{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T15:10:07Z","timestamp":1752073807153,"version":"3.41.2"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,14]]},"DOI":"10.1145\/3719384.3719417","type":"proceedings-article","created":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T14:44:03Z","timestamp":1752072243000},"page":"229-236","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Image Memorability Manipulation with Intermediate Guided Diffusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6758-7962","authenticated-orcid":false,"given":"Jingyi","family":"Huang","sequence":"first","affiliation":[{"name":"Ridge-i Inc., Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2544-8592","authenticated-orcid":false,"given":"Edgar","family":"Simo-Serra","sequence":"additional","affiliation":[{"name":"Waseda University, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,9]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Andrew. 2022. Depth-to-image in Stable Diffusion 2: All you need to know. https:\/\/stable-diffusion-art.com\/depth-to-image\/"},{"key":"e_1_3_3_1_3_2","unstructured":"Arpit Bansal Eitan Borgnia Hong-Min Chu Jie\u00a0S. Li Hamid Kazemi Furong Huang Micah Goldblum Jonas Geiping and Tom Goldstein. 2022. Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise. arxiv:https:\/\/arXiv.org\/abs\/2208.09392\u00a0[cs.CV]"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Arpit Bansal Hong-Min Chu Avi Schwarzschild Soumyadip Sengupta Micah Goldblum Jonas Geiping and Tom Goldstein. 2023. Universal Guidance for Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2302.07121\u00a0[cs.CV]","DOI":"10.1109\/CVPRW59228.2023.00091"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"David Bau Jun-Yan Zhu Jonas Wulff William Peebles Hendrik Strobelt Bolei Zhou and Antonio Torralba. 2019. Seeing What a GAN Cannot Generate. arxiv:https:\/\/arXiv.org\/abs\/1910.11626\u00a0[cs.CV]","DOI":"10.1109\/ICCV.2019.00460"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967269"},{"key":"e_1_3_3_1_7_2","unstructured":"brainpriority. 2022. vitmem. https:\/\/github.com\/brainpriority\/vitmem Software."},{"key":"e_1_3_3_1_8_2","unstructured":"Andrew Brock Jeff Donahue and Karen Simonyan. 2019. Large Scale GAN Training for High Fidelity Natural Image Synthesis. arxiv:https:\/\/arXiv.org\/abs\/1809.11096\u00a0[cs.LG]"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Zoya Bylinskii Lore Goetschalckx Anelise Newman and Aude Oliva. 2021. Memorability: An image-computable measure of information utility. arxiv:https:\/\/arXiv.org\/abs\/2104.00805\u00a0[cs.CV]","DOI":"10.1007\/978-3-030-81465-6_8"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Zoya Bylinskii Phillip Isola Constance Bainbridge Antonio Torralba and Aude Oliva. 2015. Intrinsic and Extrinsic Effects on Image Memorability. Vision research 116 (2015) 165\u2013178.","DOI":"10.1016\/j.visres.2015.03.005"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Jooyoung Choi Sungwon Kim Yonghyun Jeong Youngjune Gwon and Sungroh Yoon. 2021. Ilvr: Conditioning method for denoising diffusion probabilistic models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2108.02938 (2021).","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"e_1_3_3_1_12_2","unstructured":"Guillaume Couairon Jakob Verbeek Holger Schwenk and Matthieu Cord. 2022. DiffEdit: Diffusion-based semantic image editing with mask guidance. arxiv:https:\/\/arXiv.org\/abs\/2210.11427\u00a0[cs.CV]"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","unstructured":"Florinel-Alin Croitoru Vlad Hondru Radu\u00a0Tudor Ionescu and Mubarak Shah. 2023. Diffusion Models in Vision: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 45 9 (Sept. 2023) 10850\u201310869. 10.1109\/tpami.2023.3261988","DOI":"10.1109\/tpami.2023.3261988"},{"key":"e_1_3_3_1_14_2","unstructured":"Katherine Crowson. 2021. Generates images from text prompts with CLIP guided diffusion.https:\/\/colab.research.google.com\/drive\/1V66mUeJbXrTuQITvJunvnWVn96FEbSI3"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_3_1_16_2","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in neural information processing systems 34 (2021) 8780\u20138794."},{"key":"e_1_3_3_1_17_2","unstructured":"Sander Dieleman. 2022. Guidance: a cheat code for diffusion models. https:\/\/benanne.github.io\/2022\/05\/26\/guidance.html"},{"key":"e_1_3_3_1_18_2","unstructured":"Sander Dieleman. 