{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T04:59:22Z","timestamp":1776488362423,"version":"3.51.2"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"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":["Multimedia Systems"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s00530-025-02143-3","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T03:26:45Z","timestamp":1770089205000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DPFA-net: a lightweight hybrid neural network with dual path feature aggregation for food image recognition"],"prefix":"10.1007","volume":"32","author":[{"given":"Xiangyi","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Wenli","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yingnan","family":"Sheng","sequence":"additional","affiliation":[]},{"given":"Congrui","family":"Lv","sequence":"additional","affiliation":[]},{"given":"Guorui","family":"Sheng","sequence":"additional","affiliation":[]},{"given":"Weiqing","family":"Min","sequence":"additional","affiliation":[]},{"given":"Shuqiang","family":"Jiang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,3]]},"reference":[{"issue":"14","key":"2143_CR1","doi-asserted-by":"publisher","first-page":"5263","DOI":"10.1007\/s11042-015-2685-2","volume":"74","author":"Y Kawano","year":"2015","unstructured":"Kawano, Y., Yanai, K.: Foodcam: a real-time food recognition system on a smartphone. Multimedia Tools Appl 74(14), 5263\u20135287 (2015). https:\/\/doi.org\/10.1007\/s11042-015-2685-2","journal-title":"Multimedia Tools Appl"},{"key":"2143_CR2","doi-asserted-by":"publisher","unstructured":"Ishino, A., Yamakata, Y., Karasawa, H., Aizawa, K.: RecipeLog: Recipe authoring app for accurate food recording. In: Proceedings of the 29th ACM International Conference on Multimedia, 2798\u20132800, (2021). https:\/\/doi.org\/10.1145\/3474085.3478563","DOI":"10.1145\/3474085.3478563"},{"issue":"8","key":"2143_CR3","doi-asserted-by":"publisher","first-page":"9932","DOI":"10.1109\/TPAMI.2023.3267030","volume":"45","author":"W Min","year":"2023","unstructured":"Min, W., Wang, Z., Liu, Y., Luo, M., Kang, L., Wei, X., Wei, X., Jiang, S.: Large scale visual food recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(8), 9932\u20139949 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3267030","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2143_CR4","doi-asserted-by":"publisher","unstructured":"Rostami, A., Nagesh, N., Rahmani, A., Jain, R.: World food atlas for food navigation. In: Proceedings of the 7th International Workshop on Multimedia Assisted Dietary Management, 39\u201347, (2022). https:\/\/doi.org\/10.1145\/3552484.3555748","DOI":"10.1145\/3552484.3555748"},{"key":"2143_CR5","doi-asserted-by":"publisher","unstructured":"Rostami, A., Pandey, V., Nag, N., Wang, V., Jain, R.: Personal food model. In: Proceedings of the 28th ACM International Conference on Multimedia, 4416\u20134424 (2020). https:\/\/doi.org\/10.1145\/3394171.3413769","DOI":"10.1145\/3394171.3413769"},{"key":"2143_CR6","doi-asserted-by":"publisher","unstructured":"Nakamoto, K., Amano, S., Karasawa, H., Yamakata, Y., Aizawa, K.: Prediction of mental state from food images. In: Proceedings of the 1st International Workshop on Multimedia for Cooking, Eating, and related APPlications, 21\u201328 (2022). https:\/\/doi.org\/10.1145\/3552485.3554937","DOI":"10.1145\/3552485.3554937"},{"issue":"7","key":"2143_CR7","doi-asserted-by":"publisher","first-page":"1926","DOI":"10.1109\/JBHI.2020.2972068","volume":"24","author":"FPW Lo","year":"2020","unstructured":"Lo, F.P.W., Sun, Y., Qiu, J., Lo, B.: Image-based food classification and volume estimation for dietary assessment: a review. IEEE J. Biomed. Health Inform. 