Update README.md
Browse files
README.md
CHANGED
|
@@ -13,12 +13,12 @@ pipeline_tag: visual-question-answering
|
|
| 13 |
|
| 14 |
|
| 15 |
|
| 16 |
-
## Dataset Description
|
| 17 |
-
|
| 18 |
- **Repository:** [Shot2Story](https://github.com/bytedance/Shot2Story)
|
| 19 |
- **Paper:** [2312.10300](https://arxiv.org/abs/2312.10300)
|
| 20 |
- **Point of Contact:** mailto:[Mingfei Han]([email protected])
|
| 21 |
|
|
|
|
|
|
|
| 22 |
**For video data downloading, please have a look at [this issue](https://github.com/bytedance/Shot2Story/issues/5).**
|
| 23 |
|
| 24 |
We are excited to release a new video-text benchmark for multi-shot video understanding. This release contains a 134k version of our dataset. It includes detailed long summaries (human annotated + GPTV generated) for 134k videos and shot captions (human annotated) for 188k video shots. Please check the dataset [here](https://huggingface.co/datasets/mhan/Shot2Story-134K).
|
|
|
|
| 13 |
|
| 14 |
|
| 15 |
|
|
|
|
|
|
|
| 16 |
- **Repository:** [Shot2Story](https://github.com/bytedance/Shot2Story)
|
| 17 |
- **Paper:** [2312.10300](https://arxiv.org/abs/2312.10300)
|
| 18 |
- **Point of Contact:** mailto:[Mingfei Han]([email protected])
|
| 19 |
|
| 20 |
+
## Training Dataset
|
| 21 |
+
|
| 22 |
**For video data downloading, please have a look at [this issue](https://github.com/bytedance/Shot2Story/issues/5).**
|
| 23 |
|
| 24 |
We are excited to release a new video-text benchmark for multi-shot video understanding. This release contains a 134k version of our dataset. It includes detailed long summaries (human annotated + GPTV generated) for 134k videos and shot captions (human annotated) for 188k video shots. Please check the dataset [here](https://huggingface.co/datasets/mhan/Shot2Story-134K).
|