Update README.md
Browse files
README.md
CHANGED
|
@@ -7,7 +7,7 @@ pipeline_tag: visual-question-answering
|
|
| 7 |
---
|
| 8 |
# Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input
|
| 9 |
|
| 10 |
-
**Kangaroo** has been released. Please check out our [blog](https://kangaroogroup.github.io/Kangaroo.github.io/) and [github](https://github.com/KangarooGroup/Kangaroo) for details.
|
| 11 |
|
| 12 |
## Abstract
|
| 13 |
We introduce <strong>Kangaroo</strong>, a powerful Multimodal Large Language Model designed for long-context video understanding. Our presented Kangaroo model shows remarkable performance across diverse video understanding tasks including video caption, QA and conversation. Generally, our key contributions in this work can be summarized as follows:
|
|
|
|
| 7 |
---
|
| 8 |
# Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input
|
| 9 |
|
| 10 |
+
**Kangaroo** has been released. Please check out our [paper](https://arxiv.org/pdf/2408.15542), [blog](https://kangaroogroup.github.io/Kangaroo.github.io/) and [github](https://github.com/KangarooGroup/Kangaroo) for details.
|
| 11 |
|
| 12 |
## Abstract
|
| 13 |
We introduce <strong>Kangaroo</strong>, a powerful Multimodal Large Language Model designed for long-context video understanding. Our presented Kangaroo model shows remarkable performance across diverse video understanding tasks including video caption, QA and conversation. Generally, our key contributions in this work can be summarized as follows:
|