24(7), 1926\u20131939 (2020). https:\/\/doi.org\/10.1109\/JBHI.2020.2972068","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"2143_CR8","doi-asserted-by":"publisher","unstructured":"Yamakata, Y., Ishino, A., Sunto, A., Amano, S., Aizawa, K.: Recipe-oriented food logging for nutritional management. In: Proceedings of the 30th ACM International Conference on Multimedia, 6898\u20136904 (2022). https:\/\/doi.org\/10.1145\/3503161.3547957","DOI":"10.1145\/3503161.3547957"},{"key":"2143_CR9","doi-asserted-by":"publisher","unstructured":"R\u00f3denas, J., Nagarajan, B., Bola\u00f1os, M., Radeva, P.: Learning multi-subset of classes for fine-grained food recognition. In: Proceedings of the 7th International Workshop on Multimedia Assisted Dietary Management, 17\u201326 (2022). https:\/\/doi.org\/10.1145\/3552484.3555754","DOI":"10.1145\/3552484.3555754"},{"key":"2143_CR10","doi-asserted-by":"publisher","unstructured":"Kawano, Y., Yanai, K.: Real-time mobile food recognition system. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 1\u20137 (2013). https:\/\/doi.org\/10.1109\/CVPRW.2013.5","DOI":"10.1109\/CVPRW.2013.5"},{"issue":"14","key":"2143_CR11","doi-asserted-by":"publisher","first-page":"5263","DOI":"10.1007\/s11042-014-2000-8","volume":"74","author":"Y Kawano","year":"2015","unstructured":"Kawano, Y., Yanai, K.: Foodcam: a real-time food recognition system on a smartphone. Multimedia Tools Appl 74(14), 5263\u20135287 (2015). https:\/\/doi.org\/10.1007\/s11042-014-2000-8","journal-title":"Multimedia Tools Appl"},{"issue":"3s","key":"2143_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3052432","volume":"13","author":"P Pouladzadeh","year":"2017","unstructured":"Pouladzadeh, P., Shirmohammadi, S.: Mobile multi-food recognition using deep learning. ACM Trans Multimedia Comput Commun Appl 13(3s), 1\u201321 (2017). https:\/\/doi.org\/10.1145\/3052432","journal-title":"ACM Trans Multimedia Comput Commun Appl"},{"issue":"13","key":"2143_CR13","doi-asserted-by":"publisher","first-page":"6654","DOI":"10.1002\/jsfa.12574","volume":"103","author":"W Nie","year":"2023","unstructured":"Nie, W., Liu, C.: Assessing food safety risks based on a geospatial analysis: toward a cross-regional food safety management. J. Sci. Food Agric. 103(13), 6654\u20136663 (2023). https:\/\/doi.org\/10.1002\/jsfa.12574","journal-title":"J. Sci. Food Agric."},{"key":"2143_CR14","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1109\/TIP.2019.2942344","volume":"29","author":"S Jiang","year":"2019","unstructured":"Jiang, S., Yan, C., Tang, X., et al.: Multi-scale multi-view deep feature aggregation for food recognition. IEEE Trans. Image Process. 29, 265\u2013276 (2019). https:\/\/doi.org\/10.1109\/TIP.2019.2942344","journal-title":"IEEE Trans. Image Process."},{"key":"2143_CR15","doi-asserted-by":"publisher","unstructured":"Kagaya, H., Aizawa, K., Ogawa, M.: Food detection and recognition using convolutional neural network. In: Proceedings of the 22nd ACM International Conference on Multimedia, 1085\u20131088 (2014). https:\/\/doi.org\/10.1145\/2647868.2654932","DOI":"10.1145\/2647868.2654932"},{"key":"2143_CR16","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint (2020) arXiv:2010.11929"},{"key":"2143_CR17","unstructured":"Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint (2023) arXiv:2312.00752"},{"key":"2143_CR18","doi-asserted-by":"publisher","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, 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"2143_CR19","doi-asserted-by":"publisher","unstructured":"Ma, N., Zhang, X., Zheng, H.