Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,7 @@
|
|
| 1 |
# Narrations / Steps to Video Aligner (NSVA)
|
| 2 |
|
|
|
|
|
|
|
| 3 |
NSVA is a lightweight Transformer-based architecture, where the narration or procedural steps are used as queries, to iteratively attend the video features, and output the alignability or optimal temporal windows.
|
| 4 |
|
| 5 |
[[project page]](https://lzq5.github.io/Video-Text-Alignment/)
|
|
|
|
| 1 |
# Narrations / Steps to Video Aligner (NSVA)
|
| 2 |
|
| 3 |
+
|
| 4 |
+
|
| 5 |
NSVA is a lightweight Transformer-based architecture, where the narration or procedural steps are used as queries, to iteratively attend the video features, and output the alignability or optimal temporal windows.
|
| 6 |
|
| 7 |
[[project page]](https://lzq5.github.io/Video-Text-Alignment/)
|