{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:42:40Z","timestamp":1783438960131,"version":"3.54.6"},"reference-count":23,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","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\/icassp48485.2024.10446922","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10206-10210","source":"Crossref","is-referenced-by-count":20,"title":["SDIF-DA: A Shallow-to-Deep Interaction Framework with Data Augmentation for Multi-Modal Intent Detection"],"prefix":"10.1109","author":[{"given":"Shijue","family":"Huang","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),School of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Libo","family":"Qin","sequence":"additional","affiliation":[{"name":"Central South University,School of Computer Science and Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingbing","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),School of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Geng","family":"Tu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),School of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruifeng","family":"Xu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),School of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/622"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1214"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1469"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3470482.3479636"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.36"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053281"},{"key":"ref7","first-page":"7157","article-title":"Tie your embeddings down: Cross-modal latent spaces for end-toend spoken language understanding","volume-title":"Proc. of ICASSP","author":"Agrawal"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-658"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547906"},{"key":"ref10","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. of NAACL","author":"Devlin"},{"key":"ref11","article-title":"Wav2vec 2.0: A framework for selfsupervised learning of speech representations","volume-title":"Proc. of NIPS","author":"Baevski"},{"key":"ref12","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume-title":"Proc. of NIPS","volume":"28","author":"Ren"},{"key":"ref13","first-page":"6","article-title":"Bibimodal modality fusion for correlation-controlled multimodal sentiment analysis","volume-title":"ICMI \u201921","author":"Han"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.417"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3380688.3380693"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897323"},{"key":"ref20","article-title":"A comprehensive survey on pretrained foundation models: A history from bert to chatgpt","author":"Zhou","year":"2023"},{"key":"ref21","article-title":"Auggpt: Leveraging chatgpt for text data augmentation","author":"Dai","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref23","article-title":"Decoupled weight decay regularization","volume-title":"Proc. of ICLR","author":"Loshchilov"}],"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\/10446922.pdf?arnumber=10446922","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:27:38Z","timestamp":1722576458000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446922\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446922","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}