{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/efficient-low-rank-multimodal-fusion-with","title":"Efficient Low-rank Multimodal Fusion with Modality-Specific Factors","arxiv_id":"1806.00064","date":"2018-05-31","proceeding":"ACL 2018 7","authors":["Zhun Liu","Ying Shen","Varun Bharadhwaj Lakshminarasimhan","Paul Pu Liang","Amir Zadeh","Louis-Philippe Morency"],"abstract":"Multimodal research is an emerging field of artificial intelligence, and one\nof the main research problems in this field is multimodal fusion. The fusion of\nmultimodal data is the process of integrating multiple unimodal representations\ninto one compact multimodal representation. Previous research in this field has\nexploited the expressiveness of tensors for multimodal representation. However,\nthese methods often suffer from exponential increase in dimensions and in\ncomputational complexity introduced by transformation of input into tensor. In\nthis paper, we propose the Low-rank Multimodal Fusion method, which performs\nmultimodal fusion using low-rank tensors to improve efficiency. We evaluate our\nmodel on three different tasks: multimodal sentiment analysis, speaker trait\nanalysis, and emotion recognition. Our model achieves competitive results on\nall these tasks while drastically reducing computational complexity. Additional\nexperiments also show that our model can perform robustly for a wide range of\nlow-rank settings, and is indeed much more efficient in both training and\ninference compared to other methods that utilize tensor representations.","url_abs":"http://arxiv.org/abs/1806.00064v1","url_pdf":"http://arxiv.org/pdf/1806.00064v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"efficient-low-rank-multimodal-fusion-with","repo_url":"https://github.com/Justin1904/Low-rank-Multimodal-Fusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"efficient-low-rank-multimodal-fusion-with","repo_url":"https://github.com/18XiWenjuan/LMF_Paddle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"efficient-low-rank-multimodal-fusion-with","repo_url":"https://github.com/righ120/multimodal_nlp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"},{"task_slug":"multimodal-sentiment-analysis","task_name":"Multimodal Sentiment Analysis"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1806.00064","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}