Update README.md
Browse files
README.md
CHANGED
|
@@ -27,9 +27,12 @@ OmniEmbed generates unified embeddings across multilingual text, images, audio,
|
|
| 27 |
| MIRACL | Multilingual Retrieval | nDCG@10 | 69.1 | BGE‑M3 (69.2) |
|
| 28 |
| VIDORE | Image Document Retrieval | nDCG@5 | 85.8 | DSE‑QWen2 (85.8) |
|
| 29 |
| MSRVTT | Video Retrieval | R@1 | 51.3 | CLIP (31.2) |
|
|
|
|
| 30 |
|
| 31 |
OmniEmbed achieves strong performance, comparable to models specifically optimized for individual tasks.
|
| 32 |
|
|
|
|
|
|
|
| 33 |
---
|
| 34 |
|
| 35 |
### Usage
|
|
|
|
| 27 |
| MIRACL | Multilingual Retrieval | nDCG@10 | 69.1 | BGE‑M3 (69.2) |
|
| 28 |
| VIDORE | Image Document Retrieval | nDCG@5 | 85.8 | DSE‑QWen2 (85.8) |
|
| 29 |
| MSRVTT | Video Retrieval | R@1 | 51.3 | CLIP (31.2) |
|
| 30 |
+
| AudioCaps | Audio Retrieval | R@1 | 34.0 | [*](https://paperswithcode.com/sota/text-to-audio-retrieval-on-audiocaps) |
|
| 31 |
|
| 32 |
OmniEmbed achieves strong performance, comparable to models specifically optimized for individual tasks.
|
| 33 |
|
| 34 |
+
> Although multiple baselines exist on AudioCaps, we could not identify a consistent query/corpus setting in the literature for direct comparison.
|
| 35 |
+
|
| 36 |
---
|
| 37 |
|
| 38 |
### Usage
|