---
title: "MoLAN — paper by Xu et al. (2026) — summary and ideas"
description: "The authors propose MoLAN, a plug-in framework that works at a finer level. 50 references, cited by 1 paper here."
authors: ["Xingle Xu", "YongKang Liu", "Dexian Cai", "Shi Feng", "Xiaocui Yang", "Daling Wang", "Yifei Zhang"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1225/"
doi: "10.18653/v1/2026.findings-acl.1225"
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/xu-2026-molan-unified-modality-aware-noise/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/xu-2026-molan-unified-modality-aware-noise/)

[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/15/) / MoLAN: A Unified Modality-Aware Noise Dynamic Editing Framework for Multimodal Sentiment Analysis

# MoLAN: A Unified Modality-Aware Noise Dynamic Editing Framework for Multimodal Sentiment Analysis

**Authors:** [Xingle Xu](https://md.research.elamur.ai/free/en/authors/xingle-xu/), [YongKang Liu](https://md.research.elamur.ai/free/en/authors/yongkang-liu/), [Dexian Cai](https://md.research.elamur.ai/free/en/authors/dexian-cai/), [Shi Feng](https://md.research.elamur.ai/free/en/authors/shi-feng/), [Xiaocui Yang](https://md.research.elamur.ai/free/en/authors/xiaocui-yang/), [Daling Wang](https://md.research.elamur.ai/free/en/authors/daling-wang/) and [Yifei Zhang](https://md.research.elamur.ai/free/en/authors/yifei-zhang/) · **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.1225/) · [PDF](https://aclanthology.org/2026.findings-acl.1225.pdf) · [DOI 10.18653/v1/2026.findings-acl.1225](https://doi.org/10.18653/v1/2026.findings-acl.1225) · [OpenAlex](https://openalex.org/W7166845707)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · 1 in our library, of the 149,439 papers whose bibliographies we read

## Summary
Multimodal sentiment analysis (MSA) models often get misled by irrelevant visual or acoustic signals, such as background laughter that contradicts a speaker's mood. Earlier denoising methods treat a whole modality as one unit, so removing noise also tends to remove useful cues. The authors propose MoLAN, a plug-in framework that works at a finer level. It splits visual features into 2D blocks and audio features into 1D segments, then scales each block by its own denoising strength. That strength comes from the block's similarity to the text representation. Because MoLAN is modular, it can be added to existing MSA models and multimodal LLMs.

On top of it, the authors build MoLAN+, which adds two components:
- a cross-attention mask driven by the denoising signal;
- a contrastive objective linking denoised and original features.

Experiments on four benchmark datasets show consistent gains for host models, and MoLAN+ reports state-of-the-art results. The work matters because it suppresses noise selectively while keeping the information that sentiment prediction needs.

## Key points
- **Block size:** The block dimensions are factors of the feature sequence length and hidden size, chosen as the factors closest to their square roots. This aims for balanced blocks that are neither too coarse nor too fragmented.
- **Denoising strength:** Each block's strength is a cosine-style similarity between the reshaped block and the text features, clipped to [0, 1] to avoid sign flips. Text serves as the guiding modality.
- **MoLAN+ components:** MoLAN+ adds noise-suppressed cross-attention (w/o NC in ablations) and denoising-driven contrastive learning (w/o DC). Removing either one lowers performance.
- **Ablations:**
  - Uniform denoising strength (w/o DE) performs worse than dynamic editing.
  - Uniform 1D partitioning (w/o MB) performs worse than the modality-specific scheme.
  - Swapped schemes (v(1D), a(2D)) and all-2D partitioning also perform worse.
  - Denoising only visual (MoLAN(v)) or only audio (MoLAN(a)) still helps, but less than joint denoising.
- **Scope and code:** The paper reports evaluation across five models (seven in the contributions list) and four datasets. Code is available at github.com/betterfly123/MoLAN-Framework. The stated limitations are reliance on the quality of the guiding modality and no testing in cross-domain or open real-world settings.

