# Semantic Contact Prediction on MMHOI (test)

Source: [Semantic Contact Prediction on MMHOI (test)](<https://www.sota2.com/research/sota/semantic-contact-prediction-on-mmhoi-test>)

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

Data updated: 2026-04-15T10:04:20.285Z

Evaluation of Semantic Contact Prediction performance on the test split of the MMHOI dataset, reporting F1, Precision, Recall, and Geometric Distance.

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 | Semantic Contact Prediction |
| Dataset (including any stated split) | MMHOI (test) |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [F1 Score](<https://www.sota2.com/research/sota/semantic-contact-prediction-on-mmhoi-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/semantic-contact-prediction-on-mmhoi-test.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/semantic-contact-prediction-on-mmhoi-test.md?metric=Recall>): Higher is better; unit: PERCENT.

- [Geometric Distance](<https://www.sota2.com/research/sota/semantic-contact-prediction-on-mmhoi-test.md?metric=Geometric%20Distance>): Lower is better; unit: OTHER.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| Pi-HOC | 61.09 | Not recorded | 69df1bc67d0172140ec7bbbc |
| InteractVLM | 54.86 | Not recorded | 69df1bc67d0172140ec7bbbc |
| InteractVLM | 52.02 | Not recorded | 69df1bc67d0172140ec7bbbc |
| InteractVLM | 43.68 | Not recorded | 69df1bc67d0172140ec7bbbc |

### Pi-HOC

F1 Score: 61.09. Result ID: 69df628c47f34ce924c8a0e0.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bc67d0172140ec7bbbc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bc67d0172140ec7bbbc.md>)

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

### InteractVLM

F1 Score: 54.86. Result ID: 69df628c47f34ce924c8a0df.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bc67d0172140ec7bbbc.md>)

Recorded evaluation configuration: {"Input Strategy":"Cropped","Training Status":"Trained"}. This record does not assert independent reproduction.

### InteractVLM

F1 Score: 52.02. Result ID: 69df628c47f34ce924c8a0de.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bc67d0172140ec7bbbc.md>)

Recorded evaluation configuration: {"Input Strategy":"Full Image","Training Status":"Trained"}. This record does not assert independent reproduction.

### InteractVLM

F1 Score: 43.68. Result ID: 69df628c47f34ce924c8a0dd.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bc67d0172140ec7bbbc.md>)

Recorded evaluation configuration: {"Input Strategy":"Cropped","Training Status":"Pretrained"}. This record does not assert independent reproduction.

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