},{"key":"35_CR33","doi-asserted-by":"publisher","first-page":"103887","DOI":"10.1016\/j.imavis.2020.103887","volume":"95","author":"S Jia","year":"2020","unstructured":"Jia, S., Bruce, N.D.B.: EML-NET: an expandable multi-layer network for saliency prediction. Image Vision Comput. 95, 103887 (2020)","journal-title":"Image Vision Comput."},{"doi-asserted-by":"crossref","unstructured":"Jiang, M., Huang, S., Duan, J., Zhao, Q.: SALICON: saliency in context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1072\u20131080 (2015)","key":"35_CR34","DOI":"10.1109\/CVPR.2015.7298710"},{"unstructured":"Kanter, D.: Graphics processing requirements for enabling immersive vr. In: AMD White Paper, pp. 1\u201312 (2015)","key":"35_CR35"},{"unstructured":"Kastrati, A., Plomecka, M.B., Pascual, D., Wolf, L., Gillioz, V., Wattenhofer, R., Langer, N.: EEGEyeNet: a simultaneous electroencephalography and eye-tracking dataset and benchmark for eye movement prediction. In: Proceedings of the Neural Information Processing Systems (NIPS) Track on Datasets and Benchmarks (2021)","key":"35_CR36"},{"unstructured":"Kazemi, S.M., et al.: Time2vec: learning a vector representation of time. arXiv preprint arXiv:1907.05321 (2019)","key":"35_CR37"},{"doi-asserted-by":"crossref","unstructured":"Khan, S., Naseer, M., Hayat, M., Zamir, S.W., Khan, F.S., Shah, M.: Transformers in vision: a survey. ACM Comput. Surv. (2021)","key":"35_CR38","DOI":"10.1145\/3505244"},{"issue":"2","key":"35_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3361330","volume":"39","author":"R Konrad","year":"2020","unstructured":"Konrad, R., Angelopoulos, A., Wetzstein, G.: Gaze-contingent ocular parallax rendering for virtual reality. ACM Trans. Graph. (TOG) 39(2), 1\u201312 (2020)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"1","key":"35_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-59251-5","volume":"10","author":"R Kothari","year":"2020","unstructured":"Kothari, R., Yang, Z., Kanan, C., Bailey, R., Pelz, J.B., Diaz, G.J.: Gaze-in-wild: a dataset for studying eye and head coordination in everyday activities. Sci. Rep. 10(1), 1\u201318 (2020)","journal-title":"Sci. Rep."},{"doi-asserted-by":"crossref","unstructured":"Koulieris, G.A., Drettakis, G., Cunningham, D., Mania, K.: Gaze prediction using machine learning for dynamic stereo manipulation in games. In: IEEE Virtual Reality, pp. 113\u2013120. IEEE (2016)","key":"35_CR41","DOI":"10.1109\/VR.2016.7504694"},{"issue":"4","key":"35_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3197517.3201335","volume":"37","author":"E Langbehn","year":"2018","unstructured":"Langbehn, E., Steinicke, F., Lappe, M., Welch, G.F., Bruder, G.: In the blink of an eye: leveraging blink-induced suppression for imperceptible position and orientation redirection in virtual reality. ACM Trans. Graph. (TOG) 37(4), 1\u201311 (2018)","journal-title":"ACM Trans. Graph. (TOG)"},{"doi-asserted-by":"crossref","unstructured":"Li, R., et al.: Optical gaze tracking with spatially-sparse single-pixel detectors. In: IEEE International Symposium on Mixed and Augmented Reality (ISMAR), pp. 117\u2013126. IEEE (2020)","key":"35_CR43","DOI":"10.1109\/ISMAR50242.2020.00033"},{"doi-asserted-by":"crossref","unstructured":"Li, Y., Fathi, A., Rehg, J.M.: Learning to predict gaze in egocentric video. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 3216\u20133223 (2013)","key":"35_CR44","DOI":"10.1109\/ICCV.2013.399"},{"doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, M., Rehg, J.M.: In the eye of beholder: joint learning of gaze and actions in first person video. