# Open-Vocabulary Fine-Grained Emotion Recognition on OV-MERD

Source: [Open-Vocabulary Fine-Grained Emotion Recognition on OV-MERD](<https://www.sota2.com/research/sota/open-vocabulary-fine-grained-emotion-recognition-on-ov-merd>)

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

Data updated: 2026-03-18T08:51:59.674Z

Evaluation of Open-Vocabulary Fine-Grained Emotion Recognition performance on the OV-MERD dataset, reporting coarse-grained and fine-grained F1 scores.

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 | Open-Vocabulary Fine-Grained Emotion Recognition |
| Dataset (including any stated split) | OV-MERD |
| Metric | Coarse-grained F1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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

- [Coarse-grained F1](<https://www.sota2.com/research/sota/open-vocabulary-fine-grained-emotion-recognition-on-ov-merd.md?metric=Coarse-grained%20F1>): Higher is better; unit: PERCENT.

- [Fine-grained F1](<https://www.sota2.com/research/sota/open-vocabulary-fine-grained-emotion-recognition-on-ov-merd.md?metric=Fine-grained%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Coarse-grained F1 | Result date | Report paper |
| --- | --- | --- | --- |
| HyDRA | 55.52 | Not recorded | 69ba318b0636e5bf4afc0806 |
| MPLUG-OWL | 46.28 | Not recorded | 69ba318b0636e5bf4afc0806 |
| AFFECTGPT | 44.98 | Not recorded | 69ba318b0636e5bf4afc0806 |
| VIDEOCHAT | 43.48 | Not recorded | 69ba318b0636e5bf4afc0806 |
| CHAT-UNIVI | 43.33 | Not recorded | 69ba318b0636e5bf4afc0806 |
| PANDAGPT | 41.97 | Not recorded | 69ba318b0636e5bf4afc0806 |
| LLAMA-VID | 40.89 | Not recorded | 69ba318b0636e5bf4afc0806 |
| VIDEO-CHATGPT | 35.29 | Not recorded | 69ba318b0636e5bf4afc0806 |
| BASELINE | 34.09 | Not recorded | 69ba318b0636e5bf4afc0806 |
| VIDEOCHAT2 | 34.07 | Not recorded | 69ba318b0636e5bf4afc0806 |
| R1-OMNI | 32.8 | Not recorded | 69ba318b0636e5bf4afc0806 |
| BASELINE | 30.98 | Not recorded | 69ba318b0636e5bf4afc0806 |
| VIDEO-LLAVA | 27.4 | Not recorded | 69ba318b0636e5bf4afc0806 |
| OTTER | 14.64 | Not recorded | 69ba318b0636e5bf4afc0806 |

### HyDRA

Coarse-grained F1: 55.52. Result ID: 69ba670247f34ce924a46b19.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318b0636e5bf4afc0806.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba318b0636e5bf4afc0806.md>)

Recorded evaluation configuration: {"#PARAMS":"0.5B"}. This record does not assert independent reproduction.

### MPLUG-OWL

Coarse-grained F1: 46.28. Result ID: 69ba670247f34ce924a46b15.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318b0636e5bf4afc0806.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ae1e209131cea57d83.md>)

[Implementation](<https://github.com/X-PLUG/mPLUG-Owl>)

Recorded evaluation configuration: {"#PARAMS":"7B"}. This record does not assert independent reproduction.

### AFFECTGPT

Coarse-grained F1: 44.98. Result ID: 69ba670247f34ce924a46b16.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318b0636e5bf4afc0806.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78621e209131cea78187.md>)

Recorded evaluation configuration: {"#PARAMS":"7B"}. This record does not assert independent reproduction.

### VIDEOCHAT

Coarse-grained F1: 43.48. Result ID: 69ba670247f34ce924a46b14.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318b0636e5bf4afc0806.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71ba1e209131cea52cc7.md>)

Recorded evaluation configuration: {"#PARAMS":"7B"}. This record does not assert independent reproduction.

### CHAT-UNIVI

Coarse-grained F1: 43.33. Result ID: 69ba670247f34ce924a46b12.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318b0636e5bf4afc0806.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d31e209131cea58bff.md>)

[Implementation](<https://github.com/PKU-YuanGroup/Chat-UniVi>)

Recorded evaluation configuration: {"#PARAMS":"7B"}. This record does not assert independent reproduction.

### PANDAGPT

Coarse-grained F1: 41.97. Result ID: 69ba670247f34ce924a46b13.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318b0636e5bf4afc0806.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea46009.md>)

Recorded evaluation configuration: {"#PARAMS":"7B"}. This record does not assert independent reproduction.

### LLAMA-VID

Coarse-grained F1: 40.89. Result ID: 69ba670247f34ce924a46b11.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318b0636e5bf4afc0806.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71461e209131cea50559.md>)

[Implementation](<https://github.com/dvlab-research/LLaMA-VID>)

Recorded evaluation configuration: {"#PARAMS":"7B"}. This record does not assert independent reproduction.

### VIDEO-CHATGPT

Coarse-grained F1: 35.29. Result ID: 69ba670247f34ce924a46b10.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318b0636e5bf4afc0806.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73841e209131cea5ce32.md>)

[Implementation](<https://github.com/mbzuai-oryx/Video-ChatGPT>)

Recorded evaluation configuration: {"#PARAMS":"7B"}. This record does not assert independent reproduction.

### BASELINE

Coarse-grained F1: 34.09. Result ID: 69ba670247f34ce924a46b18.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318b0636e5bf4afc0806.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76bb1e209131cea6ecef.md>)

Recorded evaluation configuration: {"#PARAMS":"7B"}. This record does not assert independent reproduction.

### VIDEOCHAT2

Coarse-grained F1: 34.07. Result ID: 69ba670247f34ce924a46b0f.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318b0636e5bf4afc0806.md>)

Recorded evaluation configuration: {"#PARAMS":"7B"}. This record does not assert independent reproduction.

### R1-OMNI

Coarse-grained F1: 32.8. Result ID: 69ba670247f34ce924a46b0e.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318b0636e5bf4afc0806.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa775e1e209131cea72c53.md>)

Recorded evaluation configuration: {"#PARAMS":"0.5B"}. This record does not assert independent reproduction.

### BASELINE

Coarse-grained F1: 30.98. Result ID: 69ba670247f34ce924a46b17.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318b0636e5bf4afc0806.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76bb1e209131cea6ecef.md>)

Recorded evaluation configuration: {"#PARAMS":"0.5B"}. This record does not assert independent reproduction.

### VIDEO-LLAVA

Coarse-grained F1: 27.4. Result ID: 69ba670247f34ce924a46b0d.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318b0636e5bf4afc0806.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65534.md>)

[Implementation](<https://github.com/PKU-YuanGroup/Video-LLaVA>)

Recorded evaluation configuration: {"#PARAMS":"7B"}. This record does not assert independent reproduction.

### OTTER

Coarse-grained F1: 14.64. Result ID: 69ba670247f34ce924a46b0c.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318b0636e5bf4afc0806.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a411e209131cea81f51.md>)

Recorded evaluation configuration: {"#PARAMS":"7B"}. This record does not assert independent reproduction.

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