{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:38:00Z","timestamp":1782405480018,"version":"3.54.5"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448207","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"2910-2914","source":"Crossref","is-referenced-by-count":2,"title":["Language-Free Compositional Action Generation via Decoupling Refinement"],"prefix":"10.1109","author":[{"given":"Xiao","family":"Liu","sequence":"first","affiliation":[{"name":"Tsinghua University,Shenzhen Key Laboratory of Ubiquitous Data Enabling, Tsinghua Shenzhen International Graduate School,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangyi","family":"Chen","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yansong","family":"Tang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen Key Laboratory of Ubiquitous Data Enabling, Tsinghua Shenzhen International Graduate School,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangrun","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Oxford,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Ping","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen Key Laboratory of Ubiquitous Data Enabling, Tsinghua Shenzhen International Graduate School,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ser-Nam","family":"Lim","sequence":"additional","affiliation":[{"name":"University of Central Florida,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"ref4","article-title":"Compositional transformers for scene generation","volume":"34","author":"Hudson","year":"2021","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3355414\/mm2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"ref8","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref9","article-title":"Learning structured output representation using deep conditional generative models","volume":"28","author":"Sohn","year":"2015","journal-title":"NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240675"},{"key":"ref11","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref12","first-page":"1530","article-title":"Variational inference with normalizing flows","author":"Rezende","year":"2015","journal-title":"ICML"},{"key":"ref13","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00626"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00281"},{"key":"ref16","article-title":"Controllable and compositional generation with latent-space energy-based models","volume":"34","author":"Nie","year":"2021","journal-title":"NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_12"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00354"},{"key":"ref19","article-title":"Emerging disentanglement in auto-encoder based unsupervised image content transfer","author":"Press","year":"2020"},{"key":"ref20","first-page":"8821","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"ICML. PMLR"},{"key":"ref21","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref22","article-title":"mixup: Beyond empirical risk minimization","volume-title":"International Conference on Learning Representations","author":"Zhang"},{"key":"ref23","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053994"},{"key":"ref28","article-title":"Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting","author":"Yu","year":"2017"},{"key":"ref29","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref30","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"NeurIPS"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448207.pdf?arnumber=10448207","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:53:19Z","timestamp":1722574399000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448207\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448207","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}