{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:42:31Z","timestamp":1730230951569,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096573","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Scale Compositional Constraints for Representation Learning on Videos"],"prefix":"10.1109","author":[{"given":"Georgios","family":"Paraskevopoulos","sequence":"first","affiliation":[{"name":"AWS AI Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chandrashekhar","family":"Lavania","sequence":"additional","affiliation":[{"name":"AWS AI Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lovish","family":"Chum","sequence":"additional","affiliation":[{"name":"AWS AI Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiva","family":"Sundaram","sequence":"additional","affiliation":[{"name":"AWS AI Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00129"},{"key":"ref2","article-title":"Self-supervised audio-visual representation learning with relaxed cross-modal temporal synchronicity","author":"Sarkar","year":"2021","journal-title":"CoRR arXiv:2111.05329"},{"key":"ref3","first-page":"4573","article-title":"Mm-latch: Bottom-up top-down fusion for multimodal sentiment analysis","volume-title":"Proc. ICASSP","author":"Paraskevopoulos"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"article-title":"How2: A large-scale dataset for multimodal language understanding","volume-title":"Proc. ViGIL workshop, NeurIps","author":"Ramon","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.216"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01229"},{"key":"ref8","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language under-standing","volume-title":"Proc. NAACL","volume":"1","author":"Devlin"},{"key":"ref9","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. ICML","author":"Chen"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.08.002"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01058"},{"key":"ref14","first-page":"9758","article-title":"Self-supervised learning by cross-modal audio-video clustering","volume-title":"Proc. NeurIps","volume":"33","author":"Alwassel"},{"key":"ref15","article-title":"Multi-modal self-supervision from generalized data transformations","author":"Patrick","year":"2020","journal-title":"CoRR arXiv:2003.04298"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"ref18","first-page":"5679","article-title":"Self-supervised co-training for video representation learning","volume-title":"Proc. NeurIps","volume":"33","author":"Han"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780195094237.003.0002"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-6465-9"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3147198"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00640"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref24","first-page":"7025","article-title":"Contrastive learning of global and local video representations","volume-title":"Proc. NeurIps","volume":"34","author":"Zeng"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20881"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11674"},{"key":"ref27","article-title":"Learning compositionally through attentive guidance","author":"Hupkes","year":"2018","journal-title":"CoRR arXiv:2003.04298"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4814"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01401-3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.85"},{"key":"ref31","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018","journal-title":"CoRR arXiv:1807.03748"},{"key":"ref32","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. 13th AISTATS","author":"Gutmann"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref35","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012","journal-title":"CoRR arXiv:1212.0402"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12255"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747361"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096573.pdf?arnumber=10096573","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T20:01:16Z","timestamp":1705003276000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096573\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096573","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}