---
license: mit
language:
- en
- zh
tags:
- multimodal
- sentiment-analysis
- multimodal-sentiment-analysis
- missing-modality
datasets:
- Bluexxx/SemMSA-data
base_model:
- Qwen/Qwen3-1.7B
---

# SemMSA checkpoints

Checkpoints of **SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data**
([paper](https://arxiv.org/abs/2609.30238), [code](https://github.com/peacelwh/SemMSA),
[project page](https://peacelwh.github.io/SemMSA/), [data](https://huggingface.co/datasets/Bluexxx/SemMSA-data)).

SemMSA constructs sentiment-relevant latent semantics with a frozen LLM (Qwen3-1.7B) through Cross-modal Semantic
Refinement (CSR) and aligns them with language, visual and acoustic representations through Cross-modal Spectral
Alignment (CSA).

## Released checkpoints

Checkpoints for **CH-SIMS** are released; checkpoints for MOSI and MOSEI will be added later.

```
<dataset>/<config>/best_<metric>_<seed>.pth
```

`<config>` is the training configuration `configs/<dataset>/<config>.yaml` of the code repository. Following the
evaluation protocol of LNLN and P-RMF, one checkpoint is kept for each metric; `configs/<dataset>/eval.yaml` lists the
checkpoint used for every reported metric.

| Config | Files (seeds 1111, 1112, 1113) | Used for |
|---|---|---|
| `sims/main` | `best_Mult_acc_2_*.pth`, `best_MAE_*.pth` | Acc-2, Corr |
| `sims/f1` | `best_Mult_acc_2_*.pth` | F1 |
| `sims/reg` | `best_Mult_acc_3_*.pth`, `best_MAE_*.pth` | Acc-3, MAE |
| `sims/acc5` | `best_Mult_acc_5_*.pth` | Acc-5 |

The files contain only the trainable weights: the frozen Qwen3-1.7B (and BERT, when it is frozen) are loaded from
`pretrained/`.

## Usage

```bash
git clone https://github.com/peacelwh/SemMSA.git && cd SemMSA
pip install -r requirements.txt && pip install -e .
bash scripts/download_pretrained.sh
bash scripts/download_data.sh sims
bash scripts/download_checkpoints.sh sims   # this repository -> checkpoints/
bash scripts/evaluate.sh sims 0             # robust evaluation under missing rates 0.0-0.9
```

## Citation

```bibtex
@article{li2026semmsa,
  title   = {SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data},
  author  = {Li, Wenhao and Wu, Zhibin and Xiao, Chong and Wang, Qiangchang},
  journal = {arXiv preprint arXiv:2609.30238},
  year    = {2026}
}
```