HiCMAE: Hierarchical Contrastive Masked Autoencoder for self-supervised Audio-Visual Emotion Recognition
Open accessThe DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.
Abstract
Audio-Visual Emotion Recognition (AVER) has garnered increasing attention in recent years for its critical role in creating emotion-ware intelligent machines. Previous efforts in this area are dominated by the supervised learning paradigm. Despite significant progress, supervised learning is meeting its bottleneck due to the longstanding data scarcity issue in AVER. Motivated by recent advances in self-supervised learning, we propose Hierarchical Contrastive Masked Autoencoder (HiCMAE), a novel self-supervised framework that leverages large-scale self-supervised pre-training on vast unlabeled audio-visual data to promote the advancement of AVER. Following prior arts in self-supervised audio-visual representation learning, HiCMAE adopts two primary forms of self-supervision for pre-training, namely masked data modeling and contrastive learning. Unlike them which focus exclusively on top-layer representations while neglecting explicit guidance of intermediate layers, HiCMAE develops a three-pronged strategy to foster hierarchical audio-visual feature learning and improve the overall quality of learned representations. To verify the effectiveness of HiCMAE, we conduct extensive experiments on 9 datasets covering both categorical and dimensional AVER tasks. Experimental results show that our method significantly outperforms state-of-the-art supervised and self-supervised audio-visual methods, which indicates that HiCMAE is a powerful audio-visual emotion representation learner. Codes and models will be publicly available at https://github.com/sunlicai/HiCMAE.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
Masked Autoencoders Are Scalable Vision Learners
He, K., Chen, X., Xie, S., Li, Y., Dollar, P., & Girshick, R. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01553 · Cited by 8,489 · cited 5×
“Motivated by its recent success in the image and video domain [10, 56, 57], Georgescu et al. [58] extended it to the audio-visual domain and achieve significant improvements over previous methods.”
BackgroundMethodInfluentialRepresentation Learning with Contrastive Predictive Coding
Oord, A. V. D., Li, Y., & Vinyals, O. (2018) · arXiv · doi:10.48550/arxiv.1807.03748 · Cited by 6,242 · cited 1×
“After that, we utilize symmetric InfoNCE loss [62] for HCMCL.”
MethodIEMOCAP: Interactive emotional dyadic motion capture database
Busso, C., Bulut, M., Lee, C.-C., Kazemzadeh, A., Mower, E., Kim, S., Chang, J. N., Lee, S., & Narayanan, S. S. (2008) · Language Resources and Evaluation · doi:10.1007/s10579-008-9076-6 · Cited by 3,869
A Closer Look at Spatiotemporal Convolutions for Action Recognition
Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., & Paluri, M. (2017) · arXiv · doi:10.48550/arxiv.1711.11248 · Cited by 3,664
VGGFace2: A Dataset for Recognising Faces across Pose and Age
Cao, Q., Shen, L., Xie, W., Parkhi, O. M., & Zisserman, A. (2018) · 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018) · doi:10.1109/fg.2018.00020 · Cited by 3,032
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
Hsu, W.-N., Bolte, B., Tsai, Y.-H. H., Lakhotia, K., Salakhutdinov, R., & Mohamed, A. (2021) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2021.3122291 · Cited by 2,983
A Survey of Affect Recognition Methods: Audio, Visual, and Spontaneous Expressions
Zeng, Z., Pantic, M., Roisman, G. I., & Huang, T. S. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2008.52 · Cited by 2,797
Research works printed but not linked: 51
- Schwarz, 2000, Emotion, cognition, and decision making, Cogn. Emot., 14, 433, 10.1080/026999300402745 · DOI · Paper page
- Mehrabian, 1968, Communication without words, Psychol. Today, 2, 53
- Wu, 2014, Survey on audiovisual emotion recognition: databases, features, and data fusion strategies, APSIPA Trans. Signal Inf. Process., 3, 10.1017/ATSIP.2014.11 · DOI · Paper page
- Y. Liu, W. Dai, C. Feng, W. Wang, G. Yin, J. Zeng, S. Shan, MAFW: A Large-scale, Multi-modal, Compound Affective Database for Dynamic Facial Expression Recognition in the Wild, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 24–32. · DOI · Paper page
- Zhang, 2023, Transformer-based multimodal emotional perception for dynamic facial expression recognition in the wild, IEEE Trans. Circuits Syst. Video Technol.
