---
title: "CaM-HG — paper by Yang et al. (2026) — summary and ideas"
description: "The authors argue that a missing modality is more than lost data. 30 references. Among them: 0."
authors: ["Mingjian Yang", "Yong Wang", "Peng Liu", "Wen Yin"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.813/"
doi: "10.18653/v1/2026.findings-acl.813"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/yang-2026-cam-hg-causal-enhanced-moe/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yang-2026-cam-hg-causal-enhanced-moe/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/25/) / CaM-HG: Causal-Enhanced MoE and Hypergraphs Network for Incomplete Multimodal Emotion Recognition in Conversations

# CaM-HG: Causal-Enhanced MoE and Hypergraphs Network for Incomplete Multimodal Emotion Recognition in Conversations

**Authors:** Mingjian Yang, [Yong Wang](https://md.research.elamur.ai/free/en/authors/yong-wang/), [Peng Liu](https://md.research.elamur.ai/free/en/authors/peng-liu/) and Wen Yin · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.813/) · [PDF](https://aclanthology.org/2026.findings-acl.813.pdf) · [DOI 10.18653/v1/2026.findings-acl.813](https://doi.org/10.18653/v1/2026.findings-acl.813) · [OpenAlex](https://openalex.org/W7166871066)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
The paper tackles multimodal emotion recognition in conversation (MERC) when some text, audio, or visual inputs are missing. The authors argue that a missing modality is more than lost data. It breaks the fine-grained cross-modal cause-and-effect links that later emotional reactions depend on, and this damage spreads to subsequent turns. Their framework, CaM-HG, follows a two-step "restore-then-mine" design. First, a Causal-Enhanced Mixture-of-Experts uses dialogue history to generate substitute features for absent modalities, so the conversation graph has no empty nodes. Second, an Asymmetric Causal Dynamic Hypergraph models high-order (beyond pairwise) relations among the restored nodes. A Block Causal Mask keeps modalities of the same utterance together while preventing any access to future turns. The model is evaluated on IEMOCAP, CMU-MOSI, and CMU-MOSEI across different missing rates and outperforms strong baselines such as MMIN, GCNet, and SDR-GNN. The work matters because real deployments often lose modalities, and it frames robustness as a matter of causal consistency rather than statistical reconstruction alone.

## Key points
- Reported WAF1 gains over prior state of the art are 1.43% on four-class IEMOCAP and 1.25% on six-class IEMOCAP.
- Features come from pre-trained extractors: DeBERTa-large for text, Wav2Vec 2.0 for audio, and MANet for visual input. During training, random modality masking is combined with an extra text-dropping step (p = 0.25) to reduce over-reliance on text.
- In the ablation on six-class IEMOCAP, removing the causal factor extractor lowers WAF1 from 59.00% to 50.96% at missing rate η = 0.5. Swapping the hypergraph for a Transformer lowers it from 63.68% to 58.69% at η = 0.0.
- The ablation also tests variants without imputation, without the MoE (replaced by a single MLP), and without gating. Every variant performs worse than the full model.
