Skip to content

Commit

Permalink
add images to website
Browse files Browse the repository at this point in the history
  • Loading branch information
@msohaildanish
msohaildanish committed Nov 29, 2023
1 parent b00bb8e commit 5686f0f
Show file tree
Hide file tree
Showing 2 changed files with 7 additions and 7 deletions.
Binary file added images/geochat_fav.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
14 changes: 7 additions & 7 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -309,7 +309,7 @@ <h2 class="title is-3"><img src="images/logo_geochat.png" alt="geochat" width="6
<div class="column is-six-fifths"
style="display: flex; align-items: flex-start; justify-content: center;">
<figure style="text-align: center;">
<img id="teaser" width="70%" src="images/overview.png">
<img id="teaser" width="70%" src="images/teaser.png">
<!-- <figcaption>
GeoChat can accomplish multiple tasks for remote-sensing (RS) image comprehension in a unified framework. Given suitable task tokens and user queries, the model can generate visually grounded responses (text with corresponding object locations - shown on top), visual question answering on images and regions (top left and bottom right, respectively) as well as scene classification (top right) and normal natural language conversations (bottom). This makes it the first RS VLM with grounding capability.
</figcaption> -->
Expand Down Expand Up @@ -468,7 +468,7 @@ <h2 class="title is-3">Visual Question Answering (VQA)</h2>
<div class="column is-six-fifths"
style="display: flex; align-items: flex-start; justify-content: center;">
<figure style="text-align: center;">
<img id="teaser" width="100%" src="images/qualitative6.png">
<img id="teaser" width="100%" src="images/vqa.jpg">
<figcaption>
Qualitative results of GeoChat's performance in Visual Question Answering.
</figcaption>
Expand Down Expand Up @@ -582,7 +582,7 @@ <h2 class="title is-3">Scene Classification</h2>
<div class="column is-six-fifths"
style="display: flex; align-items: flex-start; justify-content: center;">
<figure style="text-align: center;">
<img id="teaser" width="100%" src="images/qualitative2.png">
<img id="teaser" width="100%" src="images/scene.jpg">
<figcaption>
Qualitative results of GeoChat's performance in scene classification.
</figcaption>
Expand Down Expand Up @@ -644,7 +644,7 @@ <h2 class="title is-3">Region-Level Caption</h2>
<div class="column is-six-fifths"
style="display: flex; align-items: flex-start; justify-content: center;">
<figure style="text-align: center;">
<img id="teaser" width="100%" src="images/qualitative7.png">
<img id="teaser" width="100%" src="images/iden.jpg">
<figcaption>
Qualitative results of GeoChat's performance in region-level caption.<caption></caption>.
</figcaption>
Expand Down Expand Up @@ -701,7 +701,7 @@ <h2 class="title is-3">Grounded Description</h2>
<div class="column is-six-fifths"
style="display: flex; align-items: flex-start; justify-content: center;">
<figure style="text-align: center;">
<img id="teaser" width="100%" src="images/qualitative3.png">
<img id="teaser" width="100%" src="images/grounded.jpg">
<figcaption>
Qualitative results of GeoChat's performance in grounded description.
</figcaption>
Expand Down Expand Up @@ -754,8 +754,8 @@ <h2 class="title is-3">Referring Expression</h2>
<div class="column is-six-fifths"
style="display: flex; align-items: flex-start; justify-content: center;">
<figure style="text-align: center;">
<img id="teaser" width="100%" src="images/qualitative4.png">
<img id="teaser" width="100%" src="images/qualitative5.png">
<img id="teaser" width="100%" src="images/ref1.jpg">
<img id="teaser" width="100%" src="images/ref_2.jpg">
<figcaption>
Qualitative results of GeoChat's performance in referring expression.
</figcaption>
Expand Down

0 comments on commit 5686f0f

Please sign in to comment.