-T., Sun, J.: Shufflenet v2: Practical guidelines for efficient CNN architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), 116\u2013131 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_10","DOI":"10.1007\/978-3-030-01246-5_10"},{"key":"2143_CR20","doi-asserted-by":"publisher","unstructured":"Mehta, S., Rastegari, M., Shapiro, L., Hajishirzi, H.: ESPNetv2: A light-weight, power efficient, and general purpose convolutional neural network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 9190\u20139200 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00938","DOI":"10.1109\/CVPR.2019.00938"},{"key":"2143_CR21","unstructured":"Tan, M., Le, Q.: EfficientNet: Rethinking model scaling for convolutional neural networks. In: Proceedings of the International Conference on Machine Learning, 6105\u20136114 (2019). PMLR. http:\/\/proceedings.mlr.press\/v97\/tan19a.html"},{"key":"2143_CR22","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1145\/3504999","volume":"3","author":"B Saeta","year":"2021","unstructured":"Saeta, B., Shabalin, D.: Swift for tensorFlow: a portable, flexible platform for deep learning. Proc Mach Learn Syst 3, 240\u2013254 (2021). https:\/\/doi.org\/10.1145\/3504999","journal-title":"Proc Mach Learn Syst"},{"key":"2143_CR23","doi-asserted-by":"publisher","unstructured":"Qin, D., Leichner, C., Delakis, M., Fornoni, M., Luo, S., Yang, F., Wang, W., Banbury, C., Ye, C., Akin, B., et al.: MobileNetV4: Universal models for the mobile ecosystem. In: Proceedings of the European Conference on Computer Vision, 78\u201396 (2024). Springer. https:\/\/doi.org\/10.1007\/978-3-031-30000-1_5","DOI":"10.1007\/978-3-031-30000-1_5"},{"key":"2143_CR24","doi-asserted-by":"publisher","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 10012\u201310022 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00984","DOI":"10.1109\/ICCV48922.2021.00984"},{"key":"2143_CR25","first-page":"12934","volume":"35","author":"Y Li","year":"2022","unstructured":"Li, Y., Yuan, G., Wen, Y., Hu, J., Evangelidis, G., Tulyakov, S., Wang, Y., Ren, J.: Efficientformer: vision transformers at MobileNet speed. Adv. Neural. Inf. Process. Syst. 35, 12934\u201312949 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2143_CR26","unstructured":"Huang, T., Huang, L., You, S., Wang, F., Qian, C., Xu, C.: LightVit: Towards light-weight convolution-free vision transformers. arXiv preprint (2022) arXiv:2207.05557"},{"key":"2143_CR27","doi-asserted-by":"publisher","unstructured":"Liu, X., Peng, H., Zheng, N., Yang, Y., Hu, H., Yuan, Y.: EfficientViT: Memory efficient vision transformer with cascaded group attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 14420\u201314430 (2023). https:\/\/doi.org\/10.1109\/CVPR52688.2023.01419","DOI":"10.1109\/CVPR52688.2023.01419"},{"key":"2143_CR28","doi-asserted-by":"publisher","unstructured":"Zhang, J., Peng, H., Wu, K., Liu, M., Xiao, B., Fu, J., Yuan, L.: MiniViT: Compressing vision transformers with weight multiplexing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 12145\u201312154 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01179","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"2143_CR29","doi-asserted-by":"publisher","unstructured":"Wu, K., Zhang, J., Peng, H., Liu, M., Xiao, B., Fu, J., Yuan, L.: TinyViT: Fast pretraining distillation for small vision transformers. In: Proceedings of the European Conference on Computer Vision, 68\u201385 (2022). Springer. https:\/\/doi.org\/10.1007\/978-3-031-19774-9_5","DOI":"10.1007\/978-3-031-19774-9_5"},{"key":"2143_CR30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.1234567","author":"G Xu","year":"2024","unstructured":"Xu, G., Jia, W., Wu, T., Chen, L., Gao, G.: HaFormer: unleashing the power of hierarchy-aware features for lightweight semantic segmentation. IEEE Trans. Image Process. (2024). https:\/\/doi.org\/10.1109\/TIP.2024.1234567","journal-title":"IEEE Trans. Image Process."},{"key":"2143_CR31","doi-asserted-by":"publisher","unstructured":"Chen, Y., Dai, X., Chen, D., Liu, M., Dong, X., Yuan, L., Liu, Z.: Mobile-Former: Bridging MobileNet and Transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 5270\u20135279 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00519","DOI":"10.1109\/CVPR52688.2022.00519"},{"key":"2143_CR32","doi-asserted-by":"publisher","unstructured":"Guo, J., Han, K., Wu, H., Tang, Y., Chen, X., Wang, Y., Xu, C.: CMT: Convolutional neural networks meet vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 12175\u201312185 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01210","DOI":"10.1109\/CVPR52688.2022.01210"},{"key":"2143_CR33","doi-asserted-by":"publisher","unstructured":"Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., Zhang, L.: CvT: Introducing convolutions to vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 22\u201331 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00010","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"2143_CR34","doi-asserted-by":"publisher","unstructured":"Srinivas, A., Lin, T.