README metadata
Browse files
README.md
CHANGED
|
@@ -1,8 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# TimeSformer-GPT2 Video Captioning
|
| 2 |
|
| 3 |
Vision Encoder Model: [timesformer-base-finetuned-k600](https://huggingface.co/facebook/timesformer-base-finetuned-k600) \
|
| 4 |
Text Decoder Model: [gpt2](https://huggingface.co/gpt2)
|
| 5 |
|
|
|
|
|
|
|
|
|
|
| 6 |
#### Example Inference Code:
|
| 7 |
```python
|
| 8 |
import av
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- HuggingFaceM4/vatex
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
metrics:
|
| 7 |
+
- bleu
|
| 8 |
+
- meteor
|
| 9 |
+
- rouge
|
| 10 |
+
pipeline_tag: image-to-text
|
| 11 |
+
---
|
| 12 |
# TimeSformer-GPT2 Video Captioning
|
| 13 |
|
| 14 |
Vision Encoder Model: [timesformer-base-finetuned-k600](https://huggingface.co/facebook/timesformer-base-finetuned-k600) \
|
| 15 |
Text Decoder Model: [gpt2](https://huggingface.co/gpt2)
|
| 16 |
|
| 17 |
+
#### Evaluation Result:
|
| 18 |
+
67.2 CIDEr on [VaTeX](https://eric-xw.github.io/vatex-website/index.html) public test set
|
| 19 |
+
|
| 20 |
#### Example Inference Code:
|
| 21 |
```python
|
| 22 |
import av
|