PUMA publications for /user/tanjamunz/exc2075https://puma.ub.uni-stuttgart.de/user/tanjamunz/exc2075PUMA RSS feed for /user/tanjamunz/exc20752024-03-29T10:17:11+01:00Visual Analysis of Scene-Graph-Based Visual Question Answeringhttps://puma.ub.uni-stuttgart.de/bibtex/245f80081761d7a4507e7f2b210b79768/tanjamunztanjamunz2023-10-23T19:14:40+02:00exc2075 myown pn6 vis(us) visus visus:kuenzesn visus:munzta visus:weiskopf <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Noel Schäfer" itemprop="url" href="/person/1e858fa98d08c5e0e3d2b4baefa5bd60e/author/0"><span itemprop="name">N. Schäfer</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Sebastian Künzel" itemprop="url" href="/person/1e858fa98d08c5e0e3d2b4baefa5bd60e/author/1"><span itemprop="name">S. Künzel</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Tanja Munz-Körner" itemprop="url" href="/person/1e858fa98d08c5e0e3d2b4baefa5bd60e/author/2"><span itemprop="name">T. Munz-Körner</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Pascal Tilli" itemprop="url" href="/person/1e858fa98d08c5e0e3d2b4baefa5bd60e/author/3"><span itemprop="name">P. Tilli</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Sandeep Vidyapu" itemprop="url" href="/person/1e858fa98d08c5e0e3d2b4baefa5bd60e/author/4"><span itemprop="name">S. Vidyapu</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Ngoc Thang Vu" itemprop="url" href="/person/1e858fa98d08c5e0e3d2b4baefa5bd60e/author/5"><span itemprop="name">N. Thang Vu</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Daniel Weiskopf" itemprop="url" href="/person/1e858fa98d08c5e0e3d2b4baefa5bd60e/author/6"><span itemprop="name">D. Weiskopf</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/Book" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="name">Proceedings of the 16th International Symposium on Visual Information Communication and Interaction</span>, </em></span><em>page <span itemprop="pagination">1–8</span>. </em><em>New York, NY, USA, </em><em><span itemprop="publisher">Association for Computing Machinery</span>, </em>(<em><span>Oct 20, 2023<meta content="Oct 20, 2023" itemprop="datePublished"/></span></em>)</span>Mon Oct 23 19:14:40 CEST 2023New York, NY, USAProceedings of the 16th International Symposium on Visual Information Communication and Interaction101–8VINCI '23Visual Analysis of Scene-Graph-Based Visual Question Answering2023exc2075 myown pn6 vis(us) visus visus:kuenzesn visus:munzta visus:weiskopf 20Scene-graph-based Visual Question Answering (VQA) has emerged as a burgeoning field in Deep Learning research, with a growing demand for robust and interpretable VQA systems. In this paper, we present a novel visual analysis approach that addresses two critical objectives in VQA: identifying and correcting prediction issues and providing insights into model decision-making processes through visualizing internal information. Our approach builds on the GraphVQA framework, which uses graph neural networks to process scene graphs representing images and which was trained on the widely-used GQA dataset. Our analysis tool aims at users familiar with the basics of graph-based VQA. By leveraging query-based scene analysis and visualization of crucial internal states, we are able to detect and pinpoint reasons for inaccurate predictions, facilitating model refinement and dataset curation. Identifying expressive internal states is a challenge. Through rigorous computer-based evaluations and presentation of a use case, we demonstrate the effectiveness of our analysis tool and model state visualization.NMTVis - Trained Models for our Visual Analytics Systemhttps://puma.ub.uni-stuttgart.de/bibtex/26cca2701ae2212a10884637e160eb7ac/tanjamunztanjamunz2023-10-04T17:35:47+02:00EXC2075 PN6 myown vis(us) visus visus:munzta visus:weiskopf <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Tanja Munz" itemprop="url" href="/person/18ffcd5ba63c57cbd84dc4174f6bb2021/author/0"><span itemprop="name">T. Munz</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Dirk Väth" itemprop="url" href="/person/18ffcd5ba63c57cbd84dc4174f6bb2021/author/1"><span itemprop="name">D. Väth</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Paul Kuznecov" itemprop="url" href="/person/18ffcd5ba63c57cbd84dc4174f6bb2021/author/2"><span itemprop="name">P. Kuznecov</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Ngoc