{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:45:32Z","timestamp":1774539932208,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-sa\/4.0\/"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172126"],"award-info":[{"award-number":["62172126"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Research Council","award":["JCYJ20210324120202006"],"award-info":[{"award-number":["JCYJ20210324120202006"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680922","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"10544-10553","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Data Generation Scheme for Thermal Modality with Edge-Guided Adversarial Conditional Diffusion Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8153-2636","authenticated-orcid":false,"given":"Guoqing","family":"Zhu","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3319-692X","authenticated-orcid":false,"given":"Honghu","family":"Pan","sequence":"additional","affiliation":[{"name":"University of Macau, Macau, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9654-0268","authenticated-orcid":false,"given":"Qiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7029-5065","authenticated-orcid":false,"given":"Chao","family":"Tian","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0426-3826","authenticated-orcid":false,"given":"Chao","family":"Yang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2546-8721","authenticated-orcid":false,"given":"Zhenyu","family":"He","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Demystifying MMD GANs. arxiv","author":"Sutherland Danica J.","year":"1801","unstructured":"Danica J. Sutherland, Michael Arbel, and Arthur Gretton. 2021. Demystifying MMD GANs. arxiv: 1801.01401 [stat.ML]"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123135"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475679"},{"key":"e_1_3_2_1_4_1","volume-title":"Radu Tudor Ionescu, and Mubarak Shah","author":"Croitoru Florinel-Alin","year":"2023","unstructured":"Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu, and Mubarak Shah. 2023. Diffusion models in vision: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00135"},{"key":"e_1_3_2_1_6_1","volume-title":"Diffusion models beat gans on image synthesis. Advances in neural information processing systems","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in neural information processing systems, Vol. 34 (2021), 8780--8794."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"e_1_3_2_1_8_1","unstructured":"Teledyne FLIR. 2019. Free Teledyne FLIR thermal dataset for algorithm training. https:\/\/www.flir.com\/oem\/adas\/adas-dataset-form. Accessed:2023-08-01."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_22"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00130"},{"key":"e_1_3_2_1_11_1","volume-title":"Generative adversarial nets. Advances in neural information processing systems","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems, Vol. 27 (2014)."},{"key":"e_1_3_2_1_12_1","volume-title":"Autonomous Systems: Sensors, Vehicles, Security, and the Internet of Everything","author":"Herrmann Christian","unstructured":"Christian Herrmann, Miriam Ruf, and J\u00fcrgen Beyerer. 2018. CNN-based thermal infrared person detection by domain adaptation. In Autonomous Systems: Sensors, Vehicles, Security, and the Internet of Everything, Vol. 10643. SPIE, 38--43."},{"key":"e_1_3_2_1_13_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_14_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840--6851."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00389"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3418213"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412764"},{"key":"e_1_3_2_1_19_1","volume-title":"U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation. arxiv","author":"Kim Junho","year":"1907","unstructured":"Junho Kim, Minjae Kim, Hyeonwoo Kang, and Kwanghee Lee. 2020. U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation. arxiv: 1907.10830 [cs.CV]"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00194"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00927"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings, Part V 13","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6--12, 2014, Proceedings, Part V 13. Springer, 740--755."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/AICIT55386.2022.9930233"},{"key":"e_1_3_2_1_25_1","volume-title":"Unsupervised image-to-image translation networks. Advances in neural information processing systems","author":"Liu Ming-Yu","year":"2017","unstructured":"Ming-Yu Liu, Thomas Breuel, and Jan Kautz. 2017. Unsupervised image-to-image translation networks. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_26_1","volume-title":"Unsupervised image-generation enhanced adaptation for object detection in thermal images. Mobile information systems","author":"Liu Peng","year":"2021","unstructured":"Peng Liu, Fuyu Li, Shanshan Yuan, and Wanyi Li. 2021. Unsupervised image-generation enhanced adaptation for object detection in thermal images. Mobile information systems, Vol. 2021 (2021), 1--6."