Update paper.html

_includes/paper.html

@@ -18,8 +18,8 @@ <h2 align="centered" class="title">PAPER</h2>
                         <div>
                           <B><a href="https://ieeexplore.ieee.org/document/10214589"><font size = "+2">Boosting Multi-Modal Unsupervised Domain Adaptation for LiDAR Semantic Segmentation by Self-Supervised Depth Completion</font></a><br></B>
                           <B><i> Adriano Cardace, Andrea Conti, Pierluigi Zama Ramirez, Riccardo Spezialetti, Samuele Salti, Luigi Di Stefano</B></i>
-                            <B><a href="https://github.com/CVLAB-Unibo/CtS"><font size = "+2">Official Code</font></a><br></B>
-                            <br>
+                        <br>
+                            <B><a href="https://github.com/CVLAB-Unibo/CtS"><font size = "+1">Official Code</font></a><br></B>
                           <br>
                           <p>
                             LiDAR semantic segmentation is receiving increased attention due to its deployment in autonomous driving applications. As LiDARs come often with other sensors such as RGB cameras, multi-modal approaches for this task have been developed, which however suffer from the domain shift problem as other deep learning approaches. To address this, we propose a novel Unsupervised Domain Adaptation (UDA) technique for multi-modal LiDAR segmentation. Unlike previous works in this field, we leverage depth completion as an auxiliary task to align features extracted from 2D images across domains, and as a powerful data augmentation for LiDARs.