*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

- [Northeastern University](https://md.research.elamur.ai/free/en/universities/northeastern-university-cn/) — University, Shenyang, China · 53 works · 2,205 citations

📚 Shelves (5): [🖥️ 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 · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 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

🧭 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: Xingle Xu, YongKang Liu, Dexian Cai, Shi Feng, Xiaocui Yang, Daling Wang and Yifei Zhang. 2026. MoLAN: A Unified Modality-Aware Noise Dynamic Editing Framework for Multimodal Sentiment Analysis. 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{xu2026molan,
  title = {{MoLAN: A Unified Modality-Aware Noise Dynamic Editing Framework for Multimodal Sentiment Analysis}},
  author = {Xingle Xu, YongKang Liu, Dexian Cai, Shi Feng, Xiaocui Yang, Daling Wang and Yifei Zhang},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1225},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1225}
}
```

- [← previous ModusPonens at SemEval-2026 Task 11: Breaking the Plausibility Trap in LLMs via Conflict-Aware Ensembling](https://md.research.elamur.ai/free/en/papers/roy-2026-modusponens-semeval-2026-task-11/)
- [next → Momentum at SemEval-2026 Task 2: LongVA-RoBERTa, a transformer-Based Longitudinal Valence and Arousal Modeling](https://md.research.elamur.ai/free/en/papers/nadiger-2026-momentum-semeval-2026-task-2/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/15/)

## References

50 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, and 1 others. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923. — [Qwen2.5-VL Technical Report](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen2-5-vl-technical/)
2. Carlos Busso, Murtaza Bulut, Chi-Chun Lee, Ebrahim (Abe) Kazemzadeh, Emily Mower Provost, Samuel Kim, Jeannette N. Chang, Sungbok Lee, and Shrikanth S. Narayanan. 2008. Iemocap: interactive emotional dyadic motion capture database. Language Resources and Evaluation, 42:335–359. [find](https://scholar.google.com/scholar?q=Carlos+Busso%2C+Murtaza+Bulut%2C+Chi%2DChun+Lee%2C+Ebrahim+%28Abe%29+Kazemzadeh%2C+Emily+Mower+Provost%2C+Samuel+Kim%2C+Jeannette+N%2E+Chang%2C+Sungbok+Lee%2C+and+Shrikanth+S%2E+Narayanan%2E+2008%2E+Iemocap%3A+interactive+emotional+)
3. Zebang Cheng, Zhi-Qi Cheng, Jun-Yan He, Jingdong Sun, Kai Wang, Yuxiang Lin, Zheng Lian, Xiaojiang Peng, and Alexander G Hauptmann. 2024. Emotion-llama: Multimodal emotion recognition and reasoning with instruction tuning. Advances in Neural Information Processing Systems, 37:110805–110853. [find](https://scholar.google.com/scholar?q=Zebang+Cheng%2C+Zhi%2DQi+Cheng%2C+Jun%2DYan+He%2C+Jingdong+Sun%2C+Kai+Wang%2C+Yuxiang+Lin%2C+Zheng+Lian%2C+Xiaojiang+Peng%2C+and+Alexander+G+Hauptmann%2E+2024%2E+Emotion%2Dllama%3A+Multimodal+emotion+recognition+and+reasoning+wi)
