# Grounded Open Vocabulary Acquisition on Flickr30k Entities 1.0 (Seen Vseen = 60)

Source: [Grounded Open Vocabulary Acquisition on Flickr30k Entities 1.0 (Seen Vseen = 60)](<https://www.sota2.com/research/sota/grounded-open-vocabulary-acquisition-on-flickr30k-entities-1-0-seen-vseen-60>)

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

Data updated: 2026-02-26T05:46:14.851Z

Evaluation of Grounded Open Vocabulary Acquisition performance on the specific subset (Seen Vseen = 60) of the Flickr30k Entities 1.0 dataset.

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 | Grounded Open Vocabulary Acquisition |
| Dataset (including any stated split) | Flickr30k Entities 1.0 (Seen Vseen = 60) |
| Metric | HR@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [HR@1](<https://www.sota2.com/research/sota/grounded-open-vocabulary-acquisition-on-flickr30k-entities-1-0-seen-vseen-60.md?metric=HR%401>): Higher is better; unit: PERCENT.

- [G-HR@1 (All)](<https://www.sota2.com/research/sota/grounded-open-vocabulary-acquisition-on-flickr30k-entities-1-0-seen-vseen-60.md?metric=G-HR%401%20(All)>): Higher is better; unit: PERCENT.

- [G-HR@1 (Any)](<https://www.sota2.com/research/sota/grounded-open-vocabulary-acquisition-on-flickr30k-entities-1-0-seen-vseen-60.md?metric=G-HR%401%20(Any)>): Higher is better; unit: PERCENT.

- [log G-PPL (All)](<https://www.sota2.com/research/sota/grounded-open-vocabulary-acquisition-on-flickr30k-entities-1-0-seen-vseen-60.md?metric=log%20G-PPL%20(All)>): Lower is better; unit: SCALAR.

- [log G-PPL (Any)](<https://www.sota2.com/research/sota/grounded-open-vocabulary-acquisition-on-flickr30k-entities-1-0-seen-vseen-60.md?metric=log%20G-PPL%20(Any)>): Lower is better; unit: SCALAR.

- [log PPL](<https://www.sota2.com/research/sota/grounded-open-vocabulary-acquisition-on-flickr30k-entities-1-0-seen-vseen-60.md?metric=log%20PPL>): Lower is better; unit: SCALAR.

- [Acc (All)](<https://www.sota2.com/research/sota/grounded-open-vocabulary-acquisition-on-flickr30k-entities-1-0-seen-vseen-60.md?metric=Acc%20(All)>): Higher is better; unit: PERCENT.

- [Acc (Any)](<https://www.sota2.com/research/sota/grounded-open-vocabulary-acquisition-on-flickr30k-entities-1-0-seen-vseen-60.md?metric=Acc%20(Any)>): Higher is better; unit: PERCENT.

- [IoU (All)](<https://www.sota2.com/research/sota/grounded-open-vocabulary-acquisition-on-flickr30k-entities-1-0-seen-vseen-60.md?metric=IoU%20(All)>): Higher is better; unit: PERCENT.

- [IoU (Any)](<https://www.sota2.com/research/sota/grounded-open-vocabulary-acquisition-on-flickr30k-entities-1-0-seen-vseen-60.md?metric=IoU%20(Any)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | HR@1 | Result date | Report paper |
| --- | --- | --- | --- |
| OctoBERT | 66.9 | Not recorded | 68fa766f1e209131cea6cfa2 |
| ViLT | 64.7 | Not recorded | 68fa766f1e209131cea6cfa2 |
| ViLT+MDETR | 64.7 | Not recorded | 68fa766f1e209131cea6cfa2 |
| OctoBERT\_w/o G | 63.9 | Not recorded | 68fa766f1e209131cea6cfa2 |
| ROBERTa | 47.9 | Not recorded | 68fa766f1e209131cea6cfa2 |
| VisualBERT | 42.3 | Not recorded | 68fa766f1e209131cea6cfa2 |
| ROBERTa | 38 | Not recorded | 68fa766f1e209131cea6cfa2 |

### OctoBERT

HR@1: 66.9. Result ID: 69942c983a6c3148491b92f0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa766f1e209131cea6cfa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa766f1e209131cea6cfa2.md>)

[Implementation](<https://github.com/sled-group/world-to-words>)

Recorded evaluation configuration: {"Fine-tuned":false}. This record does not assert independent reproduction.

### ViLT

HR@1: 64.7. Result ID: 69942c983a6c3148491b92eb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa766f1e209131cea6cfa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a1e1e209131cea260db.md>)

[Implementation](<https://github.com/dandelin/vilt>)

Recorded evaluation configuration: {"Fine-tuned":false}. This record does not assert independent reproduction.

### ViLT+MDETR

HR@1: 64.7. Result ID: 69942c983a6c3148491b92ed.

[Reporting paper](<https://www.sota2.com/research/paper/68fa766f1e209131cea6cfa2.md>)

Recorded evaluation configuration: {"Fine-tuned":false}. This record does not assert independent reproduction.

### OctoBERT\_w/o G

HR@1: 63.9. Result ID: 69942c983a6c3148491b92ef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa766f1e209131cea6cfa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa766f1e209131cea6cfa2.md>)

[Implementation](<https://github.com/sled-group/world-to-words>)

Recorded evaluation configuration: {"Fine-tuned":true}. This record does not assert independent reproduction.

### ROBERTa

HR@1: 47.9. Result ID: 69942c983a6c3148491b92ea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa766f1e209131cea6cfa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66131e209131cea0e18b.md>)

[Implementation](<https://github.com/pytorch/fairseq>)

Recorded evaluation configuration: {"Fine-tuned":true}. This record does not assert independent reproduction.

### VisualBERT

HR@1: 42.3. Result ID: 69942c983a6c3148491b92ee.

[Reporting paper](<https://www.sota2.com/research/paper/68fa766f1e209131cea6cfa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66391e209131cea0ef1d.md>)

Recorded evaluation configuration: {"Fine-tuned":true}. This record does not assert independent reproduction.

### ROBERTa

HR@1: 38. Result ID: 69942c983a6c3148491b92e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa766f1e209131cea6cfa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66131e209131cea0e18b.md>)

[Implementation](<https://github.com/pytorch/fairseq>)

Recorded evaluation configuration: {"Fine-tuned":false}. This record does not assert independent reproduction.

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