{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T14:30:09Z","timestamp":1759847409774,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,12,23]],"date-time":"2022-12-23T00:00:00Z","timestamp":1671753600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,12,23]]},"DOI":"10.1145\/3579654.3579769","type":"proceedings-article","created":{"date-parts":[[2023,3,14]],"date-time":"2023-03-14T16:09:40Z","timestamp":1678810180000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Predict Inter-photo Visual Similarity via Pre-trained Computer Vision Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6860-8221","authenticated-orcid":false,"given":"Hiroshi","family":"Omori","sequence":"first","affiliation":[{"name":"Graduate School of Agricultural and Life Sciences, The University of Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7570-6524","authenticated-orcid":false,"given":"Kazunori","family":"Hanyu","sequence":"additional","affiliation":[{"name":"Nihon University, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,3,14]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Image similarity using Deep CNN and Curriculum Learning. arXiv:1709.08761","author":"Appalaraju Srikar","year":"2017","unstructured":"Srikar Appalaraju and Vineet Chaoji. 2017. Image similarity using Deep CNN and Curriculum Learning. arXiv:1709.08761 (2017)."},{"key":"e_1_3_2_1_2_1","volume-title":"Rethinking Atrous Convolution for Semantic Image Segmentation. arXiv:1706.05587","author":"Chen Liang-Chieh","year":"2017","unstructured":"Liang-Chieh Chen, George Papandreou, Florian Schroff, and Hartwig Adam. 2017. Rethinking Atrous Convolution for Semantic Image Segmentation. arXiv:1706.05587 (2017)."},{"key":"e_1_3_2_1_3_1","volume-title":"Xception: Deep learning with depthwise separable convolutions. arXiv:1610.02357v3","author":"Chollet Francois","year":"2017","unstructured":"Francois Chollet. 2017. Xception: Deep learning with depthwise separable convolutions. arXiv:1610.02357v3 (2017), 1\u20138."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_5_1","volume-title":"d.]. vit-keras. Retrieved","author":"Dosovitskiy Alexey","year":"2022","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. [n. d.]. vit-keras. Retrieved February 28, 2022 from https:\/\/github.com\/faustomorales\/vit-keras"},{"key":"e_1_3_2_1_6_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2021. Image is worth 16x16 words: Transformers for image recognition at scale. (2021)."},{"key":"e_1_3_2_1_7_1","volume-title":"Deep residual learning for image recognition.arXiv:1512.03385v1","author":"He Kaiming","year":"2015","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep residual learning for image recognition.arXiv:1512.03385v1 (2015), 1\u201312."},{"key":"e_1_3_2_1_8_1","volume-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications.arXiv:1704.04861v1","author":"Howard G.","year":"2017","unstructured":"Andrew\u00a0G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. MobileNets: Efficient convolutional neural networks for mobile vision applications.arXiv:1704.04861v1 (2017), 1\u20139."},{"key":"e_1_3_2_1_9_1","volume-title":"Laurens van\u00a0der Maaten, and Kilian\u00a0Q. Weinberger","author":"Huang Gao","year":"2018","unstructured":"Gao Huang, Zhuang Liu, Laurens van\u00a0der Maaten, and Kilian\u00a0Q. Weinberger. 2018. Densely connected convolutional networks.arXiv:1608.06993v5 (2018), 1\u20139."},{"key":"e_1_3_2_1_10_1","volume-title":"Proxy anchor loss for deep metric learning.CVPR","author":"Kim Sungyeon","year":"2020","unstructured":"Sungyeon Kim, Dongwon Kim, Minsu Cho, and Suha Kwak. 2020. Proxy anchor loss for deep metric learning.CVPR (2020)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"e_1_3_2_1_12_1","volume-title":"Retrieved","author":"Krizhevsky Alex","year":"2009","unstructured":"Alex Krizhevsky. 2009. The CIFAR-10 dataset. Retrieved February 28, 2022 from https:\/\/www.cs.toronto.edu\/\u00a0kriz\/cifar.html"},{"key":"e_1_3_2_1_13_1","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey\u00a0E. Hinton. 2012. ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems Vol.\u00a025. 1097\u20131105."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"e_1_3_2_1_17_1","volume-title":"d.]. Keras. Retrieved","author":"Nain Aakash","year":"2022","unstructured":"Aakash Nain, Sayak Paul, and Margaret Maynard-Reid. [n. d.]. Keras. Retrieved February 28, 2022 from https:\/\/keras.io\/"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5632\/jila.77.491"},{"key":"e_1_3_2_1_19_1","first-page":"171","article-title":"SALoT MAP as collective intelligence on environment recognition: Visualization of the impression of student life (in Japanese)","volume":"16","author":"Omori Hiroshi","year":"2017","unstructured":"Hiroshi Omori, Kazunori Hanyu, and Masako Yamashita. 