Thang Vu" itemprop="url" href="/person/18ffcd5ba63c57cbd84dc4174f6bb2021/author/3"><span itemprop="name">N. Vu</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Daniel Weiskopf" itemprop="url" href="/person/18ffcd5ba63c57cbd84dc4174f6bb2021/author/4"><span itemprop="name">D. Weiskopf</span></a></span></span>. </span><span class="additional-entrytype-information">(<em><span>2021<meta content="2021" itemprop="datePublished"/></span></em>)</span>Wed Oct 04 17:35:47 CEST 2023NMTVis - Trained Models for our Visual Analytics System2021EXC2075 PN6 myown vis(us) visus visus:munzta visus:weiskopf NMTVis - Extended Neural Machine Translation Visualization Systemhttps://puma.ub.uni-stuttgart.de/bibtex/297c16a709b140b9f490d8a254107e02f/tanjamunztanjamunz2023-10-04T17:33:52+02:00EXC2075 PN6 myown vis(us) visus visus:munzta visus:weiskopf <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Tanja Munz" itemprop="url" href="/person/12ca9d88c72f0d61dcd18e560d7385e62/author/0"><span itemprop="name">T. Munz</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Dirk Väth" itemprop="url" href="/person/12ca9d88c72f0d61dcd18e560d7385e62/author/1"><span itemprop="name">D. Väth</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Paul Kuznecov" itemprop="url" href="/person/12ca9d88c72f0d61dcd18e560d7385e62/author/2"><span itemprop="name">P. Kuznecov</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Ngoc Thang Vu" itemprop="url" href="/person/12ca9d88c72f0d61dcd18e560d7385e62/author/3"><span itemprop="name">N. Vu</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Daniel Weiskopf" itemprop="url" href="/person/12ca9d88c72f0d61dcd18e560d7385e62/author/4"><span itemprop="name">D. Weiskopf</span></a></span></span>. </span><span class="additional-entrytype-information"><em>Software, </em>(<em><span>2022<meta content="2022" itemprop="datePublished"/></span></em>)<em>Related to: T. Munz, D. Väth, P. Kuznecov, N. T. Vu, and D. Weiskopf. "Visualization-based improvement of neural machine translation", Computers & Graphics, 2021. doi: 10.1016/j.cag.2021.12.003.</em></span>Wed Oct 04 17:33:52 CEST 2023SoftwareRelated to: T. Munz, D. Väth, P. Kuznecov, N. T. Vu, and D. Weiskopf. "Visualization-based improvement of neural machine translation", Computers & Graphics, 2021. doi: 10.1016/j.cag.2021.12.003NMTVis - Extended Neural Machine Translation Visualization System2022EXC2075 PN6 myown vis(us) visus visus:munzta visus:weiskopf NMTVis is a web-based visual analytics system to analyze, understand, and correct translations generated with neural machine translation. First, a document can be translated using a neural machine translation model (we support an LSTM-based and the Transformer architecture). Afterward, users can find mistranslated sentences, explore and correct these sentences and retrain the model to generate a better translation for the whole document. Our approach targets the correction of domain-specific documents. This extended version of our visual analytics system provides additional visualization and interaction techniques as well as scripts for computer-based evaluation of our approach. You can find important information about our system here and an introduction to our system here.Visual Analytics System for Hidden States in Recurrent Neural Networkshttps://puma.ub.uni-stuttgart.de/bibtex/2cc11065a707047b43139817722cc519f/tanjamunztanjamunz2023-10-04T17:32:48+02:00EXC2075 PN6 myown vis(us) visus visus:munzta visus:weiskopf <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Tanja Munz" itemprop="url" href="/person/1700a9373ea538d40a5f9b6e934af1f5f/author/0"><span itemprop="name">T. Munz</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Rafael Garcia" itemprop="url" href="/person/1700a9373ea538d40a5f9b6e934af1f5f/author/1"><span itemprop="name">R. Garcia</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Daniel Weiskopf" itemprop="url" href="/person/1700a9373ea538d40a5f9b6e934af1f5f/author/2"><span itemprop="name">D. Weiskopf</span></a></span></span>. </span><span class="additional-entrytype-information">(<em><span>2021<meta content="2021" itemprop="datePublished"/></span></em>)</span>Wed Oct 04 17:32:48 CEST 2023Visual Analytics System for Hidden States in Recurrent Neural Networks2021EXC2075 PN6 myown vis(us) visus visus:munzta visus:weiskopf Visual Analysis