update website

docs/index.html

@@ -174,20 +174,21 @@ <h3 class="subtitle has-text-centered">
             <h2 class="title is-3">Abstract</h2>
             <div class="content has-text-justified">
               <p>
-                The challenge in object-based visual reasoning lies in generating descriptive yet distinct concept
-                representations. Moreover, doing this in an unsupervised fashion requires human users to understand a
-                model's learned concepts and potentially revise false concepts. In addressing this challenge, we
-                introduce the <span class="method">Neural Concept Binder</span>, a new framework for deriving discrete
-                concept representations
-                resulting in what we term “concept-slot encodings”. These encodings leverage both "soft binding" via
-                object-centric block-slot encodings and "hard binding" via retrieval-based inference. The <span
-                  class="method">Neural Concept
-                  Binder</span> facilitates straightforward concept inspection and direct integration of external
-                knowledge, such
-                as human input or insights from other AI models like GPT-4. Additionally, we demonstrate that
-                incorporating the hard binding mechanism does not compromise performance; instead, it enables seamless
-                integration into both neural and symbolic modules for intricate reasoning tasks, as evidenced by
-                evaluations on our newly introduced CLEVR-Sudoku dataset.
+                The challenge in object-based visual reasoning lies in generating concept representations 
+                that are both descriptive and distinct. Achieving this in an unsupervised manner requires 
+                human users to understand the model's learned concepts and, if necessary, revise incorrect 
+                ones. To address this challenge, we introduce the <span class="method">Neural Concept Binder</span> (NCB), 
+                a novel framework for deriving both discrete and continuous concept representations, which 
+                we refer to as “concept-slot encodings”. NCB employs two types of binding: “soft binding”, 
+                which leverages the recent SysBinder mechanism to obtain object-factor encodings, and subsequent 
+                “hard binding”, achieved through hierarchical clustering and retrieval-based inference. 
+                This enables obtaining expressive, discrete representations from unlabeled images. 
+                Moreover, the structured nature of NCB's concept representations allows for intuitive 
+                inspection and the straightforward integration of external knowledge, such as human input 
+                or insights from other AI models like GPT-4. Additionally, we demonstrate that incorporating 
+                the hard binding mechanism preserves model performance while enabling seamless integration into 
+                both neural and symbolic modules for complex reasoning tasks. We validate the effectiveness of 
+                NCB through evaluations on our newly introduced CLEVR-Sudoku dataset.
               </p>
             </div>
           </div>
@@ -200,11 +201,12 @@ <h2 class="title is-3">Abstract</h2>
 
 
   <section class="section">
+
     <div class="container is-max-desktop">
 
       <div class="columns is-centered">
         <div class="column is-full-width">
-          <h2 class="title is-3">Learn Inspectable and Revisable Concepts</h2>
+          <h2 class="title is-3">Learn Expressive, yet Inspectable and Revisable Concepts</h2>
 
           <div class="content has-text-justified">
             <p>
@@ -222,6 +224,17 @@ <h2 class="title is-3">Learn Inspectable and Revisable Concepts</h2>
       </div>
       <br />
 
+      <!-- Video Embed Section -->
+      <div class="columns is-centered has-text-centered">
+        <div class="column is-four-fifths">
+          <h2 class="title is-3">NCB Step by Step</h2>
+          <video style="width: 100%; max-width: 1000px; height: auto;" controls>
+          <source src="./static/images/Presentation_website.mp4" type="video/mp4">
+          <p>Your browser does not support the video element. <a href="./static/images/Presentation_website.mp4">Download the video</a>.</p>          </video>
+        </div>
+      </div>
+      <!--/ Video Embed Section -->
+
       <!-- Interpretability. -->
       <div class="columns is-centered">
         <div class="column is-full-width">
@@ -263,9 +276,22 @@ <h2 class="title is-3">CLEVR Sudoku</h2>
                 varying degrees of difficulty. Each image is annotated with the correct solution to the puzzle, which
                 serves as the ground truth for evaluating the model's performance.
               </p>
-              <p>CLEVR-Sudoku requires visual perception as well as deductive reasoning skills. We as humans are able to
-                abstract the relevant information from the images to reason about missing cells. Try for yourself!</p>
-
+                <p><strong>
+                  CLEVR-Sudoku requires visual perception as well as deductive reasoning skills. Now you can try solving the puzzles yourself directly on this website! 
+                  Simply place the images where you think they belong and see if its right!
+                </strong></p>
+
+                <!-- Call to Action Button -->
+                <div class="has-text-centered">
+                  <a href="#sudoku-container" class="button is-primary is-large is-rounded">
+                    <span class="icon">
+                      <i class="fas fa-play-circle"></i>
+                    </span>
+                    <span>
+                      Play CLEVR-Sudoku Now!
+                    </span>
+                  </a>
+                </div>
             </div>
 
             <!-- Sudoku -->
@@ -338,15 +364,12 @@ <h2 class="title">BibTeX</h2>
         <div class="column is-8">
           <div class="content">
             <p>
-              This work was supported by the Priority Program (SPP) 2422 in the subproject "Optimization of active
-              surface
-              design of high-speed progressive tools using machine and deep learning algorithms" funded by the
-              German Research Foundation (DFG), the "ML2MT" project from the Volkswagen Stiftung and the
-              "The Adaptive Mind" project from the Hessian Ministry of Science and Arts (HMWK). It has further
-              benefited from the HMWK projects "The Third Wave of Artificial Intelligence - 3AI", and Hessian.AI,
-              as well as the Hessian research priority program LOEWE within the project WhiteBox, the ICT-48
-              Network of AI Research Excellence Center "TAILOR" (EU Horizon 2020, GA No 952215) and the
-              EU-funded "TANGO" project (EU Horizon 2023, GA No 57100431).
+              This work was supported by the Priority Program (SPP) 2422 in the subproject “Optimization of active surface design 
+              of high-speed progressive tools using machine and deep learning algorithms“ funded by the German Research Foundation (DFG), 
+              the ”ML2MT” project from the Volkswagen Stiftung and the ”The Adaptive Mind” project from the Hessian Ministry of Science 
+              and Arts (HMWK). It has further benefited from the HMWK projects ”The Third Wave of Artificial Intelligence - 3AI”, 
+              and Hessian.AI, as well as the Hessian research priority program LOEWE within the project WhiteBox, and the EU-funded 
+              “TANGO” project (EU Horizon 2023, GA No 57100431).
             </p>
             <p>The website template is based on the source code of <a
                 href="https://github.com/nerfies/nerfies.github.io">this