{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:23:22Z","timestamp":1774419802227,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890415","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Fusion of Computationally Diverse Modalities Using Chunking and Cross-Attention"],"prefix":"10.1109","author":[{"given":"Christian","family":"Flores","sequence":"first","affiliation":[{"name":"The University of Texas at Dallas,Richardson,TX,USA,75080"}]},{"given":"Lucas","family":"Goncalves","sequence":"additional","affiliation":[{"name":"The University of Texas at Dallas,Richardson,TX,USA,75080"}]},{"given":"Carlos","family":"Busso","sequence":"additional","affiliation":[{"name":"The University of Texas at Dallas,Richardson,TX,USA,75080"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3433386"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096138"},{"key":"ref4","article-title":"Is space-time attention all you need for video understanding?","volume-title":"CoRR","author":"Bertasius","year":"2021"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00676","article-title":"Vivit: A video vision transformer","author":"Arnab","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"issue":"1","key":"ref7","first-page":"235","article-title":"Performance analysis of a chunk-based speech emotion recognition model using rnn","volume-title":"Intelligent Automation & Soft Computing","volume":"36","author":"Shin","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3083821"},{"key":"ref9","first-page":"1686","article-title":"MissModal: Increasing Robustness to Missing Modality in Multimodal Sentiment Analysis","volume-title":"Transactions of the Association for Computational Linguistics","volume":"11","author":"Lin","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2636"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3614110"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486455"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682863"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093345"},{"key":"ref15","article-title":"Transformers in speech processing: A survey","author":"Latif","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.acl-main.216","article-title":"Multiresolution and multimodal speech recognition with transformers","author":"Paraskevopoulos","year":"2020"},{"key":"ref18","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020"},{"key":"ref19","article-title":"Rethinking attention with performers","author":"Choromanski","year":"2022"},{"key":"ref20","article-title":"Transformers are rnns: Fast autoregressive transformers with linear attention","author":"Katharopoulos","year":"2020"},{"key":"ref21","article-title":"Reformer: The efficient transformer","author":"Kitaev","year":"2020"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.acl-long.729","article-title":"Chunk, align, select: A simple long-sequence processing method for transformers","author":"Xie","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00150"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3216993"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref27","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref28","article-title":"Peft: State-of-the-art parameter-efficient fine-tuning methods","author":"Mangrulkar","year":"2022"},{"key":"ref29","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890415.pdf?arnumber=10890415","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:47Z","timestamp":1774416287000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890415\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890415","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}