System for Scene-Graph-Based Visual Question Answeringhttps://puma.ub.uni-stuttgart.de/bibtex/27a0b2decd921d15add6cf42e733fe3e4/tanjamunztanjamunz2023-10-04T17:31:48+02:00EXC2075 PN6 myown vis(us) visus visus:munzta visus:weiskopf <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Noel Schäfer" itemprop="url" href="/person/11d114b870579095267e6815b0c43d9ff/author/0"><span itemprop="name">N. Schäfer</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Pascal Tilli" itemprop="url" href="/person/11d114b870579095267e6815b0c43d9ff/author/1"><span itemprop="name">P. Tilli</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Tanja Munz-Körner" itemprop="url" href="/person/11d114b870579095267e6815b0c43d9ff/author/2"><span itemprop="name">T. Munz-Körner</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Sebastian Künzel" itemprop="url" href="/person/11d114b870579095267e6815b0c43d9ff/author/3"><span itemprop="name">S. Künzel</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Sandeep Vidyapu" itemprop="url" href="/person/11d114b870579095267e6815b0c43d9ff/author/4"><span itemprop="name">S. Vidyapu</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Ngoc Thang Vu" itemprop="url" href="/person/11d114b870579095267e6815b0c43d9ff/author/5"><span itemprop="name">N. Vu</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Daniel Weiskopf" itemprop="url" href="/person/11d114b870579095267e6815b0c43d9ff/author/6"><span itemprop="name">D. Weiskopf</span></a></span></span>. </span><span class="additional-entrytype-information"><em>Software, </em>(<em><span>2023<meta content="2023" itemprop="datePublished"/></span></em>)<em>Related to: N. Schäfer, S. Künzel, T. Munz, P. Tilli, N. T. Vu, and D. Weiskopf. Visual Analysis of Scene-Graph-Based Visual Question Answering. Proceedings of the 16th International Symposium on Visual Information Communication and Interaction (VINCI 2023). 2023.</em></span>Wed Oct 04 17:31:48 CEST 2023SoftwareRelated to: N. Schäfer, S. Künzel, T. Munz, P. Tilli, N. T. Vu, and D. Weiskopf. Visual Analysis of Scene-Graph-Based Visual Question Answering. Proceedings of the 16th International Symposium on Visual Information Communication and Interaction (VINCI 2023). 2023Visual Analysis System for Scene-Graph-Based Visual Question Answering2023EXC2075 PN6 myown vis(us) visus visus:munzta visus:weiskopf Source code of our visual analysis system to explore scene-graph-based visual question answering.This approach is built on top of the state-of-the-art GraphVQA frameworkwhich was trained on the GQA dataset. Instructions on how to use our system can be found in the README. Supplemental Material for "Visual-Explainable AI: The Use Case of Language Models"https://puma.ub.uni-stuttgart.de/bibtex/2aacfdf6c2c737f334037a550bec8295b/tanjamunztanjamunz2023-10-04T17:30:48+02:00EXC2075 PN6 myown vis(us) visus visus:munzta visus:weiskopf <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Tanja Munz-Körner" itemprop="url" href="/person/17223054dd9a282d46d3399e390b8f8cf/author/0"><span itemprop="name">T. Munz-Körner</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Sebastian Künzel" itemprop="url" href="/person/17223054dd9a282d46d3399e390b8f8cf/author/1"><span itemprop="name">S. Künzel</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Daniel Weiskopf" itemprop="url" href="/person/17223054dd9a282d46d3399e390b8f8cf/author/2"><span itemprop="name">D. Weiskopf</span></a></span></span>. </span><span class="additional-entrytype-information"><em>Dataset, </em>(<em><span>2023<meta content="2023" itemprop="datePublished"/></span></em>)<em>Related to: T. Munz-Körner, S. Künzel, and D. Weiskopf. "Visual-Explainable AI: The Use Case of Language Models". International Conference on Data-Integrated Simulation Science (SimTech2023). 2023.</em></span>Wed Oct 04 17:30:48 CEST 2023DatasetRelated to: T. Munz-Körner, S. Künzel, and D. Weiskopf. "Visual-Explainable AI: The Use Case of Language Models". International Conference on Data-Integrated Simulation Science (SimTech2023). 