# Human Activity Recognition on UniMiB

Source: [Human Activity Recognition on UniMiB](<https://www.sota2.com/research/sota/human-activity-recognition-on-unimib>)

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

Data updated: 2026-02-26T05:51:28.207Z

Evaluation of Human Activity Recognition performance using the UniMiB dataset, typically reporting 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) | UniMiB |
| Metric | Macro F1 |
| 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

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

## Recorded results

| Method | Macro F1 | Result date | Report paper |
| --- | --- | --- | --- |
| DeepConvLSTM | 85.83 | Not recorded | 698c0d24c97a0b3e3b5e11e5 |
| DeepConvLSTM | 84.12 | Not recorded | 698969e7c97a0b3e3b5dc3cb |
| Crossover-BiDir-BabyMamba | 83.74 | Not recorded | 698c0d24c97a0b3e3b5e11e5 |
| CI-BabyMamba-HAR | 80.83 | Not recorded | 698c0d24c97a0b3e3b5e11e5 |
| TinierHAR | 79.67 | Not recorded | 698c0d24c97a0b3e3b5e11e5 |
| TinierHAR | 79.67 | Not recorded | 698969e7c97a0b3e3b5dc3cb |
| µBi-ConvLSTM | 79.43 | Not recorded | 698969e7c97a0b3e3b5dc3cb |
| TinyHAR | 77.61 | Not recorded | 698c0d24c97a0b3e3b5e11e5 |
| TinyHAR | 77.61 | Not recorded | 698969e7c97a0b3e3b5dc3cb |

### DeepConvLSTM

Macro F1: 85.83. Result ID: 69971b5b5698665ec46952db.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d24c97a0b3e3b5e11e5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DeepConvLSTM

Macro F1: 84.12. Result ID: 699733635698665ec482dc31.

[Reporting paper](<https://www.sota2.com/research/paper/698969e7c97a0b3e3b5dc3cb.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Crossover-BiDir-BabyMamba

Macro F1: 83.74. Result ID: 69971b5b5698665ec46952d7.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d24c97a0b3e3b5e11e5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698c0d24c97a0b3e3b5e11e5.md>)

Recorded evaluation configuration: {"Directionality":"Bidirectional"}. This record does not assert independent reproduction.

### CI-BabyMamba-HAR

Macro F1: 80.83. Result ID: 69971b5b5698665ec46952d8.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d24c97a0b3e3b5e11e5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698c0d24c97a0b3e3b5e11e5.md>)

Recorded evaluation configuration: {"Channel Processing":"Channel Independent"}. This record does not assert independent reproduction.

### TinierHAR

Macro F1: 79.67. Result ID: 69971b5b5698665ec46952da.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d24c97a0b3e3b5e11e5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79fb1e209131cea80711.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### TinierHAR

Macro F1: 79.67. Result ID: 699733635698665ec482dc33.

[Reporting paper](<https://www.sota2.com/research/paper/698969e7c97a0b3e3b5dc3cb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79fb1e209131cea80711.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### µBi-ConvLSTM

Macro F1: 79.43. Result ID: 699733635698665ec482dc30.

[Reporting paper](<https://www.sota2.com/research/paper/698969e7c97a0b3e3b5dc3cb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698969e7c97a0b3e3b5dc3cb.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### TinyHAR

Macro F1: 77.61. Result ID: 69971b5b5698665ec46952d9.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d24c97a0b3e3b5e11e5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### TinyHAR

Macro F1: 77.61. Result ID: 699733635698665ec482dc32.

[Reporting paper](<https://www.sota2.com/research/paper/698969e7c97a0b3e3b5dc3cb.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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