{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:04:46Z","timestamp":1777655086319,"version":"3.51.4"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icmew63481.2024.10645412","type":"proceedings-article","created":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T17:43:36Z","timestamp":1724953416000},"page":"1-4","source":"Crossref","is-referenced-by-count":4,"title":["Multimodal Guidance Network for Missing- Modality Inference in Content Moderation"],"prefix":"10.1109","author":[{"given":"Zhuokai","family":"Zhao","sequence":"first","affiliation":[{"name":"University of Chicago,Chicago,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harish","family":"Palani","sequence":"additional","affiliation":[{"name":"Twitch Interactive, Inc.,San Francisco,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyi","family":"Liu","sequence":"additional","affiliation":[{"name":"Twitch Interactive, Inc.,San Francisco,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lena","family":"Evans","sequence":"additional","affiliation":[{"name":"Twitch Interactive, Inc.,San Francisco,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruth","family":"Toner","sequence":"additional","affiliation":[{"name":"Twitch Interactive, Inc.,San Francisco,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"689","article-title":"Multimodal deep learning","volume-title":"Proceedings of the 28th international conference on machine learning (ICML-11), 2011","author":"Ngiam"},{"key":"ref2","article-title":"Direct acquisition optimization for low-budget active learning","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref4","article-title":"Multimodal deep learning","author":"Akkus","year":"2023","journal-title":"arXiv preprint"},{"issue":"3","key":"ref5","first-page":"6","article-title":"Multi-modal classification using images and text","volume":"3","author":"Miller","year":"2020","journal-title":"SMU Data Science Review"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0287786"},{"key":"ref7","article-title":"Rankclip: Ranking-consistent language-image pretraining","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","author":"Nagrani","year":"2020","journal-title":"Video understanding using multimodal deep learning, Ph.D. thesis, University of Oxford"},{"key":"ref9","author":"Palaskar","year":"2022","journal-title":"Multimodal Learning from Videos: Exploring Models and Task Complexities, Ph.D. thesis, Carnegie Mellon University"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.11.004"},{"key":"ref12","article-title":"Halc: Object hallucination reduction via adaptive focal-contrast decoding","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"ref14","article-title":"Evaluating machine learning models with nero: Non-equivariance revealed on orbits","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.73"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01764"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3160060"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCC.2018.00008"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00193"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.793"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25378"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.29007\/9qvn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16330"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF00342633"},{"key":"ref29","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"International conference on machine learning","author":"Ioffe"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1080\/23335777.2021.1940303"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00764"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref34","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10645349\/10645352\/10645412.pdf?arnumber=10645412","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T05:10:42Z","timestamp":1725513042000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10645412\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icmew63481.2024.10645412","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}