moved slides a bit around

presentation/main.tex

@@ -1,4 +1,4 @@
-\documentclass[usenames,dvipsnames]{beamer}
+\documentclass[usenames,dvipsnames, aspectratio=169]{beamer}
 %----------------------------------------------------------------------------------------
 %	Struktur und Pointer Referat
 %   20.04.2020
@@ -40,12 +40,9 @@
 %	 TITLE SLIDE
 %----------------------------------------------------------------------------------------
 
-\title{Cross-Model Pseudo-Labeling}
-
-\subtitle{for Semi-Supervised Action Recognition}
-
+\title{De-Cluttering Scatterplots}
+\subtitle{with Integral Images}
 \author{Lukas Heiligenbrunner}
-
 \date{\today}
 
 %------------------------------------------------
@@ -59,276 +56,351 @@
     \end{frame}
 
 
-%----------------------------------------------------------------------------------------
-%	 SECTION 1
-%----------------------------------------------------------------------------------------
-% todo pic of action
-
-
-    \section{The Goal}
-    \begin{frame}{The goal}
-        \begin{itemize}
-            \item Train model
-            \item Recognize action of person
-            \item From video [$\approx$10sec]
-            \item E.g.:
-            \begin{itemize}
-                \item brushing hair
-                \item riding bike
-                \item dancing
-                \item playing violin
-            \end{itemize}
-            \item As generic as possible
-        \end{itemize}
-    \end{frame}
 
 %----------------------------------------------------------------------------------------
-%	 SECTION 2
+%	 SECTION 1: INTRODUCTION
 %----------------------------------------------------------------------------------------
 
-
-    \section{The Problem} % Section title slide, unnumbered
-
-%------------------------------------------------
-
-    \begin{frame}{Missing Labels}
-        \begin{itemize}
-            \item Supervised action recoginition
-            \begin{itemize}
-                \item lots of labeled samples necessary
-                \item videos
-            \end{itemize}
-            \item Labeling Samples very expensive
-            \begin{itemize}
-                \item Avoid!
-            \end{itemize}
-            \item Tremendous amount of unlabled data
-            \begin{itemize}
-                \item YouTube
-            \end{itemize}
-            \item Using semi-supervised learning might be benefitial
-        \end{itemize}
-    \end{frame}
-
-%------------------------------------------------
-
-    \begin{frame}{What's all about Semi supervised?}
-        \begin{itemize}
-            \item Supervised learning
-            \begin{itemize}
-                \item Data samples
-                \item Target labels
-                \item Each sample is associated to target label
-            \end{itemize}
-            \item Unsupervised learning
-            \begin{itemize}
-                \item Data samples
-                \item target is to find patterns in data
-                \item without supervision
-            \end{itemize}
-            \item Semi-Supervised learning
-            \begin{itemize}
-                \item combination of both
-                \item have labeled \& unlabeled data
-                \item labeled data guides learning process
-                \item unlabled helps to gain additional information
-                \item goal is performance improvement
-            \end{itemize}
-        \end{itemize}
-    \end{frame}
-
-%------------------------------------------------
-
-    \begin{frame}[allowframebreaks]{What's already been done}
-        \begin{itemize}
-            \item Pseudo-labeling
-            \item Train model on labeled data
-            \begin{itemize}
-                \item Eg. 1\%/10\% of data labeled
-            \end{itemize}
-            \item Predict pseudo-labels from unlabeled data
-            \item Confidence of prediction [Threshold]
-            \item Drop/Use prediction to train model further
-            \item Finally use pseudo-labels + 1/10\% to train main model
-
-        \end{itemize}
-
-        \framebreak
-        \begin{itemize}
-            \item quantity and quality of pseudo-labels
-            \item significant impact on main model accuracy!
-            \item we want to improve pseudo-label framework as much as possible
-        \end{itemize}
-    \end{frame}
-
 %----------------------------------------------------------------------------------------
-%	 SECTION 2
+%	SECTION 2: PROBLEM
 %----------------------------------------------------------------------------------------
 
