Add metadata, project page link and sample usage
Browse filesHi! I'm Niels from the community science team at Hugging Face.
I've opened this PR to improve the model card for DeepIntuit by:
- Adding the `video-classification` pipeline tag to improve discoverability.
- Adding the `library_name: transformers` metadata to enable automated code snippets.
- Including a link to the official project page.
- Adding a sample usage section based on the instructions provided in the GitHub repository.
These changes help users understand how to use the model and make it more visible on the Hugging Face Hub.
README.md
CHANGED
|
@@ -1,9 +1,11 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
datasets:
|
| 4 |
-
- violetcliff/SmartHome-Bench
|
| 5 |
base_model:
|
| 6 |
- Qwen/Qwen2.5-VL-7B-Instruct
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
# DeepIntuit
|
|
@@ -17,6 +19,7 @@ The model is introduced in:
|
|
| 17 |
**From Imitation to Intuition: Intrinsic Reasoning for Open-Instance Video Classification**
|
| 18 |
📄 Paper: [https://arxiv.org/abs/2603.10300](https://arxiv.org/abs/2603.10300)
|
| 19 |
💻 Code: [https://github.com/BWGZK-keke/DeepIntuit](https://github.com/BWGZK-keke/DeepIntuit)
|
|
|
|
| 20 |
|
| 21 |
---
|
| 22 |
|
|
@@ -44,6 +47,18 @@ DeepIntuit is designed for research on:
|
|
| 44 |
* reasoning-enhanced multimodal learning
|
| 45 |
* safety-sensitive video analysis
|
| 46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
|
| 48 |
## Citation
|
| 49 |
|
|
@@ -51,6 +66,7 @@ DeepIntuit is designed for research on:
|
|
| 51 |
@article{zhang2026deepintuit,
|
| 52 |
title={From Imitation to Intuition: Intrinsic Reasoning for Open-Instance Video Classification},
|
| 53 |
author={Zhang, Ke and Zhao, Xiangchen and Tian, Yunjie and Zheng, Jiayu and Patel, Vishal M and Fu, Di},
|
|
|
|
| 54 |
year={2026}
|
| 55 |
}
|
| 56 |
-
```
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
| 2 |
base_model:
|
| 3 |
- Qwen/Qwen2.5-VL-7B-Instruct
|
| 4 |
+
datasets:
|
| 5 |
+
- violetcliff/SmartHome-Bench
|
| 6 |
+
license: apache-2.0
|
| 7 |
+
pipeline_tag: video-classification
|
| 8 |
+
library_name: transformers
|
| 9 |
---
|
| 10 |
|
| 11 |
# DeepIntuit
|
|
|
|
| 19 |
**From Imitation to Intuition: Intrinsic Reasoning for Open-Instance Video Classification**
|
| 20 |
📄 Paper: [https://arxiv.org/abs/2603.10300](https://arxiv.org/abs/2603.10300)
|
| 21 |
💻 Code: [https://github.com/BWGZK-keke/DeepIntuit](https://github.com/BWGZK-keke/DeepIntuit)
|
| 22 |
+
🏠 Project Page: [https://bwgzk-keke.github.io/DeepIntuit/](https://bwgzk-keke.github.io/DeepIntuit/)
|
| 23 |
|
| 24 |
---
|
| 25 |
|
|
|
|
| 47 |
* reasoning-enhanced multimodal learning
|
| 48 |
* safety-sensitive video analysis
|
| 49 |
|
| 50 |
+
## Sample Usage
|
| 51 |
+
|
| 52 |
+
To run inference using the code provided in the [official repository](https://github.com/BWGZK-keke/DeepIntuit):
|
| 53 |
+
|
| 54 |
+
```bash
|
| 55 |
+
cd stage2_model
|
| 56 |
+
python inference.py \
|
| 57 |
+
--model_path BWGZK/DeepIntuit \
|
| 58 |
+
--video_path path_to_video.mp4
|
| 59 |
+
```
|
| 60 |
+
|
| 61 |
+
---
|
| 62 |
|
| 63 |
## Citation
|
| 64 |
|
|
|
|
| 66 |
@article{zhang2026deepintuit,
|
| 67 |
title={From Imitation to Intuition: Intrinsic Reasoning for Open-Instance Video Classification},
|
| 68 |
author={Zhang, Ke and Zhao, Xiangchen and Tian, Yunjie and Zheng, Jiayu and Patel, Vishal M and Fu, Di},
|
| 69 |
+
journal={arXiv preprint arXiv:2603.10300},
|
| 70 |
year={2026}
|
| 71 |
}
|
| 72 |
+
```
|