{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T21:58:24Z","timestamp":1742939904095,"version":"3.40.3"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781858"},{"type":"electronic","value":"9783031781865"}],"license":[{"start":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T00:00:00Z","timestamp":1732924800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T00:00:00Z","timestamp":1732924800000},"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\/978-3-031-78186-5_15","type":"book-chapter","created":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T14:15:28Z","timestamp":1732889728000},"page":"221-237","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic Inference and\u00a0Top-down Attention in\u00a0a\u00a0Hierarchical Classification Network"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4146-7953","authenticated-orcid":false,"given":"Andr\u00e9 Peter","family":"Kelm","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Niels","family":"Hannemann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bruno","family":"Heberle","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lucas","family":"Schmidt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9038-3196","authenticated-orcid":false,"given":"Tim","family":"Rolff","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2490-7029","authenticated-orcid":false,"given":"Christian","family":"Wilms","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3639-266X","authenticated-orcid":false,"given":"Ehsan","family":"Yaghoubi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9475-3593","authenticated-orcid":false,"given":"Simone","family":"Frintrop","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,30]]},"reference":[{"key":"15_CR1","unstructured":"Arons, B.: A review of the cocktail party effect. J. Am. Voice I\/O Soc. 12(7) (1992)"},{"key":"15_CR2","unstructured":"Aytekin, C.: Neural networks are decision trees. ArXiv. arXiv:2210.05189 (2022)"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Banik, S., Lauri, M., Knoll, A., Frintrop, S.: Object localization with attribute preference based on top-down attention. In: Computer Vision Systems. Springer (2021)","DOI":"10.1007\/978-3-030-87156-7_3"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Budiharto, W., Gunawan, A.A.S., Suroso, J.S., Chowanda, A., Patrik, A., Utama, G.: Fast object detection for quadcopter drone using deep learning. In: 2018 3rd International Conference on Computer and Communication Systems (ICCCS) (2018)","DOI":"10.1109\/CCOMS.2018.8463284"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Cai, H., et al.: Enable deep learning on mobile devices: methods, systems, and applications. ACM Trans. Des. Autom. Electron. Syst. 27(3) (2022)","DOI":"10.1145\/3486618"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., Spence, C.: When hearing the bark helps to identify the dog: semantically-congruent sounds modulate the identification of masked pictures. Cognition 114(3) (2009)","DOI":"10.1016\/j.cognition.2009.10.012"},{"key":"15_CR7","unstructured":"Cheng, H., Zhang, M., Shi, J.Q.: A survey on deep neural network pruning-taxonomy, comparison, analysis, and recommendations (2023)"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: Randaugment: practical automated data augmentation with a reduced search space. In: IEEE\/CVF CVPRW (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"15_CR9","unstructured":"Dai, Z., Liu, H., Le, Q.V., Tan, M.: Coatnet: marrying convolution and attention for all data sizes. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) NeurIPS, vol.\u00a034, pp. 3965\u20133977. Curran Associates, Inc. (2021)"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Davis, E.T., Palmer, J.: Visual search and attention: an overview. Spatial Vision (2004)","DOI":"10.1163\/1568568041920168"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: IEEE CVF CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Desislavov, R., Mart\u00ednez-Plumed, F., Hern\u00e1ndez-Orallo, J.: Trends in ai inference energy consumption: beyond the performance-vs-parameter laws of deep learning. Sustainable Comput. Inform. Syst. 38 (2023)","DOI":"10.1016\/j.suscom.2023.100857"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Fang, Y., Wang, W., Xie, B., Sun, Q., Wu, L., Wang, X., Huang, T., Wang, X., Cao, Y.: Eva: Exploring the limits of masked visual representation learning at scale. In: 2023 IEEE\/CVF CVPR. IEEE Computer Society (2023)","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"15_CR14","unstructured":"Figotin, I.: ImageNet 1000 (mini) (2020), available at Kaggle: https:\/\/www.kaggle.com\/datasets\/ifigotin\/imagenetmini-1000"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Frintrop, S., Backer, G., Rome, E.: Goal-directed search with a top-down modulated computational attention system. In: Pattern Recognition: 27th DAGM Symposium. Proceedings 27. Springer (2005)","DOI":"10.1007\/11550518_15"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Frintrop, S., Rome, E., Christensen, H.I.: Computational visual attention systems and their cognitive foundations: a survey. ACM Trans. Appl. Perception (TAP) 7(1) (2010)","DOI":"10.1145\/1658349.1658355"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Fu, D., et al.: What can computational models learn from human selective attention? a review from an audiovisual unimodal and crossmodal perspective. Front. Integrative Neurosci. 14 (2020)","DOI":"10.3389\/fnint.2020.00010"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Han, Y., Huang, G., Song, S., Yang, L., Wang, H., Wang, Y.: Dynamic neural networks: a survey. IEEE TPAMI 44(11) (2022)","DOI":"10.1109\/TPAMI.2021.3117837"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"15_CR20","unstructured":"Howard, J.: Imagewang. https:\/\/github.com\/fastai\/imagenette\/"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Iordanescu, L., Grabowecky, M., Franconeri, S., Theeuwes, J., Suzuki, S.: Characteristic sounds make you look at target objects more quickly. Attention Perception Psychophys. 