# Human Activity Recognition on Self-collected mmWave Dataset

Source: [Human Activity Recognition on Self-collected mmWave Dataset](<https://www.sota2.com/research/sota/human-activity-recognition-on-self-collected-mmwave-dataset>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-31T09:54:02.265Z

Evaluation of Human Activity Recognition performance on the self-collected mmWave dataset, reporting Accuracy and Macro F1-score.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Human Activity Recognition |
| Dataset (including any stated split) | Self-collected mmWave Dataset |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy](<https://www.sota2.com/research/sota/human-activity-recognition-on-self-collected-mmwave-dataset.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Macro F1 Score](<https://www.sota2.com/research/sota/human-activity-recognition-on-self-collected-mmwave-dataset.md?metric=Macro%20F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| ViT | 94.12 | Not recorded | 69cb555f0636e5bf4afca258 |
| RAGent | 93.39 | Not recorded | 69cb555f0636e5bf4afca258 |
| CNN | 91.76 | Not recorded | 69cb555f0636e5bf4afca258 |
| CNN-BiLSTM | 88.82 | Not recorded | 69cb555f0636e5bf4afca258 |
| mmCLIP-light | 87.06 | Not recorded | 69cb555f0636e5bf4afca258 |
| SynMotion-light | 72.35 | Not recorded | 69cb555f0636e5bf4afca258 |
| EI-adapt | 68 | Not recorded | 69cb555f0636e5bf4afca258 |
| Retrieval-Only | 65 | Not recorded | 69cb555f0636e5bf4afca258 |
| LLM-Direct | 13.1 | Not recorded | 69cb555f0636e5bf4afca258 |

### ViT

Accuracy: 94.12. Result ID: 69cb99ae47f34ce924b45785.

[Reporting paper](<https://www.sota2.com/research/paper/69cb555f0636e5bf4afca258.md>)

Recorded evaluation configuration: {"Category":"Supervised","Train-free":"false"}. This record does not assert independent reproduction.

### RAGent

Accuracy: 93.39. Result ID: 69cb99ae47f34ce924b45789.

[Reporting paper](<https://www.sota2.com/research/paper/69cb555f0636e5bf4afca258.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cb555f0636e5bf4afca258.md>)

Recorded evaluation configuration: {"Category":"Ours","Train-free":"true"}. This record does not assert independent reproduction.

### CNN

Accuracy: 91.76. Result ID: 69cb99ae47f34ce924b45783.

[Reporting paper](<https://www.sota2.com/research/paper/69cb555f0636e5bf4afca258.md>)

Recorded evaluation configuration: {"Category":"Supervised","Train-free":"false"}. This record does not assert independent reproduction.

### CNN-BiLSTM

Accuracy: 88.82. Result ID: 69cb99ae47f34ce924b45784.

[Reporting paper](<https://www.sota2.com/research/paper/69cb555f0636e5bf4afca258.md>)

Recorded evaluation configuration: {"Category":"Supervised","Train-free":"false"}. This record does not assert independent reproduction.

### mmCLIP-light

Accuracy: 87.06. Result ID: 69cb99ae47f34ce924b45786.

[Reporting paper](<https://www.sota2.com/research/paper/69cb555f0636e5bf4afca258.md>)

Recorded evaluation configuration: {"Category":"Adapted baselines","Train-free":"false"}. This record does not assert independent reproduction.

### SynMotion-light

Accuracy: 72.35. Result ID: 69cb99ae47f34ce924b45787.

[Reporting paper](<https://www.sota2.com/research/paper/69cb555f0636e5bf4afca258.md>)

Recorded evaluation configuration: {"Category":"Adapted baselines","Train-free":"false"}. This record does not assert independent reproduction.

### EI-adapt

Accuracy: 68. Result ID: 69cb99ae47f34ce924b45788.

[Reporting paper](<https://www.sota2.com/research/paper/69cb555f0636e5bf4afca258.md>)

Recorded evaluation configuration: {"Category":"Adapted baselines","Train-free":"false"}. This record does not assert independent reproduction.

### Retrieval-Only

Accuracy: 65. Result ID: 69cb99ae47f34ce924b45781.

[Reporting paper](<https://www.sota2.com/research/paper/69cb555f0636e5bf4afca258.md>)

Recorded evaluation configuration: {"Category":"Inference-only","Train-free":"true"}. This record does not assert independent reproduction.

### LLM-Direct

Accuracy: 13.1. Result ID: 69cb99ae47f34ce924b45782.

[Reporting paper](<https://www.sota2.com/research/paper/69cb555f0636e5bf4afca258.md>)

Recorded evaluation configuration: {"Category":"Inference-only","Train-free":"true"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
