Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# CLIP-Based Break Dance Move Classifier
|
| 2 |
|
| 3 |
A deep learning model for classifying break dance moves using CLIP (Contrastive Language-Image Pre-Training) embeddings. The model is fine-tuned on break dance videos to classify different power moves including windmills, halos, swipes, and baby mills.
|
|
@@ -130,4 +143,4 @@ If you use this model in your research, please cite:
|
|
| 130 |
journal = {Hugging Face Model Hub},
|
| 131 |
howpublished = {\url{https://github.com/bawolf/breaking_vision_clip_cog}}
|
| 132 |
}
|
| 133 |
-
```
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- openai/clip-vit-large-patch14
|
| 7 |
+
pipeline_tag: video-classification
|
| 8 |
+
library_name: transformers
|
| 9 |
+
tags:
|
| 10 |
+
- dance
|
| 11 |
+
- vision
|
| 12 |
+
- breaking
|
| 13 |
+
---
|
| 14 |
# CLIP-Based Break Dance Move Classifier
|
| 15 |
|
| 16 |
A deep learning model for classifying break dance moves using CLIP (Contrastive Language-Image Pre-Training) embeddings. The model is fine-tuned on break dance videos to classify different power moves including windmills, halos, swipes, and baby mills.
|
|
|
|
| 143 |
journal = {Hugging Face Model Hub},
|
| 144 |
howpublished = {\url{https://github.com/bawolf/breaking_vision_clip_cog}}
|
| 145 |
}
|
| 146 |
+
```
|