2023Supplemental Material for "Visual-Explainable AI: The Use Case of Language Models"2023EXC2075 PN6 myown vis(us) visus visus:munzta visus:weiskopf Supplemental material for the poster "Visual-Explainable AI: The Use Case of Language Models" published at the International Conference on Data-Integrated Simulation Science 2023.Collection of videos and images showing our interactive visualization systems for exploring language models: - Text classification (https://github.com/MunzT/hiddenStatesVis) - Neural machine translation (https://github.com/MunzT/NMTVis) Model Parameters and Evaluation Data for our Visual Analysis System for Scene-Graph-Based Visual Question Answeringhttps://puma.ub.uni-stuttgart.de/bibtex/26774c40f675c4a80e0af50602d8ae27f/tanjamunztanjamunz2023-10-04T17:29:33+02:00EXC2075 PN6 myown vis(us) visus visus:munzta visus:weiskopf <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Noel Schäfer" itemprop="url" href="/person/1b0a066b246f44748697d674a49927b13/author/0"><span itemprop="name">N. Schäfer</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Pascal Tilli" itemprop="url" href="/person/1b0a066b246f44748697d674a49927b13/author/1"><span itemprop="name">P. Tilli</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Tanja Munz-Körner" itemprop="url" href="/person/1b0a066b246f44748697d674a49927b13/author/2"><span itemprop="name">T. Munz-Körner</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Sebastian Künzel" itemprop="url" href="/person/1b0a066b246f44748697d674a49927b13/author/3"><span itemprop="name">S. Künzel</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Sandeep Vidyapu" itemprop="url" href="/person/1b0a066b246f44748697d674a49927b13/author/4"><span itemprop="name">S. Vidyapu</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Ngoc Thang Vu" itemprop="url" href="/person/1b0a066b246f44748697d674a49927b13/author/5"><span itemprop="name">N. Vu</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Daniel Weiskopf" itemprop="url" href="/person/1b0a066b246f44748697d674a49927b13/author/6"><span itemprop="name">D. Weiskopf</span></a></span></span>. </span><span class="additional-entrytype-information"><em>Dataset, </em>(<em><span>2023<meta content="2023" itemprop="datePublished"/></span></em>)<em>Related to: N. Schäfer, S. Künzel, T. Munz, P. Tilli, N. T. Vu, and D. Weiskopf. Visual Analysis of Scene-Graph-Based Visual Question Answering. Proceedings of the 16th International Symposium on Visual Information Communication and Interaction (VINCI 2023). 2023.</em></span>Wed Oct 04 17:29:33 CEST 2023DatasetRelated to: N. Schäfer, S. Künzel, T. Munz, P. Tilli, N. T. Vu, and D. Weiskopf. Visual Analysis of Scene-Graph-Based Visual Question Answering. Proceedings of the 16th International Symposium on Visual Information Communication and Interaction (VINCI 2023). 2023Model Parameters and Evaluation Data for our Visual Analysis System for Scene-Graph-Based Visual Question Answering2023EXC2075 PN6 myown vis(us) visus visus:munzta visus:weiskopf Pretrained model parameters and pregenerated evaluation data for our visual analysis system for scene-graph-based visual question answering (https://doi.org/10.18419/darus-3589). Supplemental Material for Comparative Visual Gaze Analysis for Virtual Board Gameshttps://puma.ub.uni-stuttgart.de/bibtex/2822917f36a27e63e69f8e6520182b9f8/tanjamunztanjamunz2023-10-04T16:25:36+02:00EXC2075 PN6 myown vis(us) visus visus:blaschta visus:munzta visus:weiskopf <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Tanja Munz" itemprop="url" href="/person/1a5aa33c56e2811b691cc04356694db9e/author/0"><span itemprop="name">T. Munz</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Noel Schäfer" itemprop="url" href="/person/1a5aa33c56e2811b691cc04356694db9e/author/1"><span itemprop="name">N. Schäfer</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Tanja Blascheck" itemprop="url" href="/person/1a5aa33c56e2811b691cc04356694db9e/author/2"><span itemprop="name">T. Blascheck</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Kuno Kurzhals" itemprop="url" href="/person/1a5aa33c56e2811b691cc04356694db9e/author/3"><span itemprop="name">K. Kurzhals</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Eugene Zhang" itemprop="url" href="/person/1a5aa33c56e2811b691cc04356694db9e/author/4"><span itemprop="name">E. Zhang</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Daniel Weiskopf" itemprop="url" href="/person/1a5aa33c56e2811b691cc04356694db9e/author/5"><span itemprop="name">D. Weiskopf</span></a></span></span>. </span><span class="additional-entrytype-information">(<em><span>2020<meta content="2020" itemprop="datePublished"/></span></em>)</span>Wed