Add pipeline tag, paper, and code links to model card
#1
by
nielsr
HF Staff
- opened
README.md
CHANGED
|
@@ -1,3 +1,16 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
pipeline_tag: image-to-text
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Talking Points: Describing and Localizing Pixels
|
| 7 |
+
|
| 8 |
+
This repository contains the Point Descriptor and Point Localizer models presented in the paper [Talking Points: Describing and Localizing Pixels](https://huggingface.co/papers/2510.14583).
|
| 9 |
+
|
| 10 |
+
Talking Points introduces a novel framework for pixel-level grounding. It consists of two complementary components: a Point Descriptor that generates rich, contextual descriptions of individual keypoints, and a Point Localizer that regresses precise pixel coordinates from these descriptions. Unlike prior work, our approach produces free-form, coarse-to-fine descriptions that situate keypoints within their visual context.
|
| 11 |
+
|
| 12 |
+
<div align="center">
|
| 13 |
+
<img src="https://github.com/matanr/Talking_Points/raw/master/images/teaser.png" alt="Talking Points Teaser Image">
|
| 14 |
+
</div>
|
| 15 |
+
|
| 16 |
+
For detailed information on installation, dataset creation, training, and evaluation scripts, please refer to the official [GitHub repository](https://github.com/matanr/Talking_Points).
|