# Video-to-image affordance grounding on OPRA fine-grained 256 x 256

Source: [Video-to-image affordance grounding on OPRA fine-grained 256 x 256](<https://www.sota2.com/research/sota/video-to-image-affordance-grounding-on-opra-fine-grained-256-x-256>)

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

Data updated: 2026-02-26T05:46:26.115Z

Evaluation of Video-to-image affordance grounding performance on the OPRA fine-grained 256x256 dataset, measured using Heatmap KLD and Action Top-1 Accuracy.

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 | Video-to-image affordance grounding |
| Dataset (including any stated split) | OPRA fine-grained 256 x 256 |
| Metric | Heatmap KLD |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 11 of 11 |
| 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

- [Heatmap KLD](<https://www.sota2.com/research/sota/video-to-image-affordance-grounding-on-opra-fine-grained-256-x-256.md?metric=Heatmap%20KLD>): Lower is better; unit: SCALAR.

- [Action Top-1 Acc](<https://www.sota2.com/research/sota/video-to-image-affordance-grounding-on-opra-fine-grained-256-x-256.md?metric=Action%20Top-1%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Heatmap KLD | Result date | Report paper |
| --- | --- | --- | --- |
| MaskAHand | 1.48 | Not recorded | 68fa6eea1e209131cea42e03 |
| Afformer | 1.51 | Not recorded | 68fa6eea1e209131cea42e03 |
| Afformer | 1.55 | Not recorded | 68fa6eea1e209131cea42e03 |
| MaskAHand | 1.74 | Not recorded | 68fa6eea1e209131cea42e03 |
| Naive Baseline | 2.2 | Not recorded | 68fa6eea1e209131cea42e03 |
| Demo2Vec | 2.34 | Not recorded | 68fa6eea1e209131cea42e03 |
| MaskAHand | 2.36 | Not recorded | 68fa6eea1e209131cea42e03 |
| MaskAHand | 2.89 | Not recorded | 68fa6eea1e209131cea42e03 |
| Demo2Vec | 3.31 | Not recorded | 68fa6eea1e209131cea42e03 |
| Demo2Vec | 3.34 | Not recorded | 68fa6eea1e209131cea42e03 |
| Demo2Vec | 3.45 | Not recorded | 68fa6eea1e209131cea42e03 |

### MaskAHand

Heatmap KLD: 1.48. Result ID: 699070ab3a6c31484900920e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e03.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e03.md>)

[Implementation](<https://github.com/showlab/afformer>)

Recorded evaluation configuration: {"Protocol":"Fine-tune","Backbone":"ResNet-50-Afformer"}. This record does not assert independent reproduction.

### Afformer

Heatmap KLD: 1.51. Result ID: 699070ab3a6c314849009209.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e03.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e03.md>)

[Implementation](<https://github.com/showlab/afformer>)

Recorded evaluation configuration: {"Backbone":"ViTDet-B"}. This record does not assert independent reproduction.

### Afformer

Heatmap KLD: 1.55. Result ID: 699070ab3a6c31484900920a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e03.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e03.md>)

[Implementation](<https://github.com/showlab/afformer>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### MaskAHand

Heatmap KLD: 1.74. Result ID: 699070ab3a6c31484900920d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e03.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e03.md>)

[Implementation](<https://github.com/showlab/afformer>)

Recorded evaluation configuration: {"Protocol":"Fine-tune","Backbone":"ResNet-50","Architecture":"Deconv"}. This record does not assert independent reproduction.

### Naive Baseline

Heatmap KLD: 2.2. Result ID: 699070ab3a6c314849009208.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e03.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e03.md>)

[Implementation](<https://github.com/showlab/afformer>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Decoder":"Deconv"}. This record does not assert independent reproduction.

### Demo2Vec

Heatmap KLD: 2.34. Result ID: 699070ab3a6c314849009207.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e03.md>)

Recorded evaluation configuration: {"Variants":"Motion + TSA + ConvLSTM"}. This record does not assert independent reproduction.

### MaskAHand

Heatmap KLD: 2.36. Result ID: 699070ab3a6c31484900920c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e03.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e03.md>)

[Implementation](<https://github.com/showlab/afformer>)

Recorded evaluation configuration: {"Protocol":"Zero-shot","Backbone":"ResNet-50-Afformer"}. This record does not assert independent reproduction.

### MaskAHand

Heatmap KLD: 2.89. Result ID: 699070ab3a6c31484900920b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e03.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e03.md>)

[Implementation](<https://github.com/showlab/afformer>)

Recorded evaluation configuration: {"Protocol":"Zero-shot","Backbone":"ResNet-50","Architecture":"Deconv"}. This record does not assert independent reproduction.

### Demo2Vec

Heatmap KLD: 3.31. Result ID: 699070ab3a6c314849009205.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e03.md>)

Recorded evaluation configuration: {"Variants":"ConvLSTM"}. This record does not assert independent reproduction.

### Demo2Vec

Heatmap KLD: 3.34. Result ID: 699070ab3a6c314849009206.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e03.md>)

Recorded evaluation configuration: {"Variants":"TSA + ConvLSTM"}. This record does not assert independent reproduction.

### Demo2Vec

Heatmap KLD: 3.45. Result ID: 699070ab3a6c314849009204.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e03.md>)

Recorded evaluation configuration: {"Variants":"LSTM"}. This record does not assert independent reproduction.

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