- The authors list two limitations: prolonged extreme missingness remains hard, and the method addresses temporal causality only, not structural causal discovery.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of Electronic Science and Technology of China](https://md.research.elamur.ai/free/en/universities/university-of-electronic-science-and-technology-of-china/) — University, Chengdu, China · 38 works · 2,088 citations

📚 Shelves (7): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,649 works · [💭 Experimental and Cognitive Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/experimental-and-cognitive-psychology/) · 930 works · [🔊 Signal Processing](https://md.research.elamur.ai/free/en/shelves/computer-science/signal-processing/) · 493 works

🧭 Topics (2): [😊 Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · 1,035 works · [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 811 works

## Cite

Cite as: Mingjian Yang, Yong Wang, Peng Liu and Wen Yin. 2026. CaM-HG: Causal-Enhanced MoE and Hypergraphs Network for Incomplete Multimodal Emotion Recognition in Conversations. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{yang2026cam,
  title = {{CaM-HG: Causal-Enhanced MoE and Hypergraphs Network for Incomplete Multimodal Emotion Recognition in Conversations}},
  author = {Mingjian Yang, Yong Wang, Peng Liu and Wen Yin},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.813},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.813}
}
```

- [← previous Call Support Copilot: A Reproducible Multimodal System for Speech Emotion Recognition, Intent Understanding, and Agent Assistance](https://md.research.elamur.ai/free/en/papers/rakhmatillokhon-2026-call-support-copilot-reproducible-multimodal/)
- [next → CAMEC: Complexity-Aware Multi-Expert Collaboration for Reliable Chinese Medical Question Answering](https://md.research.elamur.ai/free/en/papers/wu-2026-camec-complexity-aware-multi-expert/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/25/)

## References

30 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Wei Ai, Fuchen Zhang, Yuntao Shou, Tao Meng, Haowen Chen, and Keqin Li. 2025. Revisiting multimodal emotion recognition in conversation from the perspective of graph spectrum. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 11418–11426. [find](https://scholar.google.com/scholar?q=Wei+Ai%2C+Fuchen+Zhang%2C+Yuntao+Shou%2C+Tao+Meng%2C+Haowen+Chen%2C+and+Keqin+Li%2E+2025%2E+Revisiting+multimodal+emotion+recognition+in+conversation+from+the+perspective+of+graph+spectrum%2E+In+Proceedings+of+the+AA)
2. Xuping Chen and Wuzhen Shi. 2025. Dynamic interactive bimodal hypergraph networks for emotion recognition in conversations. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 1256–1264. [find](https://scholar.google.com/scholar?q=Xuping+Chen+and+Wuzhen+Shi%2E+2025%2E+Dynamic+interactive+bimodal+hypergraph+networks+for+emotion+recognition+in+conversations%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+volume+39%2C)
3. Fangze Fu, Wei Ai, Fan Yang, Yuntao Shou, Tao Meng, and Keqin Li. 2025. Sdr-gnn: spectral domain reconstruction graph neural network for incomplete multimodal learning in conversational emotion recognition. Knowledge-Based Systems, 309:112825. [find](https://scholar.google.com/scholar?q=Fangze+Fu%2C+Wei+Ai%2C+Fan+Yang%2C+Yuntao+Shou%2C+Tao+Meng%2C+and+Keqin+Li%2E+2025%2E+Sdr%2Dgnn%3A+spectral+domain+reconstruction+graph+neural+network+for+incomplete+multimodal+learning+in+conversational+emotion+recogn)
4. Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2020. [Deberta: Decoding-enhanced bert with disentangled attention](https://md.research.elamur.ai/free/en/papers/he-2020-deberta-decoding-enhanced-bert-disentangled/). arXiv preprint arXiv:2006.03654.
