{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:35:49Z","timestamp":1772724949888,"version":"3.50.1"},"reference-count":42,"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\/icassp49357.2023.10095762","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Multi-Modal Food Classification in a Diet Tracking System with Spoken and Visual Inputs"],"prefix":"10.1109","author":[{"given":"Shivani","family":"Gowda","sequence":"first","affiliation":[{"name":"Loyola Marymount University,Computer Science Department,Los Angeles,CA,USA"}]},{"given":"Yifan","family":"Hu","sequence":"additional","affiliation":[{"name":"Loyola Marymount University,Computer Science Department,Los Angeles,CA,USA"}]},{"given":"Mandy","family":"Korpusik","sequence":"additional","affiliation":[{"name":"Loyola Marymount University,Computer Science Department,Los Angeles,CA,USA"}]}],"member":"263","reference":[{"key":"ref13","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref35","first-page":"446","article-title":"Food-101– mining discriminative components with random forests","author":"bossard","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref12","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref34","article-title":"Deep-daze","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref37","article-title":"textgenrnn","author":"woolf","year":"2020"},{"key":"ref14","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv preprint arXiv 1409 1556"},{"key":"ref36","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref31","first-page":"104","article-title":"Uniter: Universal image-text representation learning","author":"chen","year":"2020","journal-title":"European Conference on Computer Vision"},{"key":"ref30","article-title":"Vl-bert: Pre-training of generic visual-linguistic representations","author":"su","year":"2019","journal-title":"arXiv Preprint arXiv 1908 08098"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1561\/9781601982957"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2918618"},{"key":"ref10","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2694699"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2147\/DMSO.S95247"},{"key":"ref1","article-title":"Obesity and overweight","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2638728.2641339"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","author":"kim","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.09.001"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2015.7169816"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2018.2840738"},{"key":"ref23","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv preprint arXiv 1810 04805"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2020.10"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3439726"},{"key":"ref20","article-title":"Foodx-251: A dataset for fine-grained food classification","author":"kaur","year":"2019","journal-title":"arXiv preprint arXiv 1907 06777"},{"key":"ref42","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLR (Poster)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ECTI-NCON.2018.8378293"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2016.07.006"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref27","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"arXiv preprint arXiv 1908 02262"},{"key":"ref29","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"li","year":"2019","journal-title":"arXiv preprint arXiv 1908 03156"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078635"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-422"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1262"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472843"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2196\/mhealth.9838"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461769"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953245"},{"key":"ref40","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv 2010 11419"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"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\/10095762.pdf?arnumber=10095762","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T18:59:53Z","timestamp":1699901993000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095762\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095762","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}