4. Cunhang Fan, Kang Zhu, Jianhua Tao, Guofeng Yi, Jun Xue, and Zhao Lv. 2024. Multi-level contrastive learning: Hierarchical alleviation of heterogeneity in multimodal sentiment analysis. IEEE Transactions on Affective Computing. [find](https://scholar.google.com/scholar?q=Cunhang+Fan%2C+Kang+Zhu%2C+Jianhua+Tao%2C+Guofeng+Yi%2C+Jun+Xue%2C+and+Zhao+Lv%2E+2024%2E+Multi%2Dlevel+contrastive+learning%3A+Hierarchical+alleviation+of+heterogeneity+in+multimodal+sentiment+analysis%2E+IEEE+Transacti)
5. Xinyu Feng, Yuming Lin, Lihua He, You Li, Liang Chang, and Ya Zhou. 2024. Knowledge-guided dynamic modality attention fusion framework for multimodal sentiment analysis. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 14755–14766. [find](https://scholar.google.com/scholar?q=Xinyu+Feng%2C+Yuming+Lin%2C+Lihua+He%2C+You+Li%2C+Liang+Chang%2C+and+Ya+Zhou%2E+2024%2E+Knowledge%2Dguided+dynamic+modality+attention+fusion+framework+for+multimodal+sentiment+analysis%2E+In+Findings+of+the+Association)
6. Jiwei Guo, Jiajia Tang, Weichen Dai, Yu Ding, and Wanzeng Kong. 2022. Dynamically adjust word representations using unaligned multimodal information. In Proceedings of the 30th ACM International Conference on Multimedia, MM ’22, page 3394–3402, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Jiwei+Guo%2C+Jiajia+Tang%2C+Weichen+Dai%2C+Yu+Ding%2C+and+Wanzeng+Kong%2E+2022%2E+Dynamically+adjust+word+representations+using+unaligned+multimodal+information%2E+In+Proceedings+of+the+30th+ACM+International+Confe)
7. Zirun Guo, Tao Jin, and Zhou Zhao. 2024. Multimodal prompt learning with missing modalities for sentiment analysis and emotion recognition. In ACL, pages 1726–1736. [find](https://scholar.google.com/scholar?q=Zirun+Guo%2C+Tao+Jin%2C+and+Zhou+Zhao%2E+2024%2E+Multimodal+prompt+learning+with+missing+modalities+for+sentiment+analysis+and+emotion+recognition%2E+In+ACL%2C+pages+1726%E2%80%931736%2E)
8. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, and 1 others. 2022a. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). ICLR, 1(2):3.
9. Guimin Hu, Ting-En Lin, Yi Zhao, Guangming Lu, Yuchuan Wu, and Yongbin Li. 2022b. UniMSE: Towards unified multimodal sentiment analysis and emotion recognition. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7837–7851, Abu Dhabi, United Arab Emirates… [find](https://scholar.google.com/scholar?q=Guimin+Hu%2C+Ting%2DEn+Lin%2C+Yi+Zhao%2C+Guangming+Lu%2C+Yuchuan+Wu%2C+and+Yongbin+Li%2E+2022b%2E+UniMSE%3A+Towards+unified+multimodal+sentiment+analysis+and+emotion+recognition%2E+In+Proceedings+of+the+2022+Conference+o)
10. Xun Jiang, Xing Xu, Huimin Lu, Lianghua He, and Heng Tao Shen. 2024. Joint objective and subjective fuzziness denoising for multimodal sentiment analysis. IEEE Transactions on Fuzzy Systems. [find](https://scholar.google.com/scholar?q=Xun+Jiang%2C+Xing+Xu%2C+Huimin+Lu%2C+Lianghua+He%2C+and+Heng+Tao+Shen%2E+2024%2E+Joint+objective+and+subjective+fuzziness+denoising+for+multimodal+sentiment+analysis%2E+IEEE+Transactions+on+Fuzzy+Systems%2E)
11. Feng Li, Renrui Zhang, Hao Zhang, Yuanhan Zhang, Bo Li, Wei Li, Zejun Ma, and Chunyuan Li. 2024a. [Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models](https://md.research.elamur.ai/free/en/papers/li-2024-llava-next-interleave-tackling-multi/). arXiv preprint arXiv:2407.07895.