- Zhang, 2023, Deep learning-based multimodal emotion recognition from audio, visual, and text modalities: A systematic review of recent advancements and future prospects, Expert Syst. Appl.
- Pei, 2024, Affective computing: Recent advances, challenges, and future trends, Intell. Comput., 3, 0076, 10.34133/icomputing.0076 · DOI
- Mao, 2022, The biases of pre-trained language models: An empirical study on prompt-based sentiment analysis and emotion detection, IEEE Trans. Affect. Comput.
- W. Li, L. Zhu, R. Mao, E. Cambria, Skier: A symbolic knowledge integrated model for conversational emotion recognition, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2023. · DOI · Paper page
- Y. Gong, A. Rouditchenko, A.H. Liu, D. Harwath, L. Karlinsky, H. Kuehne, J.R. Glass, Contrastive Audio-Visual Masked Autoencoder, in: The Eleventh International Conference on Learning Representations, 2023.
- P.-Y. Huang, V. Sharma, H. Xu, C. Ryali, H. Fan, Y. Li, S.-W. Li, G. Ghosh, J. Malik, C. Feichtenhofer, MAViL: Masked Audio-Video Learners, in: Thirty-Seventh Conference on Neural Information Processing Systems, 2023.
- H. Wang, Y. Tang, Y. Wang, J. Guo, Z.-H. Deng, K. Han, Masked Image Modeling with Local Multi-Scale Reconstruction, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 2122–2131. · DOI
- Y. Liu, S. Zhang, J. Chen, Z. Yu, K. Chen, D. Lin, Improving pixel-based mim by reducing wasted modeling capability, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 5361–5372. · DOI
- Zhang, 2023, Werewolf-XL: A database for identifying spontaneous affect in large competitive group interactions, IEEE Trans. Affect. Comput., 14, 1201, 10.1109/TAFFC.2021.3101563 · DOI
- Z. Lian, H. Sun, L. Sun, K. Chen, M. Xu, K. Wang, K. Xu, Y. He, Y. Li, J. Zhao, et al., Mer 2023: Multi-label learning, modality robustness, and semi-supervised learning, in: Proceedings of the 31st ACM International Conference on Multimedia, 2023, pp. 9610–9614. · DOI
- Cao, 2014, Crema-d: Crowd-sourced emotional multimodal actors dataset, IEEE Trans. Affect. Comput., 5, 377, 10.1109/TAFFC.2014.2336244 · DOI · Paper page
- X. Jiang, Y. Zong, W. Zheng, C. Tang, W. Xia, C. Lu, J. Liu, Dfew: A large-scale database for recognizing dynamic facial expressions in the wild, in: Proceedings of the 28th ACM International Conference on Multimedia, 2020, pp. 2881–2889. · DOI · Paper page
- B. Schuller, S. Steidl, A. Batliner, A. Vinciarelli, K. Scherer, F. Ringeval, M. Chetouani, F. Weninger, F. Eyben, E. Marchi, et al., The INTERSPEECH 2013 computational paralinguistics challenge: Social signals, conflict, emotion, autism, in: Proceedings INTERSPEECH 2013, 14th Annual Conference of the International Speech Communication Association, Lyon, France, 2013. · DOI · Paper page
- Zhao, 2007, Dynamic texture recognition using local binary patterns with an application to facial expressions, IEEE Trans. Pattern Anal. Mach. Intell., 29, 915, 10.1109/TPAMI.2007.1110 · DOI · Paper page
- Dalal, 2005, Histograms of oriented gradients for human detection, vol. 1, 886
- L. Meng, Y. Liu, X. Liu, Z. Huang, W. Jiang, T. Zhang, C. Liu, Q. Jin, Valence and arousal estimation based on multimodal temporal-aware features for videos in the wild, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 2345–2352. · DOI
- D. Tran, L. Bourdev, R. Fergus, L. Torresani, M. Paluri, Learning spatiotemporal features with 3d convolutional networks, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 4489–4497. · DOI · Paper page
- Y. Wang, Y. Sun, Y. Huang, Z. Liu, S. Gao, W. Zhang, W. Ge, W. Zhang, FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 20922–20931. · DOI
- L. Sun, Z. Lian, B. Liu, J. Tao, MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition, in: Proceedings of the 31st ACM International Conference on Multimedia, 2023, pp. 6110–6121. · DOI
