ABSTRACT
Multi-modal emotion recognition aims to recognize emotion states from multi-modal inputs. Existing end-to-end models typically fuse the uni-modal representations in the last layers without leveraging the multi-modal interactions among the intermediate representations. In this paper, we propose the multi-modal Recurrent Intermediate-Layer Aggregation (RILA) model to explore the effectiveness of leveraging the multi-modal interactions among the intermediate representations of deep pre-trained transformers for end-to-end emotion recognition. At the heart of our model is the Intermediate-Representation Fusion Module (IRFM), which consists of the multi-modal aggregation gating module and multi-modal token attention module. Specifically, at each layer, we first use the multi-modal aggregation gating module to capture the utterance-level interactions across the modalities and layers. Then we utilize the multi-modal token attention module to leverage the token-level multi-modal interactions. The experimental results on IEMOCAP and CMU-MOSEI show that our model achieves the state-of-the-art performance, benefiting from fully exploiting the multi-modal interactions among the intermediate representations.
- Guillaume Alain and Yoshua Bengio. 2016. Understanding intermediate layers using linear classifier probes. arXiv preprint arXiv:1610.01644 (2016).Google Scholar
- Shahin Amiriparian, Lukas Christ, Andreas König, Eva-Maria Meßner, Alan Cowen, Erik Cambria, and Björn W. Schuller. 2022. MuSe 2022 Challenge: Multimodal Humour, Emotional Reactions, and Stress. In Proceedings of the 30th ACM International Conference on Multimedia (MM'22), October 10--14, 2022, Lisbon, Portugal. Association for Computing Machinery, Lisbon, Portugal. 3 pages, to appear.Google ScholarDigital Library
- Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. arXiv preprint arXiv:1607.06450 (2016).Google Scholar
- AmirAli Bagher Zadeh, Paul Pu Liang, Soujanya Poria, Erik Cambria, and Louis-Philippe Morency. 2018. Multimodal Language Analysis in the Wild: Carnegie Mellon University-MOSEI Dataset and Interpretable Dynamic Fusion Graph. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Melbourne, Australia, 2236--2246. https://doi.org/10.18653/v1/P18--1208Google ScholarCross Ref
- Tadas Baltrusaitis, Amir Zadeh, Yao Chong Lim, and Louis-Philippe Morency. 2018. Openface 2.0: Facial behavior analysis toolkit. In 2018 13th IEEE international conference on automatic face & gesture recognition (FG 2018). IEEE, 59--66.Google ScholarDigital Library
- Carlos Busso, Murtaza Bulut, Chi-Chun Lee, Abe Kazemzadeh, Emily Mower, Samuel Kim, Jeannette N Chang, Sungbok Lee, and Shrikanth S Narayanan. 2008. IEMOCAP: Interactive emotional dyadic motion capture database. Language resources and evaluation , Vol. 42, 4 (2008), 335--359.Google Scholar
- Shi Chen and Qi Zhao. 2018. Shallowing deep networks: Layer-wise pruning based on feature representations. IEEE transactions on pattern analysis and machine intelligence, Vol. 41, 12 (2018), 3048--3056.Google Scholar
- Lukas Christ, Shahin Amiriparian, Alice Baird, Panagiotis Tzirakis, Alexander Kathan, Niklas Müller, Lukas Stappen, Eva-Maria Meßner, Andreas König, Alan Cowen, Erik Cambria, and Björn W. Schuller. 2022. The MuSe 2022 Multimodal Sentiment Analysis Challenge: Humor, Emotional Reactions, and Stress. In Proceedings of the 3rd Multimodal Sentiment Analysis Challenge. Association for Computing Machinery, Lisbon, Portugal. Workshop held at ACM Multimedia 2022, to appear.Google Scholar
- Wenliang Dai, Samuel Cahyawijaya, Zihan Liu, and Pascale Fung. 2021. Multimodal End-to-End Sparse Model for Emotion Recognition. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Online, 5305--5316. https://www.aclweb.org/anthology/2021.naacl-main.417Google ScholarCross Ref