Oct 04 16:25:36 CEST 2023Supplemental Material for Comparative Visual Gaze Analysis for Virtual Board Games2020EXC2075 PN6 myown vis(us) visus visus:blaschta visus:munzta visus:weiskopf Visual analytics tool for the interpretation of hidden states in recurrent neural networkshttps://puma.ub.uni-stuttgart.de/bibtex/2f65dee96df3a935490e6f037f27adfc3/tanjamunztanjamunz2021-10-04T10:08:53+02:00exc2075 myown peerreviewed pn6 vis(us) visus visus:munzta visus:weiskopf <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Rafael Garcia" itemprop="url" href="/person/18d4415a4570cdb47380efc922ec257d2/author/0"><span itemprop="name">R. Garcia</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Tanja Munz" itemprop="url" href="/person/18d4415a4570cdb47380efc922ec257d2/author/1"><span itemprop="name">T. Munz</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Daniel Weiskopf" itemprop="url" href="/person/18d4415a4570cdb47380efc922ec257d2/author/2"><span itemprop="name">D. Weiskopf</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/PublicationIssue" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="journal">Visual Computing for Industry, Biomedicine, and Art</span>, </em> </span>(<em><span>2021<meta content="2021" itemprop="datePublished"/></span></em>)</span>Mon Oct 04 10:08:53 CEST 2021Visual Computing for Industry, Biomedicine, and Art24Visual analytics tool for the interpretation of hidden states in recurrent neural networks42021exc2075 myown peerreviewed pn6 vis(us) visus visus:munzta visus:weiskopf In this paper, we introduce a visual analytics approach aimed at helping machine learning experts analyze the hidden states of layers in recurrent neural networks. Our technique allows the user to interactively inspect how hidden states store and process information throughout the feeding of an input sequence into the network. The technique can help answer questions, such as which parts of the input data have a higher impact on the prediction and how the model correlates each hidden state configuration with a certain output. Our visual analytics approach comprises several components: First, our input visualization shows the input sequence and how it relates to the output (using color coding). In addition, hidden states are visualized through a nonlinear projection into a 2-D visualization space using t-distributed stochastic neighbor embedding to understand the shape of the space of the hidden states. Trajectories are also employed to show the details of the evolution of the hidden state configurations. Finally, a time-multi-class heatmap matrix visualizes the evolution of the expected predictions for multi-class classifiers, and a histogram indicates the distances between the hidden states within the original space. The different visualizations are shown simultaneously in multiple views and support brushing-and-linking to facilitate the analysis of the classifications and debugging for misclassified input sequences. To demonstrate the capability of our approach, we discuss two typical use cases for long short-term memory models applied to two widely used natural language processing datasets.Visual-Interactive Neural Machine Translationhttps://puma.ub.uni-stuttgart.de/bibtex/221a30885ad46c4bca0c3e0cf69db0ea5/tanjamunztanjamunz2021-09-22T01:31:37+02:00exc2075 myown peerreviewed pn6 vis(us) visus visus:munzta visus:weiskopf <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Tanja Munz" itemprop="url" href="/person/12e31f60be1fcd371a424481cfb8b1c07/author/0"><span itemprop="name">T. Munz</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Dirk Väth" itemprop="url" href="/person/12e31f60be1fcd371a424481cfb8b1c07/author/1"><span itemprop="name">D. Väth</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Paul Kuznecov" itemprop="url" href="/person/12e31f60be1fcd371a424481cfb8b1c07/author/2"><span itemprop="name">P. Kuznecov</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Thang Vu" itemprop="url" href="/person/12e31f60be1fcd371a424481cfb8b1c07/author/3"><span itemprop="name">T. Vu</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Daniel Weiskopf" itemprop="url" href="/person/12e31f60be1fcd371a424481cfb8b1c07/author/4"><span itemprop="name">D. Weiskopf</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/Book" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="name">Graphics