Skip to content

Commit

Permalink
Update index.html
Browse files Browse the repository at this point in the history
  • Loading branch information
tirtho149 authored Nov 10, 2024
1 parent f1b7daf commit 6af954d
Showing 1 changed file with 4 additions and 6 deletions.
10 changes: 4 additions & 6 deletions index.html
Original file line number Diff line number Diff line change
Expand Up @@ -145,7 +145,7 @@ <h2 class="title is-3" style="margin: 0;">Dataset Features</h2>

<!-- First Image -->
<div class="publication-image" id="image-container-1">
<img src="static/images/dataser.png" alt="Category Distribution" style="cursor: pointer; width: 100%; height: auto;">
<img src="static/images/dataset.png" alt="Category Distribution" style="cursor: pointer; width: 100%; height: auto;">
</div>
<p class="description">
Example images input to NeRFs for reconstruction across 3 different scenarios. (A) Scenario I: Indoor single object. (B) Scenario II: Indoor multiple objects. (C) Scenario III:Outdoor scene
Expand All @@ -159,7 +159,7 @@ <h2 class="title is-3" style="margin: 0;">Dataset Features</h2>
<img src="static/images/Workflow_page_1.png" alt="Sample Image 3" style="cursor: pointer; width: 80%; height: auto;">
</div>
<p class="description">
Workflow for 3D reconstruction and evaluation. The different steps of the above workflow is explained in detail below.
Workflow for 3D reconstruction and evaluation.
</div>
</div>
</div>
Expand All @@ -177,16 +177,14 @@ <h2 class="title is-3" style="margin: 0;">Dataset Features</h2>
<h2 class="title is-4">New Benchmark</h2>
<div class="content">
<p>
From <b>AgEval</b>, we created three new benchmark datasets for plant Stress Phenotyping tasks with Multimodal LLMs. <br><br>
They are- <b>Identification (I)</b>, <b>Classification (C)</b> and <b>Quantification (Q)</b>.

</p>
</div>

<div class="image-container" style="text-align: center;">
<img src="static/images/BenchMark.png" alt="lifestages" style="width: 80%; height: auto;">
<p class="caption has-text-centered">
Performance comparison of models across 0-shot, 2-shot, and 8-shot settings on various datasets. F1 scores are shown directly,
while NMAE is inverted (100 - NMAE) for consistent visualization, with higher values indicating better performance

</p>
</div>
<div class="image-container" style="text-align: center;">
Expand Down

0 comments on commit 6af954d

Please sign in to comment.