- Wenliang Dai, Zihan Liu, Tiezheng Yu, and Pascale Fung. 2020. Modality-Transferable Emotion Embeddings for Low-Resource Multimodal Emotion Recognition. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing. Association for Computational Linguistics, Suzhou, China, 269--280. https://aclanthology.org/2020.aacl-main.30Google Scholar
- Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations.Google Scholar
- Florian Eyben, Martin Wöllmer, and Björn Schuller. 2010. Opensmile: the munich versatile and fast open-source audio feature extractor. In Proceedings of the 18th ACM international conference on Multimedia. 1459--1462.Google ScholarDigital Library
- Deepanway Ghosal, Navonil Majumder, Soujanya Poria, Niyati Chhaya, and Alexander Gelbukh. 2019. DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 154--164.Google ScholarCross Ref
- Chengyue Gong, Dilin Wang, Meng Li, Vikas Chandra, and Qiang Liu. 2021b. Vision transformers with patch diversification. arXiv preprint arXiv:2104.12753 (2021).Google Scholar
- Yuan Gong, Yu-An Chung, and James Glass. 2021a. AST: Audio Spectrogram Transformer. In Proc. Interspeech 2021. 571--575. https://doi.org/10.21437/Interspeech.2021--698Google Scholar
- Devamanyu Hazarika, Roger Zimmermann, and Soujanya Poria. 2020. MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis. In Proceedings of the 28th ACM International Conference on Multimedia (Seattle, WA, USA) (MM '20). Association for Computing Machinery, New York, NY, USA, 1122--1131. https://doi.org/10.1145/3394171.3413678Google ScholarDigital Library
- Dan Hendrycks and Kevin Gimpel. 2016. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016).Google Scholar
- Di Hu, Chengze Wang, Feiping Nie, and Xuelong Li. 2019. Dense multimodal fusion for hierarchically joint representation. In ICASSP 2019--2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 3941--3945.Google ScholarCross Ref
- Ganesh Jawahar, Beno^it Sagot, and Djamé Seddah. 2019. What does BERT learn about the structure of language?. In ACL 2019--57th Annual Meeting of the Association for Computational Linguistics.Google ScholarCross Ref
- Hamid Reza Vaezi Joze, Amirreza Shaban, Michael L Iuzzolino, and Kazuhito Koishida. 2020. MMTM: Multimodal transfer module for CNN fusion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 13289--13299.Google ScholarCross Ref
- Xincheng Ju, Dong Zhang, Junhui Li, and Guodong Zhou. 2020. Transformer-based label set generation for multi-modal multi-label emotion detection. In Proceedings of the 28th ACM International Conference on Multimedia. 512--520.Google ScholarDigital Library
- Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT. 4171--4186.Google Scholar
- Taeuk Kim, Kang Min Yoo, and Sang-goo Lee. 2021. Self-Guided Contrastive Learning for BERT Sentence Representations. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2528--2540.Google ScholarCross Ref
- Goro Kobayashi, Tatsuki Kuribayashi, Sho Yokoi, and Kentaro Inui. 2020. Attention is Not Only a Weight: Analyzing Transformers with Vector Norms. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, Online, 7057--7075. https://doi.org/10.18653/v1/2020.emnlp-main.574Google ScholarCross Ref
- Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2020. ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. In International Conference on Learning Representations. https://openreview.net/forum?id=H1eA7AEtvSGoogle Scholar
- Andy T Liu, Shu-wen Yang, Po-Han Chi, Po-chun Hsu, and Hung-yi Lee. 2020. Mockingjay: Unsupervised speech representation learning with deep bidirectional transformer encoders. In ICASSP 2020--2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 6419--6423.Google ScholarCross Ref
- Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. 2021. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 10012--10022.Google ScholarCross Ref
- Fengmao Lv, Xiang Chen, Yanyong Huang, Lixin Duan, and Guosheng Lin. 2021. Progressive modality reinforcement for human multimodal emotion recognition from unaligned multimodal sequences. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2554--2562.Google ScholarCross Ref