72(7) (2010)","DOI":"10.3758\/APP.72.7.1736"},{"key":"15_CR22","unstructured":"kaggle: Imagenet100. https:\/\/www.kaggle.com\/datasets\/ambityga\/imagenet100. Accessed 17 Nov 2023"},{"key":"15_CR23","unstructured":"Krizhevsky, A., Nair, V., Hinton, G.: Cifar-10 (canad. inst. for adv. res.)"},{"key":"15_CR24","unstructured":"Krizhevsky, A., Nair, V., Hinton, G.: Cifar-100 (canad. inst. for adv. res.)"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Kuo, T.Y., Liao, Y., Li, K., Hong, B., Hu, X.: Inferring mechanisms of auditory attentional modulation with deep neural networks. Neural Comput. 34(11) (2022)","DOI":"10.1162\/neco_a_01537"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Lev-Ari, T., Beeri, H., Gutfreund, Y.: The ecological view of selective attention. Front. Integrative Neurosci. 16 (2022)","DOI":"10.3389\/fnint.2022.856207"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Liu, K.Y., et al.: Denoised internal models: a brain-inspired autoencoder against adversarial attacks. Mach. Intell. Res. 19(5) (2022)","DOI":"10.1007\/s11633-022-1375-7"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., Hu, H.: Video swin transformer. In: 2022 IEEE\/CVF CVPR. IEEE Computer Society (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Marian, V., Hayakawa, S., Schroeder, S.R.: Cross-modal interaction between auditory and visual input impacts memory retrieval. Front. Neurosci. 15 (2021)","DOI":"10.3389\/fnins.2021.661477"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Mi, J.X., Li, N., Huang, K.Y., Li, W., Zhou, L.: Hierarchical neural network with efficient selection inference. Neural Netw. 161 (2023)","DOI":"10.1016\/j.neunet.2023.02.015"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Navalpakkam, V., Itti, L.: Modeling the influence of task on attention. Vis. Res. 45(2) (2005)","DOI":"10.1016\/j.visres.2004.07.042"},{"key":"15_CR32","unstructured":"OpenAI: Chatgpt. https:\/\/openai.com\/ (2023\/24)"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Pham, H., Dai, Z., Xie, Q., Le, Q.V.: Meta pseudo labels. In: CVPR, pp. 11552\u201311563 (2021)","DOI":"10.1109\/CVPR46437.2021.01139"},{"key":"15_CR34","unstructured":"Ridnik, T., Baruch, E.B., Noy, A., Zelnik, L.: Imagenet-21k pretraining for the masses. In: Vanschoren, J., Yeung, S. (eds.) Proceedings of the NeurIPS Datasets and Benchmarks (2021)"},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE ICCV (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"15_CR36","unstructured":"Shazeer, N., et al.: Outrageously large neural networks: the sparsely-gated mixture-of-experts layer. In: ICLR. OpenReview.net (2017)"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Tanny, S.M.: On some numbers related to the bell numbers. Canadian Mathematical Bulletin 17(5) (1975)","DOI":"10.4153\/CMB-1974-132-8"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Theeuwes, J.: Top\u2013down and bottom\u2013up control of visual selection. Acta psychologica 135(2) (2010)","DOI":"10.1016\/j.actpsy.2010.02.006"},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Tonegawa, S., Liu, X., Ramirez, S., Redondo, R.: Memory engram cells have come of age. Neuron 87(5) (2015)","DOI":"10.1016\/j.neuron.2015.08.002"},{"key":"15_CR40","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS, vol.\u00a030. Curran Associates, Inc. (2017)"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Sp-net: slowly progressing dynamic inference networks. In: ECCV. Springer Nature Switzerland (2022)","DOI":"10.1007\/978-3-031-20083-0_14"},{"key":"15_CR42","doi-asserted-by":"crossref","unstructured":"Wang, J., Cao, B., Yu, P., Sun, L., Bao, W., Zhu, X.: Deep learning towards mobile applications. In: 2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS) (2018)","DOI":"10.1109\/ICDCS.2018.00139"},{"key":"15_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, J., Zhang, W., Zhan, Y., Guo, S., Zheng, Q., Wang, X.: A survey on deploying mobile deep learning applications: a systemic and technical perspective. Digital Commun. Networks 8(1) (2022)","DOI":"10.1016\/j.dcan.2021.06.001"},{"key":"15_CR44","unstructured":"Wightman, R.: Pytorch image models (2019). https:\/\/github.com\/rwightman\/pytorch-image-models"},{"key":"15_CR45","doi-asserted-by":"crossref","unstructured":"Wolfe, J.M.: Guided search 6.0: an updated model of visual search. Psychonomic Bull. Rev. 28(4) (2021)","DOI":"10.3758\/s13423-020-01859-9"},{"key":"15_CR46","doi-asserted-by":"crossref","unstructured":"Woo, S., et al.: Convnext v2: co-designing and scaling convnets with masked autoencoders. In: IEEE\/CVF CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"15_CR47","doi-asserted-by":"crossref","unstructured":"Xie, H., Liu, Y., Zhu, Y., Ding, X., Yang, Y., Guan, J.S.: In vivo imaging of immediate early gene expression reveals layer-specific memory traces in the mammalian brain. Proceedings of the National Academy of Sciences 111(7) (2014)","DOI":"10.1073\/pnas.1316808111"},{"key":"15_CR48","doi-asserted-by":"crossref","unstructured":"Xue, M., Song, J., Sun, L., Song, M.: Tree-like branching network for multi-class classification. In: Intelligent Computing & Optimization. Springer (2022)","DOI":"10.1007\/978-3-030-93247-3_18"},{"key":"15_CR49","doi-asserted-by":"crossref","unstructured":"Yan, Z., et al.: Hd-cnn: hierarchical deep convolutional neural networks for large scale visual recognition. In: IEEE ICCV (2015)","DOI":"10.1109\/ICCV.2015.314"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78186-5_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T15:13:20Z","timestamp":1732893200000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78186-5_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,30]]},"ISBN":["9783031781858","9783031781865"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78186-5_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,30]]},"assertion":[{"value":"30 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}