Add pipeline tag, library name, and link to paper
Browse filesThis PR improves the model card by adding the `pipeline_tag` and `library_name` metadata, making the model more discoverable on the Hub. It also explicitly links the model to the associated research paper.
README.md
CHANGED
|
@@ -1,12 +1,14 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
# Video-LLaVA-Seg
|
| 6 |
|
| 7 |
[Project](https://ali2500.github.io/vicas-project/) | [Arxiv](https://arxiv.org/abs/2412.09754)
|
| 8 |
|
| 9 |
-
This is the official baseline implementation for the ViCas dataset.
|
| 10 |
|
| 11 |
For details about setting up the model, refer to the [Video-LLaVA-Seg GitHub repo](https://github.com/Ali2500/Video-LLaVA-Seg/tree/main)
|
| 12 |
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
library_name: transformers
|
| 4 |
+
pipeline_tag: video-text-to-text
|
| 5 |
---
|
| 6 |
|
| 7 |
# Video-LLaVA-Seg
|
| 8 |
|
| 9 |
[Project](https://ali2500.github.io/vicas-project/) | [Arxiv](https://arxiv.org/abs/2412.09754)
|
| 10 |
|
| 11 |
+
This is the official baseline implementation for the ViCas dataset, presented in the paper [ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation](https://huggingface.co/papers/2412.09754).
|
| 12 |
|
| 13 |
For details about setting up the model, refer to the [Video-LLaVA-Seg GitHub repo](https://github.com/Ali2500/Video-LLaVA-Seg/tree/main)
|
| 14 |
|