Interface 2021</span>, </em></span>(<em><span>2021<meta content="2021" itemprop="datePublished"/></span></em>)</span>Wed Sep 22 01:31:37 CEST 2021Graphics Interface 2021Visual-Interactive Neural Machine Translation2021exc2075 myown peerreviewed pn6 vis(us) visus visus:munzta visus:weiskopf ClaVis: An Interactive Visual Comparison System for Classifiershttps://puma.ub.uni-stuttgart.de/bibtex/2b94a323bb1481f5b322255b9bf245115/tanjamunztanjamunz2020-12-22T16:01:26+01:00EXC2075 myown peerReviewed pn6 visus:munzta visus:weiskopf <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Frank Heyen" itemprop="url" href="/person/15bcaeedc1ee8e009a637fa403fc78357/author/0"><span itemprop="name">F. Heyen</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Tanja Munz" itemprop="url" href="/person/15bcaeedc1ee8e009a637fa403fc78357/author/1"><span itemprop="name">T. Munz</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Michael Neumann" itemprop="url" href="/person/15bcaeedc1ee8e009a637fa403fc78357/author/2"><span itemprop="name">M. Neumann</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Daniel Ortega" itemprop="url" href="/person/15bcaeedc1ee8e009a637fa403fc78357/author/3"><span itemprop="name">D. Ortega</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Ngoc Thang Vu" itemprop="url" href="/person/15bcaeedc1ee8e009a637fa403fc78357/author/4"><span itemprop="name">N. Vu</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Daniel Weiskopf" itemprop="url" href="/person/15bcaeedc1ee8e009a637fa403fc78357/author/5"><span itemprop="name">D. Weiskopf</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Michael Sedlmair" itemprop="url" href="/person/15bcaeedc1ee8e009a637fa403fc78357/author/6"><span itemprop="name">M. Sedlmair</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/Book" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="name">Proceedings of the International Conference on Advanced Visual Interfaces</span>, </em></span><em>New York, NY, USA, </em><em><span itemprop="publisher">Association for Computing Machinery</span>, </em>(<em><span>2020<meta content="2020" itemprop="datePublished"/></span></em>)</span>Tue Dec 22 16:01:26 CET 2020New York, NY, USAProceedings of the International Conference on Advanced Visual InterfacesAVI '20ClaVis: An Interactive Visual Comparison System for Classifiers2020EXC2075 myown peerReviewed pn6 visus:munzta visus:weiskopf We propose ClaVis, a visual analytics system for comparative analysis of classification models. ClaVis allows users to visually compare the performance and behavior of tens to hundreds of classifiers trained with different hyperparameter configurations. Our approach is plugin-based and classifier-agnostic and allows users to add their own datasets and classifier implementations. It provides multiple visualizations, including a multivariate ranking, a similarity map, a scatterplot that reveals correlations between parameters and scores, and a training history chart. We demonstrate the effectivity of our approach in multiple case studies for training classification models in the domain of natural language processing.Demo of a Visual Gaze Analysis System for Virtual Board Gameshttps://puma.ub.uni-stuttgart.de/bibtex/2da830d9df7f1fbcbde334db07a9a6c7b/tanjamunztanjamunz2020-12-22T15:56:00+01:00exc2075 myown peerreviewed pn6 <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Tanja Munz" itemprop="url" href="/person/1f598ebac63d1ab8f532fbb3a624ee49a/author/0"><span itemprop="name">T. Munz</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Noel Schaefer" itemprop="url" href="/person/1f598ebac63d1ab8f532fbb3a624ee49a/author/1"><span itemprop="name">N. Schaefer</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Tanja Blascheck" itemprop="url" href="/person/1f598ebac63d1ab8f532fbb3a624ee49a/author/2"><span itemprop="name">T. Blascheck</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Kuno Kurzhals" itemprop="url" href="/person/1f598ebac63d1ab8f532fbb3a624ee49a/author/3"><span itemprop="name">K. Kurzhals</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Eugene Zhang" itemprop="url" href="/person/1f598ebac63d1ab8f532fbb3a624ee49a/author/4"><span itemprop="name">E. Zhang</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Daniel Weiskopf" itemprop="url" href="/person/1f598ebac63d1