2017. SALoT MAP as collective intelligence on environment recognition: Visualization of the impression of student life (in Japanese). J. Affective Engineering 16, 1 (2017), 171\u2013179.","journal-title":"J. Affective Engineering"},{"key":"e_1_3_2_1_20_1","volume-title":"10th Inter. Conf. of SCIS & ISIS(2018)","author":"Omori Hiroshi","year":"2018","unstructured":"Hiroshi Omori, Kazunori Hanyu, Masako Yamashita, and Satoshi Shimada. 2018. Prediction of the visual similarity between photos using several pre-trained CNNs. 10th Inter. Conf. of SCIS & ISIS(2018), 168\u2013173."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5632\/jila.68.849"},{"key":"e_1_3_2_1_22_1","volume-title":"International Conference on Machine Learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning transferable visual models from natural language supervision. International Conference on Machine Learning (2021)."},{"key":"e_1_3_2_1_23_1","volume-title":"Retrieved","author":"Ridnik Tal","year":"2022","unstructured":"Tal Ridnik, Emanuel Ben-Baruch, Asaf Noy, and Lihi Zelnik-Manor. [n. d.]. ImageNet-21K Pretraining for the Masses. Retrieved February 28, 2022 from https:\/\/github.com\/Alibaba-MIIL\/ImageNet21K"},{"key":"e_1_3_2_1_24_1","volume-title":"Image-Net-21K pretraining for the masses. NeurIPS","author":"Ridnik Tal","year":"2021","unstructured":"Tal Ridnik, Emanuel Ben-Baruch, Asaf Noy, and Lihi Zelnik-Manor. 2021. Image-Net-21K pretraining for the masses. NeurIPS (2021)."},{"key":"e_1_3_2_1_25_1","volume-title":"Proc. SPIE 3299","author":"Rogowitz E.","year":"1998","unstructured":"Bernice\u00a0E. Rogowitz, Thomas Frese, John\u00a0R. Smith, Charles\u00a0A. Bouman, and Edward\u00a0B. Kalin. 1998. Perceptual image similarity experiments. In Proc. SPIE 3299, Human Vision and Electronic Imaging III."},{"key":"e_1_3_2_1_26_1","volume-title":"Proc. ICML, PMIL 119","author":"Roth Karsten","year":"2020","unstructured":"Karsten Roth, Timo Milbich, Samarth Sinha, Prateek Gupta, Bjorn Ommer, and Joseph\u00a0Paul Cohen. 2020. Revisiting training strategies and generalization performance in deep metric learning. In Proc. ICML, PMIL 119."},{"key":"e_1_3_2_1_27_1","volume-title":"Very deep convolution networks for large-scale image recognition. arXiv:1409.1556v6","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very deep convolution networks for large-scale image recognition. arXiv:1409.1556v6 (2015), 1\u201314."},{"key":"e_1_3_2_1_28_1","volume-title":"Deep metric learning via lifted structured fearture embedding. CVPR","author":"Song Hyun\u00a0Oh","year":"2016","unstructured":"Hyun\u00a0Oh Song, Yu Xiang, and Stefanie Jegelkaand\u00a0Silvio Savarese. 2016. Deep metric learning via lifted structured fearture embedding. CVPR (2016)."},{"key":"e_1_3_2_1_29_1","volume-title":"Rethinking the Inception architecture for computer vision. arXiv:1512.00567v3","author":"Szegedy Christian","year":"2015","unstructured":"Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, and Zbigniew Wojna. 2015. Rethinking the Inception architecture for computer vision. arXiv:1512.00567v3 (2015), 1\u201310."},{"key":"e_1_3_2_1_30_1","volume-title":"Mlp-mixer: An all-mlp architecture for vision. arXiv:2105.01601","author":"Tolstikhin Ilya","year":"2021","unstructured":"Ilya Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, Mario Lucic, and Alexey Dosovitskiy. 2021. Mlp-mixer: An all-mlp architecture for vision. arXiv:2105.01601 (2021)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1162\/153244304322765649"},{"key":"e_1_3_2_1_32_1","unstructured":"Catherine Wah Steve Branson Peter Welinder Pietro Perona and Serge Belongie. 2011. The Caltech-UCSD Birds-200-2011 Dataset. Master\u2019s thesis."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00516"},{"key":"e_1_3_2_1_34_1","volume-title":"GluonCV. Retrieved","author":"Zhang Z.","year":"2022","unstructured":"Joshua\u00a0Z. Zhang, Yi Zhu, and Mu\u00a0Li et al.[n. d.]. GluonCV. Retrieved February 28, 2022 from https:\/\/cv.gluon.ai\/index.html"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"}],"event":{"name":"ACAI 2022: 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","acronym":"ACAI 2022","location":"Sanya China"},"container-title":["Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3579654.3579769","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3579654.3579769","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T07:00:53Z","timestamp":1755846053000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3579654.3579769"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,23]]},"references-count":35,"alternative-id":["10.1145\/3579654.3579769","10.1145\/3579654"],"URL":"https:\/\/doi.org\/10.1145\/3579654.3579769","relation":{},"subject":[],"published":{"date-parts":[[2022,12,23]]},"assertion":[{"value":"2023-03-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}