2023. The geometry of diffusion guidance. https:\/\/sander.ai\/2023\/08\/28\/geometry.html"},{"key":"e_1_3_3_1_19_2","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. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arxiv:https:\/\/arXiv.org\/abs\/2010.11929\u00a0[cs.CV]"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.130"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Jiri Fajtl Vasileios Argyriou Dorothy Monekosso and Paolo Remagnino. 2018. AMNet: Memorability Estimation with Attention. arxiv:https:\/\/arXiv.org\/abs\/1804.03115\u00a0[cs.AI]","DOI":"10.1109\/CVPR.2018.00666"},{"key":"e_1_3_3_1_22_2","unstructured":"Goetschalckx. 2019. GANalyze. https:\/\/github.com\/LoreGoetschalckx\/GANalyze Software."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Lore Goetschalckx Alex Andonian Aude Oliva and Phillip Isola. 2019. GANalyze: Toward Visual Definitions of Cognitive Image Properties. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1906.10112 (2019).","DOI":"10.1109\/ICCV.2019.00584"},{"key":"e_1_3_3_1_24_2","unstructured":"Alexandros Graikos Nikolay Malkin Nebojsa Jojic and Dimitris Samaras. 2023. Diffusion models as plug-and-play priors. arxiv:https:\/\/arXiv.org\/abs\/2206.09012\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2206.09012"},{"key":"e_1_3_3_1_25_2","unstructured":"Thomas Hagen and Thomas Espeseth. 2023. Image Memorability Prediction with Vision Transformers. arxiv:https:\/\/arXiv.org\/abs\/2301.08647\u00a0[cs.CV]"},{"key":"e_1_3_3_1_26_2","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. arxiv:https:\/\/arXiv.org\/abs\/2006.11239\u00a0[cs.LG]"},{"key":"e_1_3_3_1_27_2","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-Free Diffusion Guidance. arxiv:https:\/\/arXiv.org\/abs\/2207.12598\u00a0[cs.LG]"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.5555\/2986459.2986730"},{"key":"e_1_3_3_1_29_2","first-page":"145","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Isola Phillip","year":"2011","unstructured":"Phillip Isola, Jianxiong Xiao, Antonio Torralba, and Aude Oliva. 2011. What makes an image memorable?. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 145\u2013152."},{"key":"e_1_3_3_1_30_2","unstructured":"Bahjat Kawar Roy Ganz and Michael Elad. 2023. Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance. arxiv:https:\/\/arXiv.org\/abs\/2208.08664\u00a0[cs.CV]"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.275"},{"key":"e_1_3_3_1_32_2","unstructured":"Diederik\u00a0P Kingma and Max Welling. 2022. Auto-Encoding Variational Bayes. arxiv:https:\/\/arXiv.org\/abs\/1312.6114\u00a0[stat.ML]"},{"key":"e_1_3_3_1_33_2","unstructured":"Xihui Liu Dong\u00a0Huk Park Samaneh Azadi Gong Zhang Arman Chopikyan Yuxiao Hu Humphrey Shi Anna Rohrbach and Trevor Darrell. 2022. More Control for Free! Image Synthesis with Semantic Diffusion Guidance. arxiv:https:\/\/arXiv.org\/abs\/2112.05744\u00a0[cs.CV]"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2013.6738041"},{"key":"e_1_3_3_1_35_2","unstructured":"Naoki Matsunaga Masato Ishii Akio Hayakawa Kenji Suzuki and Takuya Narihira. 2023. Fine-grained Image Editing by Pixel-wise Guidance Using Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2212.02024\u00a0[cs.CV]"},{"key":"e_1_3_3_1_36_2","unstructured":"Chenlin Meng Yutong He Yang Song Jiaming Song Jiajun Wu Jun-Yan Zhu and Stefano Ermon. 2022. SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations. arxiv:https:\/\/arXiv.org\/abs\/2108.01073\u00a0[cs.CV]"},{"key":"e_1_3_3_1_37_2","unstructured":"Coen\u00a0D. Needell and Wilma\u00a0A. Bainbridge. 2022. Embracing New Techniques in Deep Learning for Estimating Image Memorability. arxiv:https:\/\/arXiv.org\/abs\/2105.10598\u00a0[cs.CV]"},{"key":"e_1_3_3_1_38_2","unstructured":"Alex Nichol and Prafulla Dhariwal. 2021. Improved Denoising Diffusion Probabilistic Models. arxiv:https:\/\/arXiv.org\/abs\/2102.09672\u00a0[cs.LG]"},{"key":"e_1_3_3_1_39_2","unstructured":"Alex Nichol Prafulla Dhariwal Aditya Ramesh Pranav Shyam Pamela Mishkin Bob McGrew Ilya Sutskever and Mark Chen. 2022. GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2112.10741\u00a0[cs.CV]"},{"key":"e_1_3_3_1_40_2","unstructured":"ok1zjf. 2018. AMNet. https:\/\/github.com\/ok1zjf\/AMNet Software."},{"key":"e_1_3_3_1_41_2","unstructured":"openai. 2021. guided-diffusion. https:\/\/github.com\/openai\/guided-diffusion Software."},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"crossref","unstructured":"Shay Perera Ayellet Tal and Lihi Zelnik-Manor. 