-Y., Parmar, N., Shlens, J., Abbeel, P., Vaswani, A.: Bottleneck transformers for visual recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 16519\u201316529 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01637","DOI":"10.1109\/CVPR46437.2021.01637"},{"key":"2143_CR35","unstructured":"Li, J., Xia, X., Li, W., Li, H., Wang, X., Xiao, X., Wang, R., Zheng, M., Pan, X.: Next-ViT: Next generation vision transformer for efficient deployment in realistic industrial scenarios. arXiv preprint (2022) arXiv:2207.05501"},{"key":"2143_CR36","doi-asserted-by":"publisher","unstructured":"Pan, J., Bulat, A., Tan, F., Zhu, X., Dudziak, L., Li, H., Tzimiropoulos, G., Martinez, B.: EdgeViTs: Competing light-weight CNNs on mobile devices with vision transformers. In: Proceedings of the European Conference on Computer Vision, 294\u2013311 (2022). Springer. https:\/\/doi.org\/10.1007\/978-3-031-19775-6_17","DOI":"10.1007\/978-3-031-19775-6_17"},{"key":"2143_CR37","doi-asserted-by":"publisher","unstructured":"Mehta, S., Rastegari, M.: MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer. arXiv preprint arXiv:2110.02178. https:\/\/doi.org\/10.48550\/arXiv.2110.02178 (2021)","DOI":"10.48550\/arXiv.2110.02178"},{"key":"2143_CR38","doi-asserted-by":"publisher","unstructured":"Mehta, S., Rastegari, M.: Separable self-attention for mobile vision transformers. arXiv preprint arXiv:2206.02680. https:\/\/doi.org\/10.48550\/arXiv.2206.02680 (2022)","DOI":"10.48550\/arXiv.2206.02680"},{"key":"2143_CR39","doi-asserted-by":"publisher","unstructured":"Liu, X., Zhang, C., Zhang, L.: Vision Mamba: A comprehensive survey and taxonomy. arXiv preprint arXiv:2405.04404. https:\/\/doi.org\/10.48550\/arXiv.2405.04404 (2024)","DOI":"10.48550\/arXiv.2405.04404"},{"key":"2143_CR40","first-page":"103031","volume":"37","author":"Y Liu","year":"2024","unstructured":"Liu, Y., Tian, Y., Zhao, Y., Yu, H., Xie, L., Wang, Y., Ye, Q., Jiao, J., Liu, Y.: Vmamba: visual state space model. Adv. Neural. Inf. Process. Syst. 37, 103031\u2013103063 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2143_CR41","doi-asserted-by":"publisher","unstructured":"Hatamizadeh, A., Kautz, J.: MambaVision: A hybrid Mamba\u2011Transformer vision backbone. In: Proceedings of the Computer Vision and Pattern Recognition Conference, 25261\u201325270 (2025). https:\/\/doi.org\/10.48550\/arXiv.2407.08083","DOI":"10.48550\/arXiv.2407.08083"},{"key":"2143_CR42","doi-asserted-by":"publisher","unstructured":"Yu, W., Wang, X.: MambaOut: Do we really need Mamba for vision? In: Proceedings of the Computer Vision and Pattern Recognition Conference, 4484\u20134496 (2025). https:\/\/doi.org\/10.1109\/CVPR52525.2025.00448","DOI":"10.1109\/CVPR52525.2025.00448"},{"key":"2143_CR43","doi-asserted-by":"publisher","unstructured":"Han, D., Wang, Z., Xia, Z., Han, Y., Pu, Y., Ge, C., Song, J., Song, S., Zheng, B., Huang, G.: Demystify Mamba in vision: A linear attention perspective. Adv Neural Inf Process Syst 37:127181\u2013127203 (2024). https:\/\/doi.org\/10.48550\/arXiv.2403.09374","DOI":"10.48550\/arXiv.2403.09374"},{"issue":"2","key":"2143_CR44","doi-asserted-by":"publisher","first-page":"200","DOI":"10.3390\/nu16020200","volume":"16","author":"G Sheng","year":"2024","unstructured":"Sheng, G., Min, W., Zhu, X., Xu, L., Sun, Q., Yang, Y., Wang, L., Jiang, S.: A lightweight hybrid model with location-preserving ViT for efficient food recognition. Nutrients 16(2), 200 (2024). https:\/\/doi.org\/10.3390\/nu16020200","journal-title":"Nutrients"},{"issue":"12","key":"2143_CR45","doi-asserted-by":"publisher","first-page":"11465","DOI":"10.1002\/int.22995","volume":"37","author":"G Sheng","year":"2022","unstructured":"Sheng, G., Sun, S., Liu, C., Yang, Y.: Food recognition via an efficient neural network with transformer grouping. Int. J. Intell. Syst. 37(12), 11465\u201311481 (2022). https:\/\/doi.org\/10.1002\/int.22995","journal-title":"Int. J. Intell. Syst."