{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T22:36:14Z","timestamp":1775687774678,"version":"3.50.1"},"reference-count":32,"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"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447954","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"6125-6129","source":"Crossref","is-referenced-by-count":4,"title":["Multimodal Transformer with a Low-Computational-Cost Guarantee"],"prefix":"10.1109","author":[{"given":"Sungjin","family":"Park","sequence":"first","affiliation":[{"name":"KAIST"}]},{"given":"Edward","family":"Choi","sequence":"additional","affiliation":[{"name":"KAIST"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.542"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref3","author":"Kay","year":"2017","journal-title":"The kinetics human action video dataset"},{"key":"ref4","author":"Abu-El-Haija","year":"2016","journal-title":"Youtubep-8m: A large-scale video classification benchmark"},{"key":"ref5","article-title":"Rescaling egocentric vision: Collection, pipeline and challenges for epic-kitchens-100","author":"Damen","year":"2021","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref7","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proc. ICML","author":"Jaegle"},{"key":"ref8","article-title":"Universal transformers","volume-title":"Proc. ICLR","author":"Dehghani"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref10","article-title":"Pali: A jointly-scaled multilingual language-image model","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref11","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. ICML","volume":"162","author":"Wang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.232"},{"key":"ref13","author":"Child","year":"2019","journal-title":"Generating long sequences with sparse transformers"},{"key":"ref14","author":"Beltagy","year":"2020","journal-title":"Longformer: The long-document transformer"},{"key":"ref15","article-title":"Reformer: The efficient transformer","volume-title":"Proc. ICLR","author":"Kitaev"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00353"},{"key":"ref17","author":"Wang","year":"2020","journal-title":"Linformer: Self-attention with linear complexity"},{"key":"ref18","article-title":"Rethinking attention with performers","volume-title":"Proc. ICLR","author":"Choromanski"},{"key":"ref19","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","volume-title":"Proc. NeurIPS","author":"Nagrani"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02036-y"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01479"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref25","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. NeurIPS","volume":"32","author":"Lu"},{"key":"ref26","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref27","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume-title":"Proc. NeurIPS","volume":"33","author":"Zaheer"},{"key":"ref28","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref31","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-010-0182-0"}],"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\/10447954.pdf?arnumber=10447954","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:31:54Z","timestamp":1722573114000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447954\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447954","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}