Hugging Face's logo

Spaces:
altndrr
/
vic
Runtime error

App Files Community
2
altndrr commited on
Commit
c6a2d52
•
1 Parent(s): f52d497

Update README image urls (#2)

Browse files

- Update images url (7d0075ae84ab3202d53ce194ee0b93290666a76d)

Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -20,9 +20,9 @@ Recent advances in large vision-language models have revolutionized the image cl
20
 
21
  <div align="center">
22
 
23
- | <img src="https://altndrr.github.io/vic/assets/images/task_left.png"> | <img src="https://altndrr.github.io/vic/assets/images/task_right.png"> |
24
- | :-------------------------------------------------------------------: | :--------------------------------------------------------------------: |
25
- | Vision Language Model (VLM)-based classification | Vocabulary-free Image Classification |
26
 
27
  </div>
28
 
@@ -30,7 +30,7 @@ In this work, we first empirically verify that representing this semantic space
30
 
31
  <div align="center">
32
 
33
- | <img src="https://altndrr.github.io/vic/assets/images/method.png"> |
34
  | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
35
  | Overview of CaSED. Given an input image, CaSED retrieves the most relevant captions from an external database filtering them to extract candidate categories. We classify image-to-text and text-to-text, using the retrieved captions centroid as the textual counterpart of the input image. |
36
 
 
20
 
21
  <div align="center">
22
 
23
+ | <img src="https://alessandroconti.me/papers/assets/2306.00917/images/task_left.webp"> | <img src="https://alessandroconti.me/papers/assets/2306.00917/images/task_right.webp"> |
24
+ | :-----------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------: |
25
+ | Vision Language Model (VLM)-based classification | Vocabulary-free Image Classification |
26
 
27
  </div>
28
 
 
30
 
31
  <div align="center">
32
 
33
+ | <img src="https://alessandroconti.me/papers/assets/2306.00917/images/method.webp"> |
34
  | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
35
  | Overview of CaSED. Given an input image, CaSED retrieves the most relevant captions from an external database filtering them to extract candidate categories. We classify image-to-text and text-to-text, using the retrieved captions centroid as the textual counterpart of the input image. |
36