},{"issue":"10","key":"2143_CR46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3609266","volume":"20","author":"Y Yang","year":"2024","unstructured":"Yang, Y., Min, W., Song, J., Sheng, G., Wang, L., Jiang, S.: Lightweight food recognition via aggregation block and feature encoding. ACM Trans Multimedia Comput Commun Appl 20(10), 1\u201325 (2024). https:\/\/doi.org\/10.1145\/3609266","journal-title":"ACM Trans Multimedia Comput Commun Appl"},{"key":"2143_CR47","doi-asserted-by":"publisher","unstructured":"Bossard, L., Guillaumin, M., Van Gool, L.: Food-101\u2014mining discriminative components with random forests. In: European Conference on Computer Vision, 446\u2013461 (2014). https:\/\/doi.org\/10.1007\/978-3-319-10593-2_28","DOI":"10.1007\/978-3-319-10593-2_28"},{"key":"2143_CR48","doi-asserted-by":"publisher","unstructured":"Klasson, M., Zhang, C., Kjellstr\u00f6m, H.: A hierarchical grocery store image dataset with visual and semantic labels. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), 491\u2013500 (2019).https:\/\/doi.org\/10.1109\/WACV.2019.00057","DOI":"10.1109\/WACV.2019.00057"},{"key":"2143_CR49","doi-asserted-by":"publisher","unstructured":"Kawano, Y., Yanai, K.: Foodcam-256: a large-scale real-time mobile food recognition system employing high-dimensional features and compression of classifier weights. In: Proceedings of the 22nd ACM International Conference on Multimedia, 761\u2013762 (2014). https:\/\/doi.org\/10.1145\/2647868.2654943","DOI":"10.1145\/2647868.2654943"},{"issue":"9","key":"2143_CR50","doi-asserted-by":"publisher","first-page":"7871","DOI":"10.1109\/TGRS.2020.2982740","volume":"59","author":"R Liu","year":"2020","unstructured":"Liu, R., Mi, L., Chen, Z.: AFNet: adaptive fusion network for remote sensing image semantic segmentation. IEEE Trans. Geosci. Remote Sens. 59(9), 7871\u20137886 (2020). https:\/\/doi.org\/10.1109\/TGRS.2020.2982740","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"2143_CR51","doi-asserted-by":"publisher","unstructured":"Tang, Y., Han, K., Guo, J., Xu, C., Xu, C., Wang, Y.: GhostNetv2: enhance cheap operation with long-range attention. Adv Neural Inf Process Syst 35:9969\u20139982 (2022). https:\/\/doi.org\/10.48550\/arXiv.2207.01797","DOI":"10.48550\/arXiv.2207.01797"},{"key":"2143_CR52","doi-asserted-by":"publisher","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 International Conference on Computer Vision, 618\u2013626 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.74","DOI":"10.1109\/ICCV.2017.74"},{"key":"2143_CR53","doi-asserted-by":"crossref","unstructured":"Han, K., Wang, Y., Tian, Q., et al.: Ghostnet: More features from cheap operations[C]\/\/Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 1580-1589 (2020)","DOI":"10.1109\/CVPR42600.2020.00165"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02143-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-02143-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02143-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T04:27:44Z","timestamp":1776486464000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-02143-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,3]]},"references-count":53,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["2143"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-02143-3","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,3]]},"assertion":[{"value":"17 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"80"}}