{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T17:54:31Z","timestamp":1782928471033,"version":"3.54.5"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T00:00:00Z","timestamp":1716768000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T00:00:00Z","timestamp":1716768000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,27]]},"DOI":"10.1109\/fg59268.2024.10581912","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T17:40:08Z","timestamp":1720719608000},"page":"1-9","source":"Crossref","is-referenced-by-count":22,"title":["Discovering Interpretable Directions in the Semantic Latent Space of Diffusion Models"],"prefix":"10.1109","author":[{"given":"Ren\u00e9","family":"Haas","sequence":"first","affiliation":[{"name":"IT University of Copenhagen,Computer Science,Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Inbar","family":"Huberman-Spiegelglas","sequence":"additional","affiliation":[{"name":"Technion,Computer Science,Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rotem","family":"Mulayoff","sequence":"additional","affiliation":[{"name":"Technion,Computer Science,Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stella","family":"Gra\u00dfhof","sequence":"additional","affiliation":[{"name":"IT University of Copenhagen,Computer Science,Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sami S.","family":"Brandt","sequence":"additional","affiliation":[{"name":"IT University of Copenhagen,Computer Science,Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomer","family":"Michaeli","sequence":"additional","affiliation":[{"name":"Technion,Computer Science,Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25063-7_13"},{"key":"ref2","article-title":"Diffedit: Diffusion-based semantic image editing with mask guidance","author":"Couairon","year":"2022","journal-title":"arXiv preprint"},{"key":"ref3","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref4","volume-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref6","article-title":"Tensor-based emotion editing in the stylegan latent space","author":"Haas","year":"2022","journal-title":"arXiv:2205.06102 [cs]"},{"key":"ref7","first-page":"9841","article-title":"Ganspace: Discovering interpretable gan controls","volume":"33","author":"H\u00e4rk\u00f6nen","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint"},{"key":"ref9","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Ho","year":"2020"},{"key":"ref10","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref13","article-title":"Diffusion-based image translation using disentangled style and content representation","author":"Kwon","year":"2023","journal-title":"ICLR 2023"},{"key":"ref14","article-title":"Diffusion models already have a semantic latent space","volume-title":"International Conference on Learning Representations","author":"Kwon"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01474"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref17","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"International Conference on Learning Representations","author":"Meng"},{"key":"ref18","article-title":"Null-text inversion for editing real images using guided diffusion models","author":"Mokady","year":"2022","journal-title":"arXiv preprint"},{"key":"ref19","first-page":"16784","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"International Conference on Machine Learning","author":"Nichol"},{"key":"ref20","article-title":"Unsupervised discovery of semantic latent directions in diffusion models","author":"Park","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"ref23","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford","year":"2021"},{"key":"ref24","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","volume-title":"4th International Conference on Learning Representations, ICLR 2016","author":"Radford","year":"2016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00832"},{"key":"ref26","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"CoRR, abs\/2204.06125"},{"key":"ref27","volume-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0075-7"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00281"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02155"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970739"},{"key":"ref34","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Advances in Neural Information Processing Systems","author":"Saharia","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3034267"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00158"},{"key":"ref38","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","volume":"37","author":"Sohl-Dickstein"},{"key":"ref39","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv"},{"key":"ref40","article-title":"GAN Steerability without optimization","volume-title":"International Conference on Learning Representations","author":"Spingarn"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00618"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3592451"},{"key":"ref44","volume-title":"Diffusers: State-of-the-art diffusion models","author":"von Platen","year":"2022"},{"key":"ref45","article-title":"Gan-generated faces detection: A survey and new perspectives","author":"Wang","year":"2022","journal-title":"ArXiv"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01267"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/FGR.2006.6"},{"key":"ref48","article-title":"Low-rank subspaces in GANs","author":"Zhu","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"}],"event":{"name":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","location":"Istanbul, Turkiye","start":{"date-parts":[[2024,5,27]]},"end":{"date-parts":[[2024,5,31]]}},"container-title":["2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10581880\/10581860\/10581912.pdf?arnumber=10581912","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T05:17:59Z","timestamp":1721279879000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10581912\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,27]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/fg59268.2024.10581912","relation":{},"subject":[],"published":{"date-parts":[[2024,5,27]]}}}