+    \section{Introduction}
 
-    \section{Cross-Model Pseudo-Labeling}
-
-    \begin{frame}[allowframebreaks]{Papers approach}
+    \begin{frame}{Problem: Scatterplots Clutter}
         \begin{itemize}
-            \item Based on complementary-representations of model
-            \item Models of different size
-            \item Different structural-bias $\rightarrow$ different category-wise performance
-            \item Small model
+            \item Scatterplots are fundamental for exploring multidimensional data
+            \item Modern datasets: millions of samples
+            \item Pixel resolution fixed → many samples map to the same pixel
+            \item This results in \textbf{overplotting}
+            \item Consequences:
             \begin{itemize}
-                \item lower capacity
-                \item better captures temporal dynamics in recognizing actions
-                \item scene changes/motion over time
+                \item Occlusion of clusters
+                \item Loss of density information
+                \item Hard to select and see individual items
+                %\item Misleading visual perception
             \end{itemize}
-            \item Large model
+            \item A method is needed to \textbf{declutter} without losing structure
+        \end{itemize}
+    \end{frame}
+
+    \begin{frame}
+        \centering
+        \includegraphics[scale=0.8]{rsc/overplotting}
+        \footnotesize\text{Source: \cite{statisticsglobe_overplotting_r}}
+    \end{frame}
+
+    \begin{frame}{Goal of the Paper}
+        \begin{itemize}
+            \item Goal:
             \begin{itemize}
-                \item better learns spatial semantics
-                \item to distinguish different action instances
-                \item localize/identify objects in specific scene
+                \item Reduce clutter
+                \item Preserve neighborhood relations
+                \item Achieve uniform sample distribution
+                \item Maintain interpretability
             \end{itemize}
         \end{itemize}
+    \end{frame}
 
-        \framebreak
-
+    \begin{frame}{Limitations of Traditional Approaches}
         \begin{itemize}
-            \item Cross-Model Pseudo-Labeling
-            \item Primary backbone (large model)
-            \item Supplemented by lightweight auxiliary network
+            \item Transparency-based methods
             \begin{itemize}
-                \item Different structure
-                \item Fewer channels (smaller)
+                \item Improve density perception
+                \item But still lose individual sample visibility
             \end{itemize}
-            \item Different representation of data complements primary backbone
+            \item Down-sampling
+            \begin{itemize}
+                \item Removes data → not acceptable for analysis
+            \end{itemize}
+            \item Local spatial distortions
+            \begin{itemize}
+                \item Risk of collisions
+                \item Often non-monotonic mappings
+            \end{itemize}
+            \item Need a \textbf{global}, \textbf{smooth}, \textbf{monotonic}, \textbf{collision-free} method
+        \end{itemize}
+    \end{frame}
+    %----------------------------------------------------------------------------------------
+%	SECTION 3: BACKGROUND
+%----------------------------------------------------------------------------------------
+
+    \section{Background:\\Density Fields \& Integral Images}
+
+    \begin{frame}{Density Estimation}
+        \begin{itemize}
+            \item Given samples $z_i = (x_i, y_i)$
+            \item Build smoothed density:
+            \[
+                d_r(x,y) = \sum_{p=1}^n \varphi_r(x-x_p, y-y_p)
+            \]
+            \item Typically Gaussian kernel
+            \item Add global constant $d_0$ for stability:
+            \[
+                d(i,j) = d_r(i,j) + d_0
+            \]
+            \item Ensures no empty regions → avoids singular mappings
         \end{itemize}
     \end{frame}
 
-    \begin{frame}{Structure Visualization}
-        \includegraphics[scale=.17]{rsc/structure}
-    \end{frame}
-
-    \begin{frame}{Performance Perspectives}
+    \begin{frame}{Integral Images (InIms) I}
         \begin{itemize}
-            \item 1\% labeled data + 400 Labels
-            \item Kinetics-400 dataset
-        \end{itemize}
-        \includegraphics[scale=.205]{rsc/performance_comparison}
-    \end{frame}
-
-
-    \section{Give me the math!}
-
-    \begin{frame}{Definitions}
-        \begin{itemize}
-            \item Labeled data set of size $N_l$\\
-            $\mathcal{V} = \{(v_1,y_1), \dots, (v_{N_l}, y_{N_l})\}$
-            \item Unlabeled data set of size $N_u$\\
-            $\mathcal{U} = \{u_1, \dots, u_{N_u}\}$
-            \item in general $\lvert\mathcal{U}\rvert \gg \lvert\mathcal{V}\rvert$\\
+            \item Integral images compute cumulative sums over regions
+            \item Four standard tables:
+            \[
+                \alpha,\beta,\gamma,\delta
+            \]
+            \item Four tilted (45°) tables:
+            \[
+                \alpha_t, \beta_t, \gamma_t, \delta_t
+            \]
+            \item Each encodes global density distribution
+            \item Key advantage:
+            \begin{itemize}
+                \item Displacements depend on \textbf{global density}, not local neighborhood
+                \item Avoids collisions
+            \end{itemize}
         \end{itemize}
     \end{frame}
 