12. Mingcheng Li, Dingkang Yang, Yuxuan Lei, Shunli Wang, Shuaibing Wang, Liuzhen Su, Kun Yang, Yuzheng Wang, Mingyang Sun, and Lihua Zhang. 2024b. A unified self-distillation framework for multimodal sentiment analysis with uncertain missing modalities. In Proceedings of the AAAI conference on artifici… [find](https://scholar.google.com/scholar?q=Mingcheng+Li%2C+Dingkang+Yang%2C+Yuxuan+Lei%2C+Shunli+Wang%2C+Shuaibing+Wang%2C+Liuzhen+Su%2C+Kun+Yang%2C+Yuzheng+Wang%2C+Mingyang+Sun%2C+and+Lihua+Zhang%2E+2024b%2E+A+unified+self%2Ddistillation+framework+for+multimodal+sen)
13. Tianyi Li and Daming Liu. 2025. Mpid: A modality-preserving and interaction-driven fusion network for multimodal sentiment analysis. In Proceedings of the 31st International Conference on Computational Linguistics, pages 4313–4322. [find](https://scholar.google.com/scholar?q=Tianyi+Li+and+Daming+Liu%2E+2025%2E+Mpid%3A+A+modality%2Dpreserving+and+interaction%2Ddriven+fusion+network+for+multimodal+sentiment+analysis%2E+In+Proceedings+of+the+31st+International+Conference+on+Computationa)
14. Zuocheng Li and Lishuang Li. 2025. t-hne: A text-guided hierarchical noise eliminator for multimodal sentiment analysis. In Proceedings of the 31st International Conference on Computational Linguistics, pages 2834–2844. [find](https://scholar.google.com/scholar?q=Zuocheng+Li+and+Lishuang+Li%2E+2025%2E+t%2Dhne%3A+A+text%2Dguided+hierarchical+noise+eliminator+for+multimodal+sentiment+analysis%2E+In+Proceedings+of+the+31st+International+Conference+on+Computational+Linguistic)
15. Ronghao Lin and Haifeng Hu. 2022. Multimodal contrastive learning via uni-modal coding and cross-modal prediction for multimodal sentiment analysis. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 511–523. [find](https://scholar.google.com/scholar?q=Ronghao+Lin+and+Haifeng+Hu%2E+2022%2E+Multimodal+contrastive+learning+via+uni%2Dmodal+coding+and+cross%2Dmodal+prediction+for+multimodal+sentiment+analysis%2E+In+Findings+of+the+Association+for+Computational+Li)
16. Yuanyuan et al. Liu. 2024. Noise-resistant multimodal transformer for emotion recognition. International Journal of Computer Vision, pages 1–21. [find](https://scholar.google.com/scholar?q=Yuanyuan+et+al%2E+Liu%2E+2024%2E+Noise%2Dresistant+multimodal+transformer+for+emotion+recognition%2E+International+Journal+of+Computer+Vision%2C+pages+1%E2%80%9321%2E)
17. Zhun Liu and Ying Shen. 2018. [Efficient low-rank multimodal fusion with modality-specific factors](https://md.research.elamur.ai/free/en/papers/liu-2018-efficient-low-rank-multimodal-fusion/). In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Long Papers).
18. Zhun Liu, Ying Shen, Varun Bharadhwaj Lakshminarasimhan, Paul Pu Liang, AmirAli Bagher Zadeh, and Louis-Philippe Morency. 2018. [Efficient low-rank multimodal fusion with modality-specific factors](https://md.research.elamur.ai/free/en/papers/liu-2018-efficient-low-rank-multimodal-fusion/). In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: L…
19. Sijie Mai, Haifeng Hu, and Songlong Xing. 2020. Modality to modality translation: An adversarial representation learning and graph fusion network for multimodal fusion. In AAAI, volume 34, pages 164– 172. [find](https://scholar.google.com/scholar?q=Sijie+Mai%2C+Haifeng+Hu%2C+and+Songlong+Xing%2E+2020%2E+Modality+to+modality+translation%3A+An+adversarial+representation+learning+and+graph+fusion+network+for+multimodal+fusion%2E+In+AAAI%2C+volume+34%2C+pages+164%E2%80%93+)