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3008028"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2017.07.032"},{"key":"e_1_3_2_1_29_1","unstructured":"Cheng Lu Yuhao Zhou Fan Bao Jianfei Chen Chongxuan Li and Jun Zhu. 2023. DPM-Solver: Fast Solver for Guided Sampling of Diffusion Probabilistic Models. arxiv: 2211.01095 [cs.LG]"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW58289.2023.00018"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.11.024"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.108793"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3099846"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3254449"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3276996"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3426335"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Gaurav Parmar Richard Zhang and Jun-Yan Zhu. 2022. On Aliased Resizing and Surprising Subtleties in GAN Evaluation. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01112"},{"key":"e_1_3_2_1_38_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, Vol. 28 (2015)."},{"key":"e_1_3_2_1_39_1","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2021. High-Resolution Image Synthesis with Latent Diffusion Models. arxiv: 2112.10752 [cs.CV]"},{"key":"e_1_3_2_1_40_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention--MICCAI 2015: 18th International Conference","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention--MICCAI 2015: 18th International Conference, Munich, Germany, October 5--9, 2015, Proceedings, Part III 18. Springer, 234--241."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"e_1_3_2_1_42_1","unstructured":"Maximilian Seitzer. 2020. pytorch-fid: FID Score for PyTorch. https:\/\/github.com\/mseitzer\/pytorch-fid. Version 0.3.0."},{"key":"e_1_3_2_1_43_1","volume-title":"Denoising Diffusion Implicit Models. arxiv","author":"Song Jiaming","year":"2010","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2022. Denoising Diffusion Implicit Models. arxiv: 2010.02502 [cs.LG]"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_2"},{"key":"e_1_3_2_1_45_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_46_1","volume-title":"Diffusion-GAN: Training GANs with Diffusion. In The Eleventh International Conference on Learning Representations.","author":"Wang Zhendong","year":"2022","unstructured":"Zhendong Wang, Huangjie Zheng, Pengcheng He, Weizhu Chen, and Mingyuan Zhou. 2022. Diffusion-GAN: Training GANs with Diffusion. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_47_1","volume-title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection. arxiv: 2203.03605 [cs.CV]","author":"Zhang Hao","year":"2022","unstructured":"Hao Zhang, Feng Li, Shilong Liu, Lei Zhang, Hang Su, Jun Zhu, Lionel M. Ni, and Heung-Yeung Shum. 2022. DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection. arxiv: 2203.03605 [cs.CV]"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"crossref","unstructured":"Richard Zhang Phillip Isola Alexei A Efros Eli Shechtman and Oliver Wang. 2018. The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. In CVPR.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_50_1","first-page":"3609","article-title":"Egsde: Unpaired image-to-image translation via energy-guided stochastic differential equations","volume":"35","author":"Zhao Min","year":"2022","unstructured":"Min Zhao, Fan Bao, Chongxuan Li, and Jun Zhu. 2022. Egsde: Unpaired image-to-image translation via energy-guided stochastic differential equations. Advances in Neural Information Processing Systems, Vol. 35 (2022), 3609--3623.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_51_1","volume-title":"IEEE International Conference on.","author":"Zheng Liang","year":"2015","unstructured":"Liang Zheng, Liyue Shen, Lu Tian, Shengjin Wang, Jingdong Wang, and Qi Tian. 2015. Scalable Person Re-identification: A Benchmark. In Computer Vision, IEEE International Conference on."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.357"},{"key":"e_1_3_2_1_53_1","volume-title":"Semantic segmentation in thermal videos: a new benchmark and multi-granularity contrastive learning-based framework","author":"Zheng Yu","year":"2023","unstructured":"Yu Zheng, Fugen Zhou, Shangying Liang, Wentao Song, and Xiangzhi Bai. 2023. Semantic segmentation in thermal videos: a new benchmark and multi-granularity contrastive learning-based framework. IEEE Transactions on Intelligent Transportation Systems (2023)."},{"key":"e_1_3_2_1_54_1","volume-title":"Denoising diffusion bridge models. arXiv preprint arXiv:2309.16948","author":"Zhou Linqi","year":"2023","unstructured":"Linqi Zhou, Aaron Lou, Samar Khanna, and Stefano Ermon. 2023. Denoising diffusion bridge models. arXiv preprint arXiv:2309.16948 (2023)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680922","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680922","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:34Z","timestamp":1750295854000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680922"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":55,"alternative-id":["10.1145\/3664647.3680922","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680922","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}