- Lian, 2021, Ctnet: Conversational transformer network for emotion recognition, IEEE/ACM Trans. Audio, Speech, Lang. Process., 29, 985, 10.1109/TASLP.2021.3049898 · DOI · Paper page
- Hsu, 2023, Applying segment-level attention on bi-modal transformer encoder for audio-visual emotion recognition, IEEE Trans. Affect. Comput., 10.1109/TAFFC.2023.3258900 · DOI
- Sun, 2023, Efficient multimodal transformer with dual-level feature restoration for robust multimodal sentiment analysis, IEEE Trans. Affect. Comput.
- R. Arandjelovic, A. Zisserman, Look, listen and learn, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 609–617. · DOI · Paper page
- P. Morgado, N. Vasconcelos, I. Misra, Audio-visual instance discrimination with cross-modal agreement, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 12475–12486. · DOI · Paper page
- M.-I. Georgescu, E. Fonseca, R.T. Ionescu, M. Lucic, C. Schmid, A. Arnab, Audiovisual masked autoencoders, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 16144–16154. · DOI · Paper page
- Vaswani, 2017, Attention is all you need, vol. 30
- Livingstone, 2018, The ryerson audio-visual database of emotional speech and song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in north American english, PLoS One, 13, 10.1371/journal.pone.0196391 · DOI · Paper page
- Z. Zhao, Q. Liu, Former-dfer: Dynamic facial expression recognition transformer, in: Proceedings of the 29th ACM International Conference on Multimedia, 2021, pp. 1553–1561. · DOI · Paper page
- K. Hara, H. Kataoka, Y. Satoh, Can spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet?, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 6546–6555. · DOI · Paper page
- Liu, 2022, Clip-aware expressive feature learning for video-based facial expression recognition, Inform. Sci., 598, 182, 10.1016/j.ins.2022.03.062 · DOI
- Liu, 2023, Expression snippet transformer for robust video-based facial expression recognition, Pattern Recognit., 138, 10.1016/j.patcog.2023.109368 · DOI
- Y. Wang, Y. Sun, W. Song, S. Gao, Y. Huang, Z. Chen, W. Ge, W. Zhang, DPCNet: Dual Path Multi-Excitation Collaborative Network for Facial Expression Representation Learning in Videos, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 101–110. · DOI
- Li, 2023, Intensity-aware loss for dynamic facial expression recognition in the wild, vol. 37, 67
- H. Wang, B. Li, S. Wu, S. Shen, F. Liu, S. Ding, A. Zhou, Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 17958–17968. · DOI
- J. Hu, L. Shen, G. Sun, Squeeze-and-excitation networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7132–7141. · DOI · Paper page
- Zhao, 2021, Learning deep global multi-scale and local attention features for facial expression recognition in the wild, IEEE Trans. Image Process., 30, 6544, 10.1109/TIP.2021.3093397 · DOI · Paper page
- M. Tran, Y. Kim, C.-C. Su, C.-H. Kuo, M. Soleymani, SAAML: A framework for semi-supervised affective adaptation via metric learning, in: Proceedings of the 31st ACM International Conference on Multimedia, 2023, pp. 6004–6015. · DOI
- A. Keesing, Y.S. Koh, V. Yogarajan, M. Witbrock, Emotion Recognition ToolKit (ERTK): Standardising Tools For Emotion Recognition Research, in: Proceedings of the 31st ACM International Conference on Multimedia, 2023, pp. 9693–9696. · DOI
- Goncalves, 2022, Robust audiovisual emotion recognition: Aligning modalities, capturing temporal information, and handling missing features, IEEE Trans. Affect. Comput., 13, 2156, 10.1109/TAFFC.2022.3216993 · DOI
- Lei, 2023, Audio-visual emotion recognition with preference learning based on intended and multi-modal perceived labels, IEEE Trans. Affect. Comput., 1
- B. Shi, W.-N. Hsu, K. Lakhotia, A. Mohamed, Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction, in: International Conference on Learning Representations, 2022.