20. Sijie Mai, Ying Zeng, and Haifeng Hu. 2023. Learning from the global view: Supervised contrastive learning of multimodal representation. Information Fusion, 100:101920. [find](https://scholar.google.com/scholar?q=Sijie+Mai%2C+Ying+Zeng%2C+and+Haifeng+Hu%2E+2023%2E+Learning+from+the+global+view%3A+Supervised+contrastive+learning+of+multimodal+representation%2E+Information+Fusion%2C+100%3A101920%2E)
21. Liang Shi, Fuyong Xu, Ru Wang, Yongqing Wei, Guangjin Wang, Bao Wang, and Peiyu Liu. 2024. Information aggregate and sentiment enhance network to handle missing modalities for multimodal sentiment analysis. In 2024 ICME, pages 1–6. IEEE. [find](https://scholar.google.com/scholar?q=Liang+Shi%2C+Fuyong+Xu%2C+Ru+Wang%2C+Yongqing+Wei%2C+Guangjin+Wang%2C+Bao+Wang%2C+and+Peiyu+Liu%2E+2024%2E+Information+aggregate+and+sentiment+enhance+network+to+handle+missing+modalities+for+multimodal+sentiment+ana)
22. Gopendra Vikram Singh, Sai Vardhan Vemulapalli, Mauajama Firdaus, and Asif Ekbal. 2024. Deciphering cognitive distortions in patient-doctor mental health conversations: A multimodal llm-based detection and reasoning framework. In Proceedings of the 2024 conference on empirical methods in natural lan… [find](https://scholar.google.com/scholar?q=Gopendra+Vikram+Singh%2C+Sai+Vardhan+Vemulapalli%2C+Mauajama+Firdaus%2C+and+Asif+Ekbal%2E+2024%2E+Deciphering+cognitive+distortions+in+patient%2Ddoctor+mental+health+conversations%3A+A+multimodal+llm%2Dbased+detectio)
23. Kaiwei Sun and Mi Tian. 2025a. Sequential fusion of text-close and text-far representations for multimodal sentiment analysis. In Proceedings of the 31st international conference on computational linguistics, pages 40–49. [find](https://scholar.google.com/scholar?q=Kaiwei+Sun+and+Mi+Tian%2E+2025a%2E+Sequential+fusion+of+text%2Dclose+and+text%2Dfar+representations+for+multimodal+sentiment+analysis%2E+In+Proceedings+of+the+31st+international+conference+on+computational+ling)
24. Kaiwei Sun and Mi Tian. 2025b. Sequential fusion of text-close and text-far representations for multimodal sentiment analysis. In Proceedings of the 31st International Conference on Computational Linguistics, pages 40–49, Abu Dhabi, UAE. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Kaiwei+Sun+and+Mi+Tian%2E+2025b%2E+Sequential+fusion+of+text%2Dclose+and+text%2Dfar+representations+for+multimodal+sentiment+analysis%2E+In+Proceedings+of+the+31st+International+Conference+on+Computational+Ling)
25. Licai Sun, Zheng Lian, Bin Liu, and Jianhua Tao. 2023. Efficient multimodal transformer with dual-level feature restoration for robust multimodal sentiment analysis. IEEE Transactions on Affective Computing, 15(1):309–325. [find](https://scholar.google.com/scholar?q=Licai+Sun%2C+Zheng+Lian%2C+Bin+Liu%2C+and+Jianhua+Tao%2E+2023%2E+Efficient+multimodal+transformer+with+dual%2Dlevel+feature+restoration+for+robust+multimodal+sentiment+analysis%2E+IEEE+Transactions+on+Affective+Com)
26. Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, J Zico Kolter, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2019a. [Multimodal transformer for unaligned multimodal language sequences](https://md.research.elamur.ai/free/en/papers/tsai-2019-multimodal-transformer-unaligned-multimodal-language/). In Proceedings of the conference. Association for computational linguistics. Meeting, volume 2019, page 6558.
27. Yao-Hung Hubert Tsai, Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2019b. Learning factorized multimodal representations. In ICLR. [find](https://scholar.google.com/scholar?q=Yao%2DHung+Hubert+Tsai%2C+Paul+Pu+Liang%2C+Amir+Zadeh%2C+Louis%2DPhilippe+Morency%2C+and+Ruslan+Salakhutdinov%2E+2019b%2E+Learning+factorized+multimodal+representations%2E+In+ICLR%2E)
28. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). Advances in neural information processing systems, 30.