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 619\u2013635 (2018)","key":"35_CR45","DOI":"10.1007\/978-3-030-01228-1_38"},{"doi-asserted-by":"crossref","unstructured":"Linardos, A., K\u00fcmmerer, M., Press, O., Bethge, M.: DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 12919\u201312928 (2021)","key":"35_CR46","DOI":"10.1109\/ICCV48922.2021.01268"},{"unstructured":"Liu, Y., Sangineto, E., Bi, W., Sebe, N., Lepri, B., Nadai, M.: Efficient training of visual transformers with small datasets. Adv. Neural Inf. Process. Syst. (NeurIPS) 34 (2021)","key":"35_CR47"},{"unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)","key":"35_CR48"},{"issue":"2","key":"35_CR49","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/s12008-015-0259-2","volume":"11","author":"E Matsas","year":"2017","unstructured":"Matsas, E., Vosniakos, G.C.: Design of a virtual reality training system for human-robot collaboration in manufacturing tasks. Int. J. Interact. Design Manuf. (IJIDeM) 11(2), 139\u2013153 (2017)","journal-title":"Int. J. Interact. Design Manuf. (IJIDeM)"},{"doi-asserted-by":"crossref","unstructured":"Mazzeo, P.L., D\u2019Amico, D., Spagnolo, P., Distante, C.: Deep learning based eye gaze estimation and prediction. In: 2021 6th International Conference on Smart and Sustainable Technologies (SpliTech), pp. 1\u20136. IEEE (2021)","key":"35_CR50","DOI":"10.23919\/SpliTech52315.2021.9566413"},{"issue":"1","key":"35_CR51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3203199","volume":"1","author":"X Meng","year":"2018","unstructured":"Meng, X., Du, R., Zwicker, M., Varshney, A.: Kernel foveated rendering. Proc. ACM Comput. Graph. Interact. Tech. (PACMCGIT) 1(1), 1\u201320 (2018)","journal-title":"Proc. ACM Comput. Graph. Interact. Tech. (PACMCGIT)"},{"unstructured":"Murphy, H.A., Duchowski, A.T.: Gaze-contingent level of detail rendering. In: Eurographics 2001 - Short Presentations. Eurographics Association (2001)","key":"35_CR52"},{"issue":"1","key":"35_CR53","doi-asserted-by":"publisher","first-page":"486","DOI":"10.3390\/encyclopedia2010031","volume":"2","author":"S Mystakidis","year":"2022","unstructured":"Mystakidis, S.: Metaverse. Encyclopedia 2(1), 486\u2013497 (2022)","journal-title":"Encyclopedia"},{"doi-asserted-by":"crossref","unstructured":"Naas, S.A., Jiang, X., Sigg, S., Ji, Y.: Functional gaze prediction in egocentric video. In: Proceedings of the 18th International Conference on Advances in Mobile Computing & Multimedia (MoMM), pp. 40\u201347. ACM, New York (2020)","key":"35_CR54","DOI":"10.1145\/3428690.3429174"},{"unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on International Conference on Machine Learning (ICML). ACM, New York (2010)","key":"35_CR55"},{"key":"35_CR56","volume-title":"The Psychology of Attention","author":"HE Pashler","year":"1999","unstructured":"Pashler, H.E.: The Psychology of Attention. MIT Press, Cambridge (1999)"},{"issue":"6","key":"35_CR57","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2980179.2980246","volume":"35","author":"A Patney","year":"2016","unstructured":"Patney, A., et al.: Towards foveated rendering for gaze-tracked virtual reality. ACM Trans. Graph. (TOG) 35(6), 1\u201312 (2016)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"1","key":"35_CR58","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1109\/MSPEC.2016.7367470","volume":"53","author":"TS Perry","year":"2015","unstructured":"Perry, T.S.: Virtual reality goes social. IEEE Spectr. 53(1), 56\u201357 (2015)","journal-title":"IEEE Spectr."},{"doi-asserted-by":"crossref","unstructured":"Rolff, T., Steinicke, F., Frintrop, S.: When do saccades begin? prediction of saccades as a time-to-event problem. In: ACM Symposium on Eye Tracking Research and Applications, ETRA 2022. ACM, New York (2022)","key":"35_CR59","DOI":"10.1145\/3517031.3529627"},{"issue":"3","key":"35_CR60","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. Vision (IJCV) 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision (IJCV)"},{"key":"35_CR61","doi-asserted-by":"publisher","first-page":"57","DOI":"10.14746\/rrpr.2020.51.06","volume":"51","author":"M Rzeszewski","year":"2020","unstructured":"Rzeszewski, M., Evans, L.: Virtual place during quarantine-a curious case of vrchat. Rozw\u00f3j Regionalny i Polityka Regionalna 51, 57\u201375 (2020)","journal-title":"Rozw\u00f3j Regionalny i Polityka Regionalna"},{"doi-asserted-by":"publisher","unstructured":"Salvucci, D.D., Goldberg, J.H.: Identifying fixations and saccades in eye-tracking protocols. In: Proceedings of the 2000 Symposium on Eye Tracking Research & Applications, ETRA 2000, pp. 71\u201378. Association for Computing Machinery, New