Deep Meditations: Controlled navigation of latent space. Atken, M., Fiebrink, R., & Grierson, M. In 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montreal, QC, Canada, 2018.
Paper abstract bibtex We introduce a method which allows users to creatively explore and navigate the vast latent spaces of deep generative models. Specifically, our method enables users to discover and design trajectories in these high dimensional spaces, to construct stories, and produce time-based media such as videos-with meaningful control over narrative. Our goal is to encourage and aid the use of deep generative models as a medium for creative expression and story telling with meaningful human control. Our method is analogous to traditional video production pipelines in that we use a conventional non-linear video editor with proxy clips, and conform with arrays of latent space vectors. Examples can be seen at http://deepmeditations.ai.
@inproceedings{Atken2018,
address = {Montreal, QC, Canada},
title = {Deep {Meditations}: {Controlled} navigation of latent space},
url = {http://deepmeditations.ai.},
abstract = {We introduce a method which allows users to creatively explore and navigate the vast latent spaces of deep generative models. Specifically, our method enables users to discover and design trajectories in these high dimensional spaces, to construct stories, and produce time-based media such as videos-with meaningful control over narrative. Our goal is to encourage and aid the use of deep generative models as a medium for creative expression and story telling with meaningful human control. Our method is analogous to traditional video production pipelines in that we use a conventional non-linear video editor with proxy clips, and conform with arrays of latent space vectors. Examples can be seen at http://deepmeditations.ai.},
urldate = {2019-09-04},
booktitle = {32nd {Conference} on {Neural} {Information} {Processing} {Systems} ({NeurIPS} 2018)},
author = {Atken, Memo and Fiebrink, Rebecca and Grierson, Mick},
year = {2018},
}
Downloads: 0
{"_id":"D7zydhN8bzPoxQBEj","bibbaseid":"atken-fiebrink-grierson-deepmeditationscontrollednavigationoflatentspace-2018","author_short":["Atken, M.","Fiebrink, R.","Grierson, M."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Montreal, QC, Canada","title":"Deep Meditations: Controlled navigation of latent space","url":"http://deepmeditations.ai.","abstract":"We introduce a method which allows users to creatively explore and navigate the vast latent spaces of deep generative models. Specifically, our method enables users to discover and design trajectories in these high dimensional spaces, to construct stories, and produce time-based media such as videos-with meaningful control over narrative. Our goal is to encourage and aid the use of deep generative models as a medium for creative expression and story telling with meaningful human control. Our method is analogous to traditional video production pipelines in that we use a conventional non-linear video editor with proxy clips, and conform with arrays of latent space vectors. Examples can be seen at http://deepmeditations.ai.","urldate":"2019-09-04","booktitle":"32nd Conference on Neural Information Processing Systems (NeurIPS 2018)","author":[{"propositions":[],"lastnames":["Atken"],"firstnames":["Memo"],"suffixes":[]},{"propositions":[],"lastnames":["Fiebrink"],"firstnames":["Rebecca"],"suffixes":[]},{"propositions":[],"lastnames":["Grierson"],"firstnames":["Mick"],"suffixes":[]}],"year":"2018","bibtex":"@inproceedings{Atken2018,\n\taddress = {Montreal, QC, Canada},\n\ttitle = {Deep {Meditations}: {Controlled} navigation of latent space},\n\turl = {http://deepmeditations.ai.},\n\tabstract = {We introduce a method which allows users to creatively explore and navigate the vast latent spaces of deep generative models. Specifically, our method enables users to discover and design trajectories in these high dimensional spaces, to construct stories, and produce time-based media such as videos-with meaningful control over narrative. Our goal is to encourage and aid the use of deep generative models as a medium for creative expression and story telling with meaningful human control. Our method is analogous to traditional video production pipelines in that we use a conventional non-linear video editor with proxy clips, and conform with arrays of latent space vectors. Examples can be seen at http://deepmeditations.ai.},\n\turldate = {2019-09-04},\n\tbooktitle = {32nd {Conference} on {Neural} {Information} {Processing} {Systems} ({NeurIPS} 2018)},\n\tauthor = {Atken, Memo and Fiebrink, Rebecca and Grierson, Mick},\n\tyear = {2018},\n}\n\n","author_short":["Atken, M.","Fiebrink, R.","Grierson, M."],"key":"Atken2018","id":"Atken2018","bibbaseid":"atken-fiebrink-grierson-deepmeditationscontrollednavigationoflatentspace-2018","role":"author","urls":{"Paper":"http://deepmeditations.ai."},"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://api.zotero.org/users/1999854/collections/DCM2A6Q7/items?key=bNsZItJrr69T2OxakZEi8c4h&format=bibtex&limit=100","dataSources":["zZu8sFBHHHNgxZx6k"],"keywords":[],"search_terms":["deep","meditations","controlled","navigation","latent","space","atken","fiebrink","grierson"],"title":"Deep Meditations: Controlled navigation of latent space","year":2018}