29. Tongzhou Wang and Phillip Isola. 2020. Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In International conference on machine learning, pages 9929–9939. PMLR. [find](https://scholar.google.com/scholar?q=Tongzhou+Wang+and+Phillip+Isola%2E+2020%2E+Understanding+contrastive+representation+learning+through+alignment+and+uniformity+on+the+hypersphere%2E+In+International+conference+on+machine+learning%2C+pages+992)
30. Yiwei Wei, Shaozu Yuan, Ruosong Yang, Lei Shen, Zhangmeizhi Li, Longbiao Wang, and Meng Chen. 2023. Tackling modality heterogeneity with multi-view calibration network for multimodal sentiment detection. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volu… [find](https://scholar.google.com/scholar?q=Yiwei+Wei%2C+Shaozu+Yuan%2C+Ruosong+Yang%2C+Lei+Shen%2C+Zhangmeizhi+Li%2C+Longbiao+Wang%2C+and+Meng+Chen%2E+2023%2E+Tackling+modality+heterogeneity+with+multi%2Dview+calibration+network+for+multimodal+sentiment+detecti)
31. Zehui Wu, Ziwei Gong, Jaywon Koo, and Julia Hirschberg. 2024. Multimodal multi-loss fusion network for sentiment analysis. In Proceedings of the 2024 NAACL, pages 3588–3602. [find](https://scholar.google.com/scholar?q=Zehui+Wu%2C+Ziwei+Gong%2C+Jaywon+Koo%2C+and+Julia+Hirschberg%2E+2024%2E+Multimodal+multi%2Dloss+fusion+network+for+sentiment+analysis%2E+In+Proceedings+of+the+2024+NAACL%2C+pages+3588%E2%80%933602%2E)
32. Jiandian Zeng, Jiantao Zhou, and Tianyi Liu. 2022b. Mitigating inconsistencies in multimodal sentiment analysis under uncertain missing modalities. In Proceedings of the 2022 EMNLP. [find](https://scholar.google.com/scholar?q=Jiandian+Zeng%2C+Jiantao+Zhou%2C+and+Tianyi+Liu%2E+2022b%2E+Mitigating+inconsistencies+in+multimodal+sentiment+analysis+under+uncertain+missing+modalities%2E+In+Proceedings+of+the+2022+EMNLP%2E)
33. Tianshu Yu, Haoyu Gao, Ting-En Lin, Min Yang, Yuchuan Wu, Wentao Ma, Chao Wang, Fei Huang, and Yongbin Li. 2023. Speech-text pre-training for spoken dialog understanding with explicit cross-modal alignment. In Proceedings of the 61st ACL, pages 7900–7913, Toronto, Canada. Association for Computation… [find](https://scholar.google.com/scholar?q=Tianshu+Yu%2C+Haoyu+Gao%2C+Ting%2DEn+Lin%2C+Min+Yang%2C+Yuchuan+Wu%2C+Wentao+Ma%2C+Chao+Wang%2C+Fei+Huang%2C+and+Yongbin+Li%2E+2023%2E+Speech%2Dtext+pre%2Dtraining+for+spoken+dialog+understanding+with+explicit+cross%2Dmodal+alig)
34. Jiandian Zeng, Jiantao Zhou, and Tianyi Liu. 2022c. Robust multimodal sentiment analysis via tag encoding of uncertain missing modalities. IEEE Transactions on Multimedia. [find](https://scholar.google.com/scholar?q=Jiandian+Zeng%2C+Jiantao+Zhou%2C+and+Tianyi+Liu%2E+2022c%2E+Robust+multimodal+sentiment+analysis+via+tag+encoding+of+uncertain+missing+modalities%2E+IEEE+Transactions+on+Multimedia%2E)
35. Wenmeng Yu, Hua Xu, Fanyang Meng, Yilin Zhu, Yixiao Ma, Jiele Wu, Jiyun Zou, and Kaicheng Yang. 2020. [Ch-sims: A chinese multimodal sentiment analysis dataset with fine-grained annotation of modality](https://md.research.elamur.ai/free/en/papers/yu-2020-ch-sims-chinese-multimodal-sentiment/). In Annual Meeting of the Association for Computational Linguistics.