2019. Is Image Memorability Prediction Solved? arxiv:https:\/\/arXiv.org\/abs\/1901.11420\u00a0[cs.CV]","DOI":"10.1109\/CVPRW.2019.00108"},{"key":"e_1_3_3_1_43_2","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. arxiv:https:\/\/arXiv.org\/abs\/2103.00020\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2103.00020"},{"key":"e_1_3_3_1_44_2","unstructured":"Danilo\u00a0Jimenez Rezende and Shakir Mohamed. 2016. Variational Inference with Normalizing Flows. arxiv:https:\/\/arXiv.org\/abs\/1505.05770\u00a0[stat.ML]"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"crossref","unstructured":"Chitwan Saharia William Chan Saurabh Saxena Lala Li Jay Whang Emily Denton Seyed Kamyar\u00a0Seyed Ghasemipour Burcu\u00a0Karagol Ayan S.\u00a0Sara Mahdavi Rapha\u00a0Gontijo Lopes Tim Salimans Jonathan Ho David\u00a0J Fleet and Mohammad Norouzi. 2022. Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding. arxiv:https:\/\/arXiv.org\/abs\/2205.11487\u00a0[cs.CV]","DOI":"10.1145\/3528233.3530757"},{"key":"e_1_3_3_1_46_2","unstructured":"Jascha Sohl-Dickstein Eric\u00a0A. Weiss Niru Maheswaranathan and Surya Ganguli. 2015. Deep Unsupervised Learning using Nonequilibrium Thermodynamics. arxiv:https:\/\/arXiv.org\/abs\/1503.03585\u00a0[cs.LG]"},{"key":"e_1_3_3_1_47_2","unstructured":"Jiaming Song Chenlin Meng and Stefano Ermon. 2022. Denoising Diffusion Implicit Models. arxiv:https:\/\/arXiv.org\/abs\/2010.02502\u00a0[cs.LG]"},{"key":"e_1_3_3_1_48_2","unstructured":"Yang Song and Stefano Ermon. 2020. Generative Modeling by Estimating Gradients of the Data Distribution. arxiv:https:\/\/arXiv.org\/abs\/1907.05600\u00a0[cs.LG]"},{"key":"e_1_3_3_1_49_2","unstructured":"Yang Song Jascha Sohl-Dickstein Diederik\u00a0P. Kingma Abhishek Kumar Stefano Ermon and Ben Poole. 2021. Score-Based Generative Modeling through Stochastic Differential Equations. arxiv:https:\/\/arXiv.org\/abs\/2011.13456\u00a0[cs.LG]"},{"key":"e_1_3_3_1_50_2","unstructured":"Shikhar Tuli Ishita Dasgupta Erin Grant and Thomas\u00a0L. Griffiths. 2021. Are Convolutional Neural Networks or Transformers more like human vision? arxiv:https:\/\/arXiv.org\/abs\/2105.07197\u00a0[cs.CV]"},{"key":"e_1_3_3_1_51_2","unstructured":"Weilun Wang Jianmin Bao Wengang Zhou Dongdong Chen Dong Chen Lu Yuan and Houqiang Li. 2022. Semantic Image Synthesis via Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2207.00050\u00a0[cs.CV]"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"crossref","unstructured":"Jay Whang Mauricio Delbracio Hossein Talebi Chitwan Saharia Alexandros\u00a0G. Dimakis and Peyman Milanfar. 2021. Deblurring via Stochastic Refinement. arxiv:https:\/\/arXiv.org\/abs\/2112.02475\u00a0[cs.CV]","DOI":"10.1109\/CVPR52688.2022.01581"},{"key":"e_1_3_3_1_53_2","unstructured":"Chen\u00a0Henry Wu and Fernando\u00a0De la Torre. 2022. Unifying Diffusion Models\u2019 Latent Space with Applications to CycleDiffusion and Guidance. arxiv:https:\/\/arXiv.org\/abs\/2210.05559\u00a0[cs.CV]"},{"key":"e_1_3_3_1_54_2","unstructured":"Weihao Xia Yulun Zhang Yujiu Yang Jing-Hao Xue Bolei Zhou and Ming-Hsuan Yang. 2022. GAN Inversion: A Survey. arxiv:https:\/\/arXiv.org\/abs\/2101.05278\u00a0[cs.CV]"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/IranianCEE.2017.7985423"},{"key":"e_1_3_3_1_56_2","doi-asserted-by":"crossref","unstructured":"Bolei Zhou Agata Lapedriza Aditya Khosla Aude Oliva and Antonio Torralba. 2017. Places: A 10 million Image Database for Scene Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (2017).","DOI":"10.1109\/TPAMI.2017.2723009"}],"event":{"name":"AICCC 2024: 2024 the 7th Artificial Intelligence and Cloud Computing Conference","location":"Tokyo Japan","acronym":"AICCC 2024"},"container-title":["Proceedings of the 2024 7th Artificial Intelligence and Cloud Computing Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3719384.3719417","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T14:48:23Z","timestamp":1752072503000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3719384.3719417"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,14]]},"references-count":55,"alternative-id":["10.1145\/3719384.3719417","10.1145\/3719384"],"URL":"https:\/\/doi.org\/10.1145\/3719384.3719417","relation":{},"subject":[],"published":{"date-parts":[[2024,12,14]]},"assertion":[{"value":"2025-07-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}