5. Ziyi Li, Wei-Long Zheng, and Bao-Liang Lu. 2025. Multimodal emotion recognition with missing modality via a unified multi-task pre-training framework. In Proceedings of the 33rd ACM International Conference on Multimedia, pages 5717–5725. [find](https://scholar.google.com/scholar?q=Ziyi+Li%2C+Wei%2DLong+Zheng%2C+and+Bao%2DLiang+Lu%2E+2025%2E+Multimodal+emotion+recognition+with+missing+modality+via+a+unified+multi%2Dtask+pre%2Dtraining+framework%2E+In+Proceedings+of+the+33rd+ACM+International+Conf)
6. Zheng Lian, Lan Chen, Licai Sun, Bin Liu, and Jianhua Tao. 2023. Gcnet: Graph completion network for incomplete multimodal learning in conversation. IEEE Transactions on pattern analysis and machine intelligence, 45(7):8419–8432. [find](https://scholar.google.com/scholar?q=Zheng+Lian%2C+Lan+Chen%2C+Licai+Sun%2C+Bin+Liu%2C+and+Jianhua+Tao%2E+2023%2E+Gcnet%3A+Graph+completion+network+for+incomplete+multimodal+learning+in+conversation%2E+IEEE+Transactions+on+pattern+analysis+and+machine+i)
7. Rui Liu, Haolin Zuo, Zheng Lian, Björn W Schuller, and Haizhou Li. 2024. Contrastive learning based modality-invariant feature acquisition for robust multimodal emotion recognition with missing modalities. IEEE Transactions on Affective Computing, 15(4):1856–1873. [find](https://scholar.google.com/scholar?q=Rui+Liu%2C+Haolin+Zuo%2C+Zheng+Lian%2C+Bj%C3%B6rn+W+Schuller%2C+and+Haizhou+Li%2E+2024%2E+Contrastive+learning+based+modality%2Dinvariant+feature+acquisition+for+robust+multimodal+emotion+recognition+with+missing+modali)
8. Nannan Lu, Zhiyuan Han, and Zhen Tan. 2024. A hypergraph based contextual relationship modeling method for multimodal emotion recognition in conversation. IEEE Transactions on Multimedia. [find](https://scholar.google.com/scholar?q=Nannan+Lu%2C+Zhiyuan+Han%2C+and+Zhen+Tan%2E+2024%2E+A+hypergraph+based+contextual+relationship+modeling+method+for+multimodal+emotion+recognition+in+conversation%2E+IEEE+Transactions+on+Multimedia%2E)
9. Xiaosen Lyu, Jiayu Xiong, Yuren Chen, Wanlong Wang, Xiaoqing Dai, and Jing Wang. 2025. Cross-space synergy: A unified framework for multimodal emotion recognition in conversation. arXiv preprint arXiv:2512.03521. — [arXiv:2512.03521](https://arxiv.org/abs/2512.03521) [find](https://scholar.google.com/scholar?q=Xiaosen+Lyu%2C+Jiayu+Xiong%2C+Yuren+Chen%2C+Wanlong+Wang%2C+Xiaoqing+Dai%2C+and+Jing+Wang%2E+2025%2E+Cross%2Dspace+synergy%3A+A+unified+framework+for+multimodal+emotion+recognition+in+conversation%2E+arXiv+preprint+arXiv)
10. Hui Ma, Jian Wang, Hongfei Lin, Bo Zhang, Yijia Zhang, and Bo Xu. 2023. A transformer-based model with self-distillation for multimodal emotion recognition in conversations. IEEE Transactions on Multimedia, 26:776–788. [find](https://scholar.google.com/scholar?q=Hui+Ma%2C+Jian+Wang%2C+Hongfei+Lin%2C+Bo+Zhang%2C+Yijia+Zhang%2C+and+Bo+Xu%2E+2023%2E+A+transformer%2Dbased+model+with+self%2Ddistillation+for+multimodal+emotion+recognition+in+conversations%2E+IEEE+Transactions+on+Multi)