36. Wenmeng Yu, Hua Xu, Ziqi Yuan, and Jiele Wu. 2021. Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis. Proceedings of the AAAI Conference on Artificial Intelligence, 35(12):10790–10797. [find](https://scholar.google.com/scholar?q=Wenmeng+Yu%2C+Hua+Xu%2C+Ziqi+Yuan%2C+and+Jiele+Wu%2E+2021%2E+Learning+modality%2Dspecific+representations+with+self%2Dsupervised+multi%2Dtask+learning+for+multimodal+sentiment+analysis%2E+Proceedings+of+the+AAAI+Confer)
37. Ziqi Yuan, Wei Li, Hua Xu, and Wenmeng Yu. 2021. Transformer-based feature reconstruction network for robust multimodal sentiment analysis. In Proceedings of the 29th ACM MM, pages 4400–4407. [find](https://scholar.google.com/scholar?q=Ziqi+Yuan%2C+Wei+Li%2C+Hua+Xu%2C+and+Wenmeng+Yu%2E+2021%2E+Transformer%2Dbased+feature+reconstruction+network+for+robust+multimodal+sentiment+analysis%2E+In+Proceedings+of+the+29th+ACM+MM%2C+pages+4400%E2%80%934407%2E)
38. Ziqi Yuan, Baozheng Zhang, Hua Xu, and Kai Gao. 2024. Meta noise adaption framework for multimodal sentiment analysis with feature noise. IEEE Transactions on Multimedia, 26:7265–7277. [find](https://scholar.google.com/scholar?q=Ziqi+Yuan%2C+Baozheng+Zhang%2C+Hua+Xu%2C+and+Kai+Gao%2E+2024%2E+Meta+noise+adaption+framework+for+multimodal+sentiment+analysis+with+feature+noise%2E+IEEE+Transactions+on+Multimedia%2C+26%3A7265%E2%80%937277%2E)
39. Amir Zadeh, Minghai Chen, Soujanya Poria, Erik Cambria, and Louis-Philippe Morency. 2017. [Tensor fusion network for multimodal sentiment analysis](https://md.research.elamur.ai/free/en/papers/zadeh-2017-tensor-fusion-network-multimodal-sentiment/). In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1103–1114, Copenhagen, Denmark. Association for Computat…
40. Amir Zadeh, Paul Pu Liang, Soujanya Poria, E. Cambria, and Louis-Philippe Morency. 2018a. [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 Annual Meeting of the Association for Computational Linguistics.
41. Amir Zadeh, Paul Pu Liang, Soujanya Poria, Prateek Vij, Erik Cambria, and Louis-Philippe Morency. 2018b. Multi-attention recurrent network for human communication comprehension. In Proceedings of the AAAI conference on artificial intelligence, volume 32. [find](https://scholar.google.com/scholar?q=Amir+Zadeh%2C+Paul+Pu+Liang%2C+Soujanya+Poria%2C+Prateek+Vij%2C+Erik+Cambria%2C+and+Louis%2DPhilippe+Morency%2E+2018b%2E+Multi%2Dattention+recurrent+network+for+human+communication+comprehension%2E+In+Proceedings+of+the+)
42. Amir Zadeh, Rowan Zellers, Eli Pincus, and Louis-Philippe Morency. 2016. Mosi: Multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos. ArXiv, abs/1606.06259. [find](https://scholar.google.com/scholar?q=Amir+Zadeh%2C+Rowan+Zellers%2C+Eli+Pincus%2C+and+Louis%2DPhilippe+Morency%2E+2016%2E+Mosi%3A+Multimodal+corpus+of+sentiment+intensity+and+subjectivity+analysis+in+online+opinion+videos%2E+ArXiv%2C+abs%2F1606%2E06259%2E)
43. Haoyu Zhang, Yu Wang, Guanghao Yin, Kejun Liu, Yuanyuan Liu, and Tianshu Yu. 2023. Learning language-guided adaptive hyper-modality representation for multimodal sentiment analysis. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 756–767. Association… [find](https://scholar.google.com/scholar?q=Haoyu+Zhang%2C+Yu+Wang%2C+Guanghao+Yin%2C+Kejun+Liu%2C+Yuanyuan+Liu%2C+and+Tianshu+Yu%2E+2023%2E+Learning+language%2Dguided+adaptive+hyper%2Dmodality+representation+for+multimodal+sentiment+analysis%2E+In+Proceedings+of+)
