diff --git a/docs/index.html b/docs/index.html
index afddc5b..d8384a8 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -34,7 +34,7 @@
 									<div class="content">
 										<header>
 											<h1> COBRA <br /> </h1>
-											<p> Boyang Yu, Aakash Kaku, Kangning Liu, Avinash Parnandi, Emily Fokas, Anita Venkatesan, Natasha Pandit, Rajesh Ranganath, Heidi Schambra and Carlos Fernandez-Granda</p>
+											<p> Joint work by Boyang Yu, Aakash Kaku, Kangning Liu, Avinash Parnandi, Emily Fokas, Anita Venkatesan, Natasha Pandit, Rajesh Ranganath, Heidi Schambra and Carlos Fernandez-Granda</p>
 										</header>
 										<p>Automatic assessment of impairment and disease severity is a key challenge in data-driven medicine. We propose a novel framework, <strong>COnfidence-Based chaRacterization of Anomalies (COBRA)</strong>, to address this challenge, which leverages AI models trained exclusively on healthy subjects. The models are designed to predict a clinically-meaningful attribute of the healthy patients. When presented with data where the attribute is affected by the medical condition of interest, the models experience a decrease in confidence that can be used to quantify deviation from the healthy population. COBRA was applied to quantification of upper-body motion impairment in stroke patients, and severity of knee osteoarthritis from magneticresonance imaging scans.</p>
 										<ul class="actions">
@@ -42,7 +42,7 @@ <h1> COBRA <br /> </h1>
 										</ul>
 									</div>
 									<span class="image object">
-										<img src="images/COBRA-Overview-Stroke.png" alt="" />
+										<img src="images/COBRA-Overview-Stroke-Vertical.png" alt="" />
 									</span>
 								</section>