11. Soujanya Poria, Navonil Majumder, Devamanyu Hazarika, Deepanway Ghosal, Rishabh Bhardwaj, Samson Yu Bai Jian, Pengfei Hong, Romila Ghosh, Abhinaba Roy, Niyati Chhaya, and 1 others. 2021. Recognizing emotion cause in conversations. Cognitive Computation, 13(5):1317–1332. [find](https://scholar.google.com/scholar?q=Soujanya+Poria%2C+Navonil+Majumder%2C+Devamanyu+Hazarika%2C+Deepanway+Ghosal%2C+Rishabh+Bhardwaj%2C+Samson+Yu+Bai+Jian%2C+Pengfei+Hong%2C+Romila+Ghosh%2C+Abhinaba+Roy%2C+Niyati+Chhaya%2C+and+1+others%2E+2021%2E+Recognizing+e)
12. Xihang Qiu, Jiarong Cheng, Yuhao Fang, Wanpeng Zhang, Yao Lu, Ye Zhang, and Chun Li. 2025. Federated dialogue-semantic diffusion for emotion recognition under incomplete modalities. arXiv preprint arXiv:2511.00344. — [arXiv:2511.00344](https://arxiv.org/abs/2511.00344) [find](https://scholar.google.com/scholar?q=Xihang+Qiu%2C+Jiarong+Cheng%2C+Yuhao+Fang%2C+Wanpeng+Zhang%2C+Yao+Lu%2C+Ye+Zhang%2C+and+Chun+Li%2E+2025%2E+Federated+dialogue%2Dsemantic+diffusion+for+emotion+recognition+under+incomplete+modalities%2E+arXiv+preprint+arX)
13. Steffen Schneider, Alexei Baevski, Ronan Collobert, and Michael Auli. 2019. wav2vec: Unsupervised pre-training for speech recognition. arXiv preprint arXiv:1904.05862. [find](https://scholar.google.com/scholar?q=Steffen+Schneider%2C+Alexei+Baevski%2C+Ronan+Collobert%2C+and+Michael+Auli%2E+2019%2E+wav2vec%3A+Unsupervised+pre%2Dtraining+for+speech+recognition%2E+arXiv+preprint+arXiv%3A1904%2E05862%2E)
14. Jiandong Shi, Ming Li, Lu Bai, Feilong Cao, Ke Lu, and Jiye Liang. 2025. Match: Modality-calibrated hypergraph fusion network for conversational emotion recognition. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, pages 6164–6172. [find](https://scholar.google.com/scholar?q=Jiandong+Shi%2C+Ming+Li%2C+Lu+Bai%2C+Feilong+Cao%2C+Ke+Lu%2C+and+Jiye+Liang%2E+2025%2E+Match%3A+Modality%2Dcalibrated+hypergraph+fusion+network+for+conversational+emotion+recognition%2E+In+Proceedings+of+the+Thirty%2DFourt)
15. Yuntao Shou, Jun Yao, Tao Meng, Wei Ai, Cen Chen, and Keqin Li. 2025. Gsdnet: Revisiting incomplete multimodal-diffusion from graph spectrum perspective for conversation emotion recognition. arXiv preprint arXiv:2506.12325. — [arXiv:2506.12325](https://arxiv.org/abs/2506.12325) [find](https://scholar.google.com/scholar?q=Yuntao+Shou%2C+Jun+Yao%2C+Tao+Meng%2C+Wei+Ai%2C+Cen+Chen%2C+and+Keqin+Li%2E+2025%2E+Gsdnet%3A+Revisiting+incomplete+multimodal%2Ddiffusion+from+graph+spectrum+perspective+for+conversation+emotion+recognition%2E+arXiv+pre)
16. Darshan Solanki, Hsia-Ming Hsu, Olivia Zhao, Renyue Zhang, Weihao Bi, and Raman Kannan. 2020. The way we think about ourselves. In International Conference on Human-Computer Interaction, pages 276– 285. Springer. [find](https://scholar.google.com/scholar?q=Darshan+Solanki%2C+Hsia%2DMing+Hsu%2C+Olivia+Zhao%2C+Renyue+Zhang%2C+Weihao+Bi%2C+and+Raman+Kannan%2E+2020%2E+The+way+we+think+about+ourselves%2E+In+International+Conference+on+Human%2DComputer+Interaction%2C+pages+276%E2%80%93+28)
17. Luan Tran, Xiaoming Liu, Jiayu Zhou, and Rong Jin. 2017. Missing modalities imputation via cascaded residual autoencoder. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1405–1414. [find](https://scholar.google.com/scholar?q=Luan+Tran%2C+Xiaoming+Liu%2C+Jiayu+Zhou%2C+and+Rong+Jin%2E+2017%2E+Missing+modalities+imputation+via+cascaded+residual+autoencoder%2E+In+Proceedings+of+the+IEEE+conference+on+computer+vision+and+pattern+recogniti)