York (2000). https:\/\/doi.org\/10.1145\/355017.355028","key":"35_CR62","DOI":"10.1145\/355017.355028"},{"unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representations (ICLR) (2015)","key":"35_CR63"},{"issue":"4","key":"35_CR64","doi-asserted-by":"publisher","first-page":"1633","DOI":"10.1109\/TVCG.2018.2793599","volume":"24","author":"V Sitzmann","year":"2018","unstructured":"Sitzmann, V., et al.: Saliency in VR: how do people explore virtual environments? IEEE Trans. Vis. Comput. Graph. (TVCG) 24(4), 1633\u20131642 (2018)","journal-title":"IEEE Trans. Vis. Comput. Graph. (TVCG)"},{"issue":"1","key":"35_CR65","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"doi-asserted-by":"crossref","unstructured":"Stein, N., et al.: A comparison of eye tracking latencies among several commercial head-mounted displays. i-Perception 12(1), 1\u201316 (2021)","key":"35_CR66","DOI":"10.1177\/2041669520983338"},{"issue":"4","key":"35_CR67","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3197517.3201294","volume":"37","author":"Q Sun","year":"2018","unstructured":"Sun, Q., et al.: Towards virtual reality infinite walking: dynamic saccadic redirection. ACM Trans. Graph. (TOG) 37(4), 1\u201313 (2018)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"11","key":"35_CR68","doi-asserted-by":"publisher","first-page":"7573","DOI":"10.1109\/TCOMM.2019.2920594","volume":"67","author":"Y Sun","year":"2019","unstructured":"Sun, Y., Chen, Z., Tao, M., Liu, H.: Communications, caching, and computing for mobile virtual reality: modeling and tradeoff. IEEE Trans. Commun. 67(11), 7573\u20137586 (2019)","journal-title":"IEEE Trans. Commun."},{"issue":"1","key":"35_CR69","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/0010-0285(80)90005-5","volume":"12","author":"AM Treisman","year":"1980","unstructured":"Treisman, A.M., Gelade, G.: A feature-integration theory of attention. Cogn. Psychol. 12(1), 97\u2013136 (1980)","journal-title":"Cogn. Psychol."},{"unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (NIPS), vol. 30. Curran Associates, Inc. (2017)","key":"35_CR70"},{"doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: Gaze prediction in dynamic 360 immersive videos. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5333\u20135342 (2018)","key":"35_CR71","DOI":"10.1109\/CVPR.2018.00559"},{"doi-asserted-by":"crossref","unstructured":"Yang, C., Zhang, L., Lu, H., Ruan, X., Yang, M.H.: Saliency detection via graph-based manifold ranking. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3166\u20133173. IEEE (2013)","key":"35_CR72","DOI":"10.1109\/CVPR.2013.407"},{"key":"35_CR73","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-5379-7","volume-title":"Eye Movements and Vision","author":"AL Yarbus","year":"2013","unstructured":"Yarbus, A.L.: Eye Movements and Vision. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-1-4899-5379-7"},{"doi-asserted-by":"crossref","unstructured":"Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8697\u20138710 (2018)","key":"35_CR74","DOI":"10.1109\/CVPR.2018.00907"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-16788-1_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,23]],"date-time":"2022-09-23T01:03:45Z","timestamp":1663895025000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16788-1_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031167874","9783031167881"],"references-count":74,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16788-1_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"20 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAGM GCPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"DAGM German Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Konstanz","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"44","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dagm2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/gcpr-vmv-2022.uni-konstanz.de\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"78","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"37","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"47% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}