- H.R.V. Joze, A. Shaban, M.L. Iuzzolino, K. Koishida, MMTM: Multimodal transfer module for CNN fusion, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 13289–13299.
- Verbitskiy, 2022, Eranns: Efficient residual audio neural networks for audio pattern recognition, Pattern Recognit. Lett., 161, 38, 10.1016/j.patrec.2022.07.012 · DOI
- Mittal, 2022, Learning state-aware visual representations from audible interactions, Adv. Neural Inf. Process. Syst., 35, 23765
- Van der Maaten, 2008, Visualizing data using t-sne., J. Mach. Learn. Res., 9
- R.R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, D. Batra, Grad-cam: Visual explanations from deep networks via gradient-based localization, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 618–626. · DOI · Paper page
Cited by
Chumachenko, K., Iosifidis, A., & Gabbouj, M. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00470 · Cited by 34
Xie, H. (2025) · Proceedings of the 2025 International Conference on Artificial Intelligence and Educational Systems · doi:10.1145/3744367.3744415
Dual-Space Masked Reconstruction for Robust Self-Supervised Human Activity Recognition
Xiao, S., Deng, J., Tang, C., & Huang, Z. (2025) · Proceedings of the 34th ACM International Conference on Information and Knowledge Management · doi:10.1145/3746252.3761215
“It have demonstrated remarkable success in com-putervisionandnaturallanguageprocessing domains[5][8][30][15].”
Metadata
- Authors
- Sun, L., Lian, Z., Liu, B., & Tao, J.
- Venue
- Information Fusion
- Publisher
- Elsevier BV
- Published
- 2024-08
- Volume
- 108
- Pages
- 102382
- ISSN
- 1566-2535 (ISSN-L)
- OpenAlex
- W4393181080
- Cited by
- 74
- References
- 32
- FWCI
- 29.92
- Type
- journal article
- Language
- en
- Open access
- green
- Licence
- www.elsevier.com/tdm/userlicense/1.0/ (tdm)
- www.elsevier.com/legal/tdmrep-license (tdm)
- doi.org/10.15223/policy-017 (stm-asf)
- doi.org/10.15223/policy-037 (stm-asf)
- doi.org/10.15223/policy-012 (stm-asf)
- doi.org/10.15223/policy-029 (stm-asf)
- doi.org/10.15223/policy-004 (stm-asf)
- Funders
- National Natural Science Foundation of China
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: HiCMAE: Hierarchical Contrastive Masked Autoencoder for self-supervised Audio-Visual Emotion Recognition. https://app.cochat.ai/papers/10.1016/j.inffus.2024.102382
- The paper
- Sun, L., Lian, Z., Liu, B., & Tao, J. (2024). HiCMAE: Hierarchical Contrastive Masked Autoencoder for self-supervised Audio-Visual Emotion Recognition. Information Fusion. https://doi.org/10.1016/j.inffus.2024.102382
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.