44. Yiqun Zhang, Fanheng Kong, Peidong Wang, Shuang Sun, SWangLing SWangLing, Shi Feng, Daling Wang, Yifei Zhang, and Kaisong Song. 2024. Stickerconv: Generating multimodal empathetic responses from scratch. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volu… [find](https://scholar.google.com/scholar?q=Yiqun+Zhang%2C+Fanheng+Kong%2C+Peidong+Wang%2C+Shuang+Sun%2C+SWangLing+SWangLing%2C+Shi+Feng%2C+Daling+Wang%2C+Yifei+Zhang%2C+and+Kaisong+Song%2E+2024%2E+Stickerconv%3A+Generating+multimodal+empathetic+responses+from+scrat)
45. Yiqun Zhang, Xiaocui Yang, Xingle Xu, Zeran Gao, Yijie Huang, Shiyi Mu, Shi Feng, Daling Wang, Yifei Zhang, Kaisong Song, and 1 others. 2026. Affective computing in the era of large language models: A survey from the nlp perspective. Knowledge-Based Systems, page 115411. [find](https://scholar.google.com/scholar?q=Yiqun+Zhang%2C+Xiaocui+Yang%2C+Xingle+Xu%2C+Zeran+Gao%2C+Yijie+Huang%2C+Shiyi+Mu%2C+Shi+Feng%2C+Daling+Wang%2C+Yifei+Zhang%2C+Kaisong+Song%2C+and+1+others%2E+2026%2E+Affective+computing+in+the+era+of+large+language+models%3A+A)
46. Miao Zhou, Lina Yang, Thomas Wu, Dongnan Yang, and Xinru Zhang. 2025. Dual-path dynamic fusion with learnable query for multimodal sentiment analysis. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 11366–11376. [find](https://scholar.google.com/scholar?q=Miao+Zhou%2C+Lina+Yang%2C+Thomas+Wu%2C+Dongnan+Yang%2C+and+Xinru+Zhang%2E+2025%2E+Dual%2Dpath+dynamic+fusion+with+learnable+query+for+multimodal+sentiment+analysis%2E+In+Proceedings+of+the+2025+Conference+on+Empirica)
47. Aoqiang Zhu, Min Hu, Xiaohua Wang, Jiaoyun Yang, Yiming Tang, and Fuji Ren. 2024. Kebr: Knowledge enhanced self-supervised balanced representation for multimodal sentiment analysis. In Proceedings of the 32nd ACM MM, pages 5732–5741. [find](https://scholar.google.com/scholar?q=Aoqiang+Zhu%2C+Min+Hu%2C+Xiaohua+Wang%2C+Jiaoyun+Yang%2C+Yiming+Tang%2C+and+Fuji+Ren%2E+2024%2E+Kebr%3A+Knowledge+enhanced+self%2Dsupervised+balanced+representation+for+multimodal+sentiment+analysis%2E+In+Proceedings+of+)
48. Zhouan Zhu, Shangfei Wang, Yuxin Wang, and Jiaqiang Wu. 2025. Integrating visual modalities with large language models for mental health support. In Proceedings of the 31st International Conference on Computational Linguistics, pages 8939–8954. [find](https://scholar.google.com/scholar?q=Zhouan+Zhu%2C+Shangfei+Wang%2C+Yuxin+Wang%2C+and+Jiaqiang+Wu%2E+2025%2E+Integrating+visual+modalities+with+large+language+models+for+mental+health+support%2E+In+Proceedings+of+the+31st+International+Conference+on)
49. Yan Zhuang, Yanru Zhang, Zheng Hu, Xiaoyue Zhang, Jiawen Deng, and Fuji Ren. 2024. Glomo: Global-local modal fusion for multimodal sentiment analysis. In Proceedings of the 32nd ACM MM, page 1800–1809. [find](https://scholar.google.com/scholar?q=Yan+Zhuang%2C+Yanru+Zhang%2C+Zheng+Hu%2C+Xiaoyue+Zhang%2C+Jiawen+Deng%2C+and+Fuji+Ren%2E+2024%2E+Glomo%3A+Global%2Dlocal+modal+fusion+for+multimodal+sentiment+analysis%2E+In+Proceedings+of+the+32nd+ACM+MM%2C+page+1800%E2%80%931809)
50. Jiandian Zeng, Tianyi Liu, and Jiantao Zhou. 2022a. Tag-assisted multimodal sentiment analysis under uncertain missing modalities. In Proceedings of the 45th ACM SIGIR, pages 1545–1554. [find](https://scholar.google.com/scholar?q=Jiandian+Zeng%2C+Tianyi+Liu%2C+and+Jiantao+Zhou%2E+2022a%2E+Tag%2Dassisted+multimodal+sentiment+analysis+under+uncertain+missing+modalities%2E+In+Proceedings+of+the+45th+ACM+SIGIR%2C+pages+1545%E2%80%931554%2E)

*Updated 2 November 2026*