# Emotional Attribute Prediction on MSP-IMPROV Audio-Visual

Source: [Emotional Attribute Prediction on MSP-IMPROV Audio-Visual](<https://www.sota2.com/research/sota/emotional-attribute-prediction-on-msp-improv-audio-visual>)

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

Data updated: 2026-02-26T05:35:01.627Z

Evaluation of dimensional emotion prediction (Arousal, Valence, Dominance) performance on the MSP-IMPROV Audio-Visual 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 | Emotional Attribute Prediction |
| Dataset (including any stated split) | MSP-IMPROV Audio-Visual |
| Metric | Arousal |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Arousal](<https://www.sota2.com/research/sota/emotional-attribute-prediction-on-msp-improv-audio-visual.md?metric=Arousal>): Higher is better; unit: SCALAR.

- [Valence](<https://www.sota2.com/research/sota/emotional-attribute-prediction-on-msp-improv-audio-visual.md?metric=Valence>): Higher is better; unit: SCALAR.

- [Dominance](<https://www.sota2.com/research/sota/emotional-attribute-prediction-on-msp-improv-audio-visual.md?metric=Dominance>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Arousal | Result date | Report paper |
| --- | --- | --- | --- |
| VAVL | 0.856 | Not recorded | 68fa74511e209131cea61059 |
| TLSTM | 0.832 | Not recorded | 68fa74511e209131cea61059 |
| SFAV | 0.786 | Not recorded | 68fa74511e209131cea61059 |
| MulT | 0.775 | Not recorded | 68fa74511e209131cea61059 |
| AuxFormer | 0.672 | Not recorded | 68fa74511e209131cea61059 |
| UAVM | 0.471 | Not recorded | 68fa74511e209131cea61059 |

### VAVL

Arousal: 0.856. Result ID: 69933c093a6c314849149a0a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74511e209131cea61059.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74511e209131cea61059.md>)

[Implementation](<https://github.com/ilucasgoncalves/VAVL>)

Recorded evaluation configuration: {"modality":"audio-visual"}. This record does not assert independent reproduction.

### TLSTM

Arousal: 0.832. Result ID: 69933c093a6c314849149a0e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74511e209131cea61059.md>)

Recorded evaluation configuration: {"modality":"audio-visual"}. This record does not assert independent reproduction.

### SFAV

Arousal: 0.786. Result ID: 69933c093a6c314849149a0d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74511e209131cea61059.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bba1e209131cea2fed0.md>)

[Implementation](<https://github.com/rwightman/pytorch-image-models>)

Recorded evaluation configuration: {"modality":"audio-visual"}. This record does not assert independent reproduction.

### MulT

Arousal: 0.775. Result ID: 69933c093a6c314849149a0f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74511e209131cea61059.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65d61e209131cea0c91f.md>)

[Implementation](<https://github.com/yaohungt/Multimodal-Transformer>)

Recorded evaluation configuration: {"modality":"audio-visual"}. This record does not assert independent reproduction.

### AuxFormer

Arousal: 0.672. Result ID: 69933c093a6c314849149a0c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74511e209131cea61059.md>)

Recorded evaluation configuration: {"modality":"audio-visual"}. This record does not assert independent reproduction.

### UAVM

Arousal: 0.471. Result ID: 69933c093a6c314849149a0b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74511e209131cea61059.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e8c1e209131cea407fa.md>)

[Implementation](<https://github.com/yuangongnd/uavm>)

Recorded evaluation configuration: {"modality":"audio-visual"}. This record does not assert independent reproduction.

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