# Embodied Referring Expression Comprehension on Refer360

Source: [Embodied Referring Expression Comprehension on Refer360](<https://www.sota2.com/research/sota/embodied-referring-expression-comprehension-on-refer360>)

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

Data updated: 2026-02-26T05:47:29.794Z

Evaluation of Embodied Referring Expression Comprehension performance on the Refer360 dataset, typically measured using IOU metrics.

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 | Embodied Referring Expression Comprehension |
| Dataset (including any stated split) | Refer360 |
| Metric | IoU@0.25 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| 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

- [IoU@0.25](<https://www.sota2.com/research/sota/embodied-referring-expression-comprehension-on-refer360.md?metric=IoU%400.25>): Higher is better; unit: PERCENT.

- [IoU@0.50](<https://www.sota2.com/research/sota/embodied-referring-expression-comprehension-on-refer360.md?metric=IoU%400.50>): Higher is better; unit: PERCENT.

## Recorded results

| Method | IoU@0.25 | Result date | Report paper |
| --- | --- | --- | --- |
| ViLT | 37.05 | Not recorded | 6937ad356cfd488761a4ea9c |
| ViLT | 36.53 | Not recorded | 6937ad356cfd488761a4ea9c |
| ViLT | 35.34 | Not recorded | 6937ad356cfd488761a4ea9c |
| Dual-Encoder | 31.36 | Not recorded | 6937ad356cfd488761a4ea9c |
| Dual-Encoder | 31.08 | Not recorded | 6937ad356cfd488761a4ea9c |
| Dual-Encoder | 31.08 | Not recorded | 6937ad356cfd488761a4ea9c |
| Dual-Encoder | 30.17 | Not recorded | 6937ad356cfd488761a4ea9c |
| Dual-Encoder | 29.43 | Not recorded | 6937ad356cfd488761a4ea9c |
| BLIP-2 | 29.42 | Not recorded | 6937ad356cfd488761a4ea9c |
| CLIP | 29.2 | Not recorded | 6937ad356cfd488761a4ea9c |
| CLIP | 28.3 | Not recorded | 6937ad356cfd488761a4ea9c |
| BLIP-2 | 27.66 | Not recorded | 6937ad356cfd488761a4ea9c |
| CLIP | 27.22 | Not recorded | 6937ad356cfd488761a4ea9c |
| BLIP-2 | 26.81 | Not recorded | 6937ad356cfd488761a4ea9c |
| CLIP | 26.65 | Not recorded | 6937ad356cfd488761a4ea9c |
| CLIP | 25.8 | Not recorded | 6937ad356cfd488761a4ea9c |
| BLIP-2 | 25.45 | Not recorded | 6937ad356cfd488761a4ea9c |
| BLIP-2 | 16.44 | Not recorded | 6937ad356cfd488761a4ea9c |

### ViLT

IoU@0.25: 37.05. Result ID: 6999f3c05698665ec474bf01.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

Recorded evaluation configuration: {"Residual Module Configuration":"MuRes(V+L)"}. This record does not assert independent reproduction.

### ViLT

IoU@0.25: 36.53. Result ID: 6999f3c05698665ec474beff.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

Recorded evaluation configuration: {"Residual Module Configuration":"Without Residual"}. This record does not assert independent reproduction.

### ViLT

IoU@0.25: 35.34. Result ID: 6999f3c05698665ec474bf00.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

Recorded evaluation configuration: {"Residual Module Configuration":"Vanilla Residual"}. This record does not assert independent reproduction.

### Dual-Encoder

IoU@0.25: 31.36. Result ID: 6999f3c05698665ec474bf09.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

Recorded evaluation configuration: {"Residual Module Configuration":"MuRes(V)"}. This record does not assert independent reproduction.

### Dual-Encoder

IoU@0.25: 31.08. Result ID: 6999f3c05698665ec474bf07.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

Recorded evaluation configuration: {"Residual Module Configuration":"Without Residual"}. This record does not assert independent reproduction.

### Dual-Encoder

IoU@0.25: 31.08. Result ID: 6999f3c05698665ec474bf0b.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

Recorded evaluation configuration: {"Residual Module Configuration":"MuRes(V+L)"}. This record does not assert independent reproduction.

### Dual-Encoder

IoU@0.25: 30.17. Result ID: 6999f3c05698665ec474bf08.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

Recorded evaluation configuration: {"Residual Module Configuration":"Vanilla Residual"}. This record does not assert independent reproduction.

### Dual-Encoder

IoU@0.25: 29.43. Result ID: 6999f3c05698665ec474bf0a.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

Recorded evaluation configuration: {"Residual Module Configuration":"MuRes(L)"}. This record does not assert independent reproduction.

### BLIP-2

IoU@0.25: 29.42. Result ID: 6999f3c05698665ec474bf02.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

Recorded evaluation configuration: {"Residual Module Configuration":"Without Residual"}. This record does not assert independent reproduction.

### CLIP

IoU@0.25: 29.2. Result ID: 6999f3c05698665ec474befc.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

Recorded evaluation configuration: {"Residual Module Configuration":"MuRes(V)"}. This record does not assert independent reproduction.

### CLIP

IoU@0.25: 28.3. Result ID: 6999f3c05698665ec474befd.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

Recorded evaluation configuration: {"Residual Module Configuration":"MuRes(L)"}. This record does not assert independent reproduction.

### BLIP-2

IoU@0.25: 27.66. Result ID: 6999f3c05698665ec474bf03.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

Recorded evaluation configuration: {"Residual Module Configuration":"Vanilla Residual"}. This record does not assert independent reproduction.

### CLIP

IoU@0.25: 27.22. Result ID: 6999f3c05698665ec474befb.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

Recorded evaluation configuration: {"Residual Module Configuration":"Vanilla Residual"}. This record does not assert independent reproduction.

### BLIP-2

IoU@0.25: 26.81. Result ID: 6999f3c05698665ec474bf05.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

Recorded evaluation configuration: {"Residual Module Configuration":"MuRes(L)"}. This record does not assert independent reproduction.

### CLIP

IoU@0.25: 26.65. Result ID: 6999f3c05698665ec474befe.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

Recorded evaluation configuration: {"Residual Module Configuration":"MuRes(V+L)"}. This record does not assert independent reproduction.

### CLIP

IoU@0.25: 25.8. Result ID: 6999f3c05698665ec474befa.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

Recorded evaluation configuration: {"Residual Module Configuration":"Without Residual"}. This record does not assert independent reproduction.

### BLIP-2

IoU@0.25: 25.45. Result ID: 6999f3c05698665ec474bf04.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

Recorded evaluation configuration: {"Residual Module Configuration":"MuRes(V)"}. This record does not assert independent reproduction.

### BLIP-2

IoU@0.25: 16.44. Result ID: 6999f3c05698665ec474bf06.

[Reporting paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6937ad356cfd488761a4ea9c.md>)

Recorded evaluation configuration: {"Residual Module Configuration":"MuRes(V+L)"}. This record does not assert independent reproduction.

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