-    \begin{frame}[allowframebreaks]{How existing method \textit{FixMatch} works}
+    \begin{frame}{Integral Images (InIms) II}
+        \centering
+        \includegraphics[scale=0.3]{rsc/2408.06513v1_page_6_5}\\
+        \footnotesize\text{Source: \cite{Rave_2025}}
+    \end{frame}
+
+    \begin{frame}{Integral Images (InIms) III}
+        \centering
+        \includegraphics[scale=0.3]{rsc/2408.06513v1_page_6_6}\\
+        \footnotesize\text{Source: \cite{Rave_2025}}
+    \end{frame}
+
+    \begin{frame}{Integral Images (InIms) IV}
+        \centering
+        \includegraphics[scale=0.3]{rsc/2408.06513v1_page_6_7}\\
+        \footnotesize\text{Source: \cite{Rave_2025}}
+    \end{frame}
+
+    %----------------------------------------------------------------------------------------
+%	SECTION 4: METHOD
+%----------------------------------------------------------------------------------------
+
+    \section{Density-Equalizing Mapping}
+
+    \begin{frame}{Goal of the Mapping}
         \begin{itemize}
-            \item $B_u \coloneqq \text{Batchsize}$
-            \item $\tau \coloneqq \text{Confidence Threshold (Hyperparameter)}$
-            \item $F(\mathcal{T}_{\text{strong}}(u_i)) \coloneqq \text{Class distribution}$
-            \item $p_i \coloneqq F(\mathcal{T}_{\text{weak}}(u_i))$
-            \item $\hat{y}_i \coloneqq \arg \max(p_i) \coloneqq \text{Pseudo Label}$
-            \item $\mathcal{H} \coloneqq \text{Cross-entropy loss}$
-            \item $\mathcal{L}_u \coloneqq \text{Loss on the unlabeled data}$
-            \item $F \coloneqq \text{Model}$
-            \item $\mathbbm{1} \coloneqq \text{Indicator Function}$
+            \item We want to transform the scatterplot domain so that:
+            \begin{itemize}
+                \item dense regions expand
+                \item sparse regions contract
+                \item overall density becomes approximately uniform
+            \end{itemize}
+            \item The deformation must be:
+            \begin{itemize}
+                \item smooth
+                \item globally consistent
+                \item monotonic (no point order swaps)
+                \item free of collisions
+            \end{itemize}
+            \item To achieve this, we compute a \textbf{density–driven displacement field}.
+        \end{itemize}
+    \end{frame}
+
+    \begin{frame}{Corrected Mapping: Key Idea}
+        \begin{itemize}
+            \item Let $t(x,y; d)$ be the deformation computed from the
+            \textbf{actual density field} $d(x,y)$.
+            \item This deformation is built from cumulative sums of density
+            through the integral images.
+            \item Problem: even for \textbf{constant density}, $t(x,y; d_0)$
+            is \emph{not} zero (due to construction of the integral tables).
+            \item Therefore:\\
+                We subtract the deformation caused by constant density.
         \end{itemize}
         \begin{align*}
-            \mathcal{L}_u = \frac{1}{B_u} \sum_{i=1}^{B_u} \mathbbm{1}(\max(p_i) \geq \tau) \mathcal{H}(\hat{y}_i,F(\mathcal{T}_{\text{strong}}(u_i)))
+            T(x,y) = (x,y) \;+\; t(x,y; d) \;-\; t(x,y; d_0) \;
         \end{align*}
 
