# Emergent modality binding (au -\> te -\> vi) on AVE (test)

Source: [Emergent modality binding (au -\> te -\> vi) on AVE (test)](<https://www.sota2.com/research/sota/emergent-modality-binding-au-te-vi-on-ave-test>)

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

Data updated: 2026-02-26T06:09:43.587Z

Evaluation of emergent modality binding performance, specifically mapping audio to text and then to video, on the test split of the AVE dataset, measured by mAP.

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 | Emergent modality binding (au -\> te -\> vi) |
| Dataset (including any stated split) | AVE (test) |
| Metric | mAP |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [mAP](<https://www.sota2.com/research/sota/emergent-modality-binding-au-te-vi-on-ave-test.md?metric=mAP>): Higher is better; unit: SCALAR.

## Recorded results

| Method | mAP | Result date | Report paper |
| --- | --- | --- | --- |
| VCLIP+CLAP+BB | 0.168 | Not recorded | 698969e1c97a0b3e3b5dc383 |
| Ex-MCR | 0.071 | Not recorded | 698969e1c97a0b3e3b5dc383 |
| VCLIP+CLAP+FT | 0.07 | Not recorded | 698969e1c97a0b3e3b5dc383 |
| C-MCR | 0.067 | Not recorded | 698969e1c97a0b3e3b5dc383 |
| VCLIP+CLAP | 0.042 | Not recorded | 698969e1c97a0b3e3b5dc383 |

### VCLIP+CLAP+BB

mAP: 0.168. Result ID: 6998e85b5698665ec44cc46c.

[Reporting paper](<https://www.sota2.com/research/paper/698969e1c97a0b3e3b5dc383.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698969e1c97a0b3e3b5dc383.md>)

Recorded evaluation configuration: {"Source Dataset":"MSRVTT","Evaluation Protocol":"au -\> te -\> vi"}. This record does not assert independent reproduction.

### Ex-MCR

mAP: 0.071. Result ID: 6998e85b5698665ec44cc46b.

[Reporting paper](<https://www.sota2.com/research/paper/698969e1c97a0b3e3b5dc383.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d51e209131cea4d7d6.md>)

[Implementation](<https://github.com/MCR-PEFT/Ex-MCR>)

Recorded evaluation configuration: {"Source Dataset":"MSRVTT","Evaluation Protocol":"au -\> te -\> vi"}. This record does not assert independent reproduction.

### VCLIP+CLAP+FT

mAP: 0.07. Result ID: 6998e85b5698665ec44cc469.

[Reporting paper](<https://www.sota2.com/research/paper/698969e1c97a0b3e3b5dc383.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af21e209131cea2b4a1.md>)

[Implementation](<https://github.com/pytorch/fairseq/tree/main/examples/MMPT>)

Recorded evaluation configuration: {"Source Dataset":"MSRVTT","Evaluation Protocol":"au -\> te -\> vi"}. This record does not assert independent reproduction.

### C-MCR

mAP: 0.067. Result ID: 6998e85b5698665ec44cc46a.

[Reporting paper](<https://www.sota2.com/research/paper/698969e1c97a0b3e3b5dc383.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70e61e209131cea4dd0e.md>)

[Implementation](<https://c-mcr.github.io/C-MCR/>)

Recorded evaluation configuration: {"Source Dataset":"MSRVTT","Evaluation Protocol":"au -\> te -\> vi"}. This record does not assert independent reproduction.

### VCLIP+CLAP

mAP: 0.042. Result ID: 6998e85b5698665ec44cc468.

[Reporting paper](<https://www.sota2.com/research/paper/698969e1c97a0b3e3b5dc383.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af21e209131cea2b4a1.md>)

[Implementation](<https://github.com/pytorch/fairseq/tree/main/examples/MMPT>)

Recorded evaluation configuration: {"Source Dataset":"MSRVTT","Evaluation Protocol":"au -\> te -\> vi"}. This record does not assert independent reproduction.

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