18. Weiran Wang, Raman Arora, Karen Livescu, and Jeff Bilmes. 2015. On deep multi-view representation learning. In International conference on machine learning, pages 1083–1092. PMLR. [find](https://scholar.google.com/scholar?q=Weiran+Wang%2C+Raman+Arora%2C+Karen+Livescu%2C+and+Jeff+Bilmes%2E+2015%2E+On+deep+multi%2Dview+representation+learning%2E+In+International+conference+on+machine+learning%2C+pages+1083%E2%80%931092%2E+PMLR%2E)
19. Yuanzhi Wang, Zhen Cui, and Yong Li. 2023a. Distribution-consistent modal recovering for incomplete multimodal learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 22025–22034. [find](https://scholar.google.com/scholar?q=Yuanzhi+Wang%2C+Zhen+Cui%2C+and+Yong+Li%2E+2023a%2E+Distribution%2Dconsistent+modal+recovering+for+incomplete+multimodal+learning%2E+In+Proceedings+of+the+IEEE%2FCVF+International+Conference+on+Computer+Vision%2C+pag)
20. Yuanzhi Wang, Yong Li, and Zhen Cui. 2023b. Incomplete multimodality-diffused emotion recognition. Advances in Neural Information Processing Systems, 36:17117–17128. [find](https://scholar.google.com/scholar?q=Yuanzhi+Wang%2C+Yong+Li%2C+and+Zhen+Cui%2E+2023b%2E+Incomplete+multimodality%2Ddiffused+emotion+recognition%2E+Advances+in+Neural+Information+Processing+Systems%2C+36%3A17117%E2%80%9317128%2E)
21. Yusong Wang, Xuanye Fang, Huifeng Yin, Dongyuan Li, Guoqi Li, Qi Xu, Yi Xu, Shuai Zhong, and Mingkun Xu. 2025. Big-fusion: Brain-inspired global-local context fusion framework for multimodal emotion recognition in conversations. In Proceedings of the AAAI Conference on Artificial Intelligence, volum… [find](https://scholar.google.com/scholar?q=Yusong+Wang%2C+Xuanye+Fang%2C+Huifeng+Yin%2C+Dongyuan+Li%2C+Guoqi+Li%2C+Qi+Xu%2C+Yi+Xu%2C+Shuai+Zhong%2C+and+Mingkun+Xu%2E+2025%2E+Big%2Dfusion%3A+Brain%2Dinspired+global%2Dlocal+context+fusion+framework+for+multimodal+emotion+r)
22. Wen Yin, Yong Wang, Guiduo Duan, Dongyang Zhang, Xin Hu, Yuan-Fang Li, and Tao He. 2025. Knowledge-aligned counterfactual-enhancement diffusion perception for unsupervised cross-domain visual emotion recognition. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 3888–38… [find](https://scholar.google.com/scholar?q=Wen+Yin%2C+Yong+Wang%2C+Guiduo+Duan%2C+Dongyang+Zhang%2C+Xin+Hu%2C+Yuan%2DFang+Li%2C+and+Tao+He%2E+2025%2E+Knowledge%2Daligned+counterfactual%2Denhancement+diffusion+perception+for+unsupervised+cross%2Ddomain+visual+emotion+)
23. Wen Yin, Siyu Zhan, Cencen Liu, Xin Hu, Guiduo Duan, Xiurui Xie, Yuan-Fang Li, and Tao He. 2026. Tical: Typicality-based consistency-aware learning for multimodal emotion recognition. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 40, pages 17948–17956. [find](https://scholar.google.com/scholar?q=Wen+Yin%2C+Siyu+Zhan%2C+Cencen+Liu%2C+Xin+Hu%2C+Guiduo+Duan%2C+Xiurui+Xie%2C+Yuan%2DFang+Li%2C+and+Tao+He%2E+2026%2E+Tical%3A+Typicality%2Dbased+consistency%2Daware+learning+for+multimodal+emotion+recognition%2E+In+Proceedings+o)