-        \framebreak
-
         \begin{itemize}
-            \item $\mathbbm{1}(\max(p_i) \geq \tau)$
-            \begin{itemize}
-                \item 'confidence-based masking'
-                \item retain label only if largest probability is above threshold
-                \item keep only 'high confidence' labels
-            \end{itemize}
-            \item $\mathcal{H}(\hat{y}_i,F(\mathcal{T}_{\text{strong}}(u_i)))$
-            \begin{itemize}
-                \item 'consistency regularization'
-                \item cross-entropy loss of strong augmented and weak augmented data
-            \end{itemize}
-        \end{itemize}
-
-    \end{frame}
-
-    \begin{frame}[allowframebreaks]{CMPL (Cross-Model Pseudo-Labeling)}
-        \begin{itemize}
-            \item $F(\cdot) \coloneqq \text{Primary backbone}$
-            \item $A(\cdot) \coloneqq \text{Auxiliary network}$
-            \item Learning on labeled data
-            \begin{align*}
-                \mathcal{L}_s^F &= \frac{1}{B_l} \sum_{i=1}^{B_l} \mathcal{H}(y_i,F(\mathcal{T}^F_{\text{standard}}(v_i)))\\
-                \mathcal{L}_s^A &= \frac{1}{B_l} \sum_{i=1}^{B_l} \mathcal{H}(y_i,A(\mathcal{T}^F_{\text{standard}}(v_i)))
-            \end{align*}
-            \item $\mathcal{T}^F_{\text{standard}}(v_i) \coloneqq \text{standard augmentations for action recognition}$
-        \end{itemize}
-
-        \framebreak
-
-        \begin{itemize}
-            \item Learning on unlabeled data
-            \begin{align*}
-                \mathcal{L}_u^F &= \frac{1}{B_u} \sum_{i=1}^{B_u} \mathbbm{1}(\max(p_i^A) \geq \tau) \mathcal{H}(\hat{y}_i^A,F(\mathcal{T}_{\text{strong}}(u_i)))\\
-                \mathcal{L}_u^A &= \frac{1}{B_u} \sum_{i=1}^{B_u} \mathbbm{1}(\max(p_i^F) \geq \tau) \mathcal{H}(\hat{y}_i^F,A(\mathcal{T}_{\text{strong}}(u_i)))\\
-            \end{align*}
-            \item Complete training objective
-            \begin{align*}
-                \mathcal{L} = (\mathcal{L}_s^F + \mathcal{L}_s^A) + \lambda(\mathcal{L}_u^F + \mathcal{L}_u^A)
-            \end{align*}
-            \item $\lambda \coloneqq \text{Balancing coefficient for unsupervised loss}$
+            \item $T(x,y)$ is the \textbf{corrected mapping}.
+            \item For uniform density: $t(x,y; d) = t(x,y; d_0)$  $\rightarrow$ identity mapping.
         \end{itemize}
     \end{frame}
 
+%    \begin{frame}{Why the Corrected Mapping Works}
+%        \begin{itemize}
+%            \item \textbf{Identity on uniform density}
+%            \begin{itemize}
+%                \item Without correction: the old mapping distorted even uniform fields.
+%                \item With correction: uniform density $\rightarrow$ no deformation.
+%            \end{itemize}
+%            \item \textbf{Monotonicity}
+%            \begin{itemize}
+%                \item The corrected mapping guarantees no coordinate inversions.
+%                \item Order of points is preserved along both axes.
+%            \end{itemize}
+%            \item \textbf{Smoothness}
+%            \begin{itemize}
+%                \item The mapping is built from integral images (global cumulative fields),
+%                \item yielding slow, continuous changes.
+%            \end{itemize}
+%            \item \textbf{Stability in iteration}
+%            \begin{itemize}
+%                \item As the density becomes more equalized, $t(x,y;d)$ approaches $t(x,y;d_0)$.
+%                \item Mapping naturally converges toward identity.
+%            \end{itemize}
+%            \item \textbf{No collisions}
+%            \begin{itemize}
+%                \item Global, monotonic deformation prevents points from crossing paths.
+%            \end{itemize}
+%        \end{itemize}
+%    \end{frame}
 