- Navonil Majumder, Soujanya Poria, Devamanyu Hazarika, Rada Mihalcea, Alexander Gelbukh, and Erik Cambria. 2019. Dialoguernn: An attentive rnn for emotion detection in conversations. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 6818--6825.Google ScholarDigital Library
- Ankita Pasad, Ju-Chieh Chou, and Karen Livescu. 2021. Layer-Wise Analysis of a Self-Supervised Speech Representation Model. In IEEE Automatic Speech Recognition and Understanding Workshop-ASRU 2021.Google ScholarCross Ref
- Han Shi, Jiahui Gao, Hang Xu, Xiaodan Liang, Zhenguo Li, Lingpeng Kong, Stephen M. S. Lee, and James Kwok. 2022. Revisiting Over-smoothing in BERT from the Perspective of Graph. In International Conference on Learning Representations. https://openreview.net/forum?id=dUV91uaXm3Google Scholar
- Edmund Tong, Amir Zadeh, Cara Jones, and Louis-Philippe Morency. 2017. Combating human trafficking with multimodal deep models. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 1547--1556.Google ScholarCross Ref
- Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Hervé Jégou. 2021. Training data-efficient image transformers & distillation through attention. In International Conference on Machine Learning. PMLR, 10347--10357.Google Scholar
- Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, J. Zico Kolter, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2019. Multimodal Transformer for Unaligned Multimodal Language Sequences. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy, 6558--6569. https://doi.org/10.18653/v1/P19--1656Google ScholarCross Ref
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008.Google Scholar
- Yang Wu, Zijie Lin, Yanyan Zhao, Bing Qin, and Li-Nan Zhu. 2021. A Text-Centered Shared-Private Framework via Cross-Modal Prediction for Multimodal Sentiment Analysis. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. Association for Computational Linguistics, Online, 4730--4738. https://doi.org/10.18653/v1/2021.findings-acl.417Google ScholarCross Ref
- Zeguan Xiao, Jiarun Wu, Qingliang Chen, and Congjian Deng. 2021. BERT4GCN: Using BERT Intermediate Layers to Augment GCN for Aspect-based Sentiment Classification. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 9193--9200.Google ScholarCross Ref
- Matthew D Zeiler and Rob Fergus. 2014. Visualizing and understanding convolutional networks. In European conference on computer vision. Springer, 818--833.Google ScholarCross Ref
Index Terms
- Leveraging Multi-modal Interactions among the Intermediate Representations of Deep Transformers for Emotion Recognition
Recommendations
Multi-modal Multi-cultural Dimensional Continues Emotion Recognition in Dyadic Interactions
AVEC'18: Proceedings of the 2018 on Audio/Visual Emotion Challenge and WorkshopAutomatic emotion recognition is a challenging task which can make great impact on improving natural human computer interactions. In this paper, we present our solutions for the Cross-cultural Emotion Sub-challenge (CES) of Audio/Visual Emotion ...
Dense Attention Memory Network for Multi-modal emotion recognition
MLNLP '22: Proceedings of the 2022 5th International Conference on Machine Learning and Natural Language ProcessingEmotion is a significant aspect of human communication. Speech, text, action, and other information are complementary to human communication, which helps the machine understand emotion better. In this paper, we propose a dense attention memory model (...
Real-time Emotion Pre-Recognition in Conversations with Contrastive Multi-modal Dialogue Pre-training
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge ManagementThis paper presents our pioneering effort in addressing a new and realistic scenario in multi-modal dialogue systems called Multi-modal Real-time Emotion Pre-recognition in Conversations (MREPC). The objective is to predict the emotion of a forthcoming ...
Comments