CoChat

HiCMAE: Hierarchical Contrastive Masked Autoencoder for self-supervised Audio-Visual Emotion Recognition

Open access
Sun, Licai, Lian, Zheng, Liu, Bin, Tao, Jianhua · 2024 · Information Fusion
Cited by 74

The DOI matches its Crossref record; 34 of the 34 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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.inffus.2024.102382

Cites

34 of 34 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Research works printed but not linked: 51

  1. Schwarz, 2000, Emotion, cognition, and decision making, Cogn. Emot., 14, 433, 10.1080/026999300402745 · DOI · Paper page
  2. Mehrabian, 1968, Communication without words, Psychol. Today, 2, 53
  3. 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
  4. 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
  5. Zhang, 2023, Transformer-based multimodal emotional perception for dynamic facial expression recognition in the wild, IEEE Trans. Circuits Syst. Video Technol.
  6. 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.
  7. Pei, 2024, Affective computing: Recent advances, challenges, and future trends, Intell. Comput., 3, 0076, 10.34133/icomputing.0076 · DOI
  8. Mao, 2022, The biases of pre-trained language models: An empirical study on prompt-based sentiment analysis and emotion detection, IEEE Trans. Affect. Comput.
  9. 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
  10. 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.
  11. 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.
  12. 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
  13. 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
  14. 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
  15. 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
  16. Cao, 2014, Crema-d: Crowd-sourced emotional multimodal actors dataset, IEEE Trans. Affect. Comput., 5, 377, 10.1109/TAFFC.2014.2336244 · DOI · Paper page
  17. 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
  18. 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
  19. 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
  20. Dalal, 2005, Histograms of oriented gradients for human detection, vol. 1, 886
  21. 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
  22. 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
  23. 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
  24. 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
  25. 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
  26. 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
  27. Sun, 2023, Efficient multimodal transformer with dual-level feature restoration for robust multimodal sentiment analysis, IEEE Trans. Affect. Comput.
  28. 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
  29. 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
  30. 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
  31. Vaswani, 2017, Attention is all you need, vol. 30
  32. 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
  33. 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
  34. 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
  35. 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
  36. Liu, 2023, Expression snippet transformer for robust video-based facial expression recognition, Pattern Recognit., 138, 10.1016/j.patcog.2023.109368 · DOI
  37. 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
  38. Li, 2023, Intensity-aware loss for dynamic facial expression recognition in the wild, vol. 37, 67
  39. 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
  40. 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
  41. 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
  42. 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
  43. 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
  44. 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
  45. Lei, 2023, Audio-visual emotion recognition with preference learning based on intended and multi-modal perceived labels, IEEE Trans. Affect. Comput., 1
  46. 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.
  47. 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.
  48. 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
  49. Mittal, 2022, Learning state-aware visual representations from audible interactions, Adv. Neural Inf. Process. Syst., 35, 23765
  50. Van der Maaten, 2008, Visualizing data using t-sne., J. Mach. Learn. Res., 9
  51. 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

See all 74

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
34
FWCI
29.92
Type
journal article
Language
en
Open access
green
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

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.