24. Jiaxuan You, Xiaobai Ma, Yi Ding, Mykel J Kochenderfer, and Jure Leskovec. 2020. Handling missing data with graph representation learning. Advances in Neural Information Processing Systems, 33:19075– 19087. [find](https://scholar.google.com/scholar?q=Jiaxuan+You%2C+Xiaobai+Ma%2C+Yi+Ding%2C+Mykel+J+Kochenderfer%2C+and+Jure+Leskovec%2E+2020%2E+Handling+missing+data+with+graph+representation+learning%2E+Advances+in+Neural+Information+Processing+Systems%2C+33%3A19075%E2%80%93+)
25. Amir Zadeh, Rowan Zellers, Eli Pincus, and Louis-Philippe Morency. 2016. Multimodal sentiment intensity analysis in videos: Facial gestures and verbal messages. IEEE Intelligent Systems, 31(6):82–88. [find](https://scholar.google.com/scholar?q=Amir+Zadeh%2C+Rowan+Zellers%2C+Eli+Pincus%2C+and+Louis%2DPhilippe+Morency%2E+2016%2E+Multimodal+sentiment+intensity+analysis+in+videos%3A+Facial+gestures+and+verbal+messages%2E+IEEE+Intelligent+Systems%2C+31%286%29%3A82%E2%80%9388%2E)
26. AmirAli Bagher Zadeh, Paul Pu Liang, Soujanya Poria, Erik Cambria, and Louis-Philippe Morency. 2018. [Multimodal language analysis in the wild: Cmu-mosei dataset and interpretable dynamic fusion graph](https://md.research.elamur.ai/free/en/papers/zadeh-2018-multimodal-language-analysis-wild-cmu/). In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume…
27. Tao Zhang and Zhenhua Tan. 2025. Ecerc: evidence-cause attention network for multi-modal emotion recognition in conversation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2064–2077. [find](https://scholar.google.com/scholar?q=Tao+Zhang+and+Zhenhua+Tan%2E+2025%2E+Ecerc%3A+evidence%2Dcause+attention+network+for+multi%2Dmodal+emotion+recognition+in+conversation%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+Association+for+Computati)
28. Jinming Zhao, Ruichen Li, and Qin Jin. 2021a. Missing modality imagination network for emotion recognition with uncertain missing modalities. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Pro… [find](https://scholar.google.com/scholar?q=Jinming+Zhao%2C+Ruichen+Li%2C+and+Qin+Jin%2E+2021a%2E+Missing+modality+imagination+network+for+emotion+recognition+with+uncertain+missing+modalities%2E+In+Proceedings+of+the+59th+Annual+Meeting+of+the+Associati)
29. Zengqun Zhao, Qingshan Liu, and Shanmin Wang. 2021b. Learning deep global multi-scale and local attention features for facial expression recognition in the wild. IEEE Transactions on Image Processing, 30:6544–6556. [find](https://scholar.google.com/scholar?q=Zengqun+Zhao%2C+Qingshan+Liu%2C+and+Shanmin+Wang%2E+2021b%2E+Learning+deep+global+multi%2Dscale+and+local+attention+features+for+facial+expression+recognition+in+the+wild%2E+IEEE+Transactions+on+Image+Processing%2C)
30. Xianxun Zhu, Yaoyang Wang, Erik Cambria, Imad Rida, José Santamaría López, Lin Cui, and Rui Wang. 2025. Rmer-dt: Robust multimodal emotion recognition in conversational contexts based on diffusion and transformers. Information Fusion, page 103268. [find](https://scholar.google.com/scholar?q=Xianxun+Zhu%2C+Yaoyang+Wang%2C+Erik+Cambria%2C+Imad+Rida%2C+Jos%C3%A9+Santamar%C3%ADa+L%C3%B3pez%2C+Lin+Cui%2C+and+Rui+Wang%2E+2025%2E+Rmer%2Ddt%3A+Robust+multimodal+emotion+recognition+in+conversational+contexts+based+on+diffusion+and)

*Updated 2 November 2026*