-    \section{Implementation}
 
-    \begin{frame}{Networks}
-        \begin{itemize}
-            \item Auxiliary Network
+    \begin{frame}{Iterative Algorithm Overview}
+        \begin{enumerate}
+            \item Rasterize and smooth density
+            \item Compute integral images
+            \item Compute corrected deformation $t(x,y)$
+            \item Apply bi-linear interpolation to sample positions
+            \item Iterate until:
             \begin{itemize}
-                \item sub-network of primary model
-                \item 3D-ResNet18
-                \item \textbf{3D-ResNet50x1/4}
+                \item Time budget reached
+                \item Uniformity threshold reached
             \end{itemize}
-            \item Backbone network
+        \end{enumerate}
+    \end{frame}
+
+    \begin{frame}
+        \centering
+        \begin{figure}
+            \centering
+            \begin{minipage}{0.4\textwidth}
+                \centering
+                \includegraphics[width=\textwidth]{rsc/2408.06513v1_page_7_1}
+
+                \vspace{4pt}
+                \footnotesize MNIST Dataset (UMAP)~\cite{Rave_2025}
+            \end{minipage}
+            \begin{minipage}{0.15\textwidth}
+                \centering
+                $\Longrightarrow$
+            \end{minipage}
+            \begin{minipage}{0.4\textwidth}
+                \centering
+                \includegraphics[width=\textwidth]{rsc/2408.06513v1_page_7_2}
+
+                \vspace{4pt}
+                \footnotesize Visual encoding of the density-equalizing transform (32 Iterations)~\cite{Rave_2025}
+            \end{minipage}
+            \label{fig:figure}
+        \end{figure}
+    \end{frame}
+
+%----------------------------------------------------------------------------------------
+%	SECTION 6: VISUAL ENCODING
+%----------------------------------------------------------------------------------------
+
+    \section{Visual Encoding of Deformation}
+
+    \begin{frame}{Problem After Deformation}
+        \begin{itemize}
+            \item After equalization:
             \begin{itemize}
-                \item larger version of aux-net
-                \item \textbf{3D-ResNet50}
+                \item Local densities lost
+                \item Cluster shapes distorted
+                \item Distances no longer meaningful
+            \end{itemize}
+            \item Need additional encodings to preserve structure
+        \end{itemize}
+    \end{frame}
+
+    \begin{frame}{Three Proposed Encodings I}
+        \begin{itemize}
+            \item \textbf{Deformed grid lines}
+            \begin{itemize}
+                \item Show local expansion / contraction
+            \end{itemize}
+            \item \textbf{Background density texture}
+            \begin{itemize}
+                \item Shows cluster cores after deformation
+            \end{itemize}
+            \item \textbf{Contour lines}
+            \begin{itemize}
+                \item Reveal subcluster structure
             \end{itemize}
         \end{itemize}
     \end{frame}
 
-    \begin{frame}{Dataset}
-        \begin{itemize}
-            \item Kinetics-400
-            \begin{itemize}
-                \item 400 categories
-                \item 240k/20k training/validation samples
-            \end{itemize}
-            \item UCF-101
-            \begin{itemize}
-                \item 101 classes
-                \item 9.5k/4k training/validation samples
-            \end{itemize}
-            \item $\approx$10sec every video
-            \item 1\% or 10\% labeled subsets balanced sampled from distribution
-        \end{itemize}
+    \begin{frame}{Three Proposed Encodings II}
+        \centering
+        \begin{figure}
+            \centering
+            \begin{minipage}{0.3\textwidth}
+                \centering
+                \includegraphics[width=\textwidth]{rsc/2408.06513v1_page_7_2}
+
+                \vspace{4pt}
+                \footnotesize Deformed grid lines~\cite{Rave_2025}
+            \end{minipage}
+            \begin{minipage}{0.3\textwidth}
+                \centering
+                \includegraphics[width=\textwidth]{rsc/2408.06513v1_page_7_3}
+
+                \vspace{4pt}
+                \footnotesize Background density texture~\cite{Rave_2025}
+            \end{minipage}
+            \begin{minipage}{0.3\textwidth}
+                \centering
+                \includegraphics[width=\textwidth]{rsc/2408.06513v1_page_7_4}
+
+                \vspace{4pt}
+                \footnotesize Contour lines~\cite{Rave_2025}
+            \end{minipage}
+            \label{fig:figure2}
+        \end{figure}
     \end{frame}
 
+    %----------------------------------------------------------------------------------------
+%	SECTION 5: IMPLEMENTATION
+%----------------------------------------------------------------------------------------
 
-    \begin{frame}{Performance Results}
-        \includegraphics[scale=.65]{rsc/results}
+
+    \begin{frame}{Example I}
+        \centering
+        \includegraphics[scale=0.1]{rsc/2408.06513v1_page_8_1}\\
+        \footnotesize\text{Source: \cite{Rave_2025}}
     \end{frame}
 
+    \begin{frame}{Example II}
+        \centering
+        \includegraphics[scale=0.1]{rsc/2408.06513v1_page_8_2}\\
+        \footnotesize\text{Source: \cite{Rave_2025}}
+    \end{frame}
+
+    \begin{frame}{Example III}
+        \centering
+        \includegraphics[scale=0.1]{rsc/2408.06513v1_page_8_3}\\
+        \footnotesize\text{Source: \cite{Rave_2025}}
+    \end{frame}
+
+    \begin{frame}{Example IV}
+        \centering
+        \includegraphics[scale=0.1]{rsc/2408.06513v1_page_8_4}\\
+        \footnotesize\text{Source: \cite{Rave_2025}}
+    \end{frame}
+
+    \begin{frame}{Example V}
+        \centering
+        \includegraphics[scale=0.1]{rsc/2408.06513v1_page_8_5}\\
+        \footnotesize\text{Source: \cite{Rave_2025}}
+    \end{frame}
+
+    \begin{frame}{Example VI}
+        \centering
+        \includegraphics[scale=0.1]{rsc/2408.06513v1_page_8_6}\\
+        \footnotesize\text{Source: \cite{Rave_2025}}
+    \end{frame}
 
     % ---  THE END
 
@@ -342,10 +414,58 @@
 
     \appendix
 
+    \section{Backup Slides}\label{sec:backup}
+
+    \begin{frame}{Efficient GPU Computation}
+        \begin{itemize}
+            \item All major steps implemented on GPU:
+            \begin{itemize}
+                \item Density accumulation $\rightarrow$ vertex + fragment shader
+                \item Gaussian smoothing $\rightarrow$ 2 compute-shader passes
+                \item Integral image computation $\rightarrow$ fragment shader
+            \end{itemize}
+            \item Achieves interactive rates for millions of samples
+        \end{itemize}
+    \end{frame}
+
+    \begin{frame}{Performance}
+        \begin{itemize}
+            \item Runs at interactive frame rates:
+            \begin{itemize}
+                \item e.g. 4M samples in $\approx 3$ ms per iteration
+            \end{itemize}
+            %\item Standard deviation of samples/bin decreases monotonically
+            %\item Overplotting fraction also decreases monotonically
+        \end{itemize}
+        \centering
+        \includegraphics[scale=0.4]{rsc/img}\\
+        Source:~\cite{Rave_2025}
+    \end{frame}
+
+    \section{Math: Domain Transformation}
+    \begin{frame}{Domain Transformation (Molchanov \& Linsen)}
+        \begin{itemize}
+            \item Integral Images $\rightarrow$ Transformation mapping
+            \item Definition:
+            \[
+                t(x,y; d) = \frac{
+                    \alpha q_1 + \beta q_2 + \gamma q_3 + \delta q_4
+                    + \alpha_t (x,1) + \beta_t (1,y) + \gamma_t (x,0) + \delta_t (0,y)
+                }{2C}
+            \]
+            \item Problems:
+            \begin{itemize}
+                \item Not identity for uniform density
+                \item Iteration unstable
+                \item Does not converge to equalized distribution
+            \end{itemize}
+        \end{itemize}
+    \end{frame}
+
+
     \begin{frame}{Sources}
         \nocite{*} % Display all references regardless of if they were cited
         \bibliography{sources}
         \bibliographystyle{plain}
     \end{frame}
-
 \end{document}

presentation/sources.bib

@@ -1,16 +1,20 @@
-@InProceedings{Xu_2022_CVPR,
-    author    = {Xu, Yinghao and Wei, Fangyun and Sun, Xiao and Yang, Ceyuan and Shen, Yujun and Dai, Bo and Zhou, Bolei and Lin, Stephen},
-    title     = {Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition},
-    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
-    month     = {June},
-    year      = {2022},
-    pages     = {2959-2968}
-}
+@article{Rave_2025,
+    title={De-Cluttering Scatterplots With Integral Images},
+    volume={31},
+    ISSN={2160-9306},
+    url={http://dx.doi.org/10.1109/TVCG.2024.3381453},
+    DOI={10.1109/tvcg.2024.3381453},
+    number={4},
+    journal={IEEE Transactions on Visualization and Computer Graphics},
+    publisher={Institute of Electrical and Electronics Engineers (IEEE)},
+    author={Rave, Hennes and Molchanov, Vladimir and Linsen, Lars},
+    year={2025},
+    month=apr, pages={2114–2126} }
 
-@online{knuthwebsite,
-    author = "Kihyuk Sohn, David Berthelot, Chun-Liang Li",
-    title = "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence",
-    url  = "https://arxiv.org/abs/2001.07685",
-    addendum = "(accessed: 20.03.2023)",
-    keywords = "FixMatch, semi-supervised"
+@online{statisticsglobe_overplotting_r,
+    author       = {Statistics Globe},
+    title        = {Avoid Overplotting in R (4 Examples) | Point Size, Opacity \& Color},
+    year         = {2025},
+    url          = {https://statisticsglobe.com/avoid-overplotting-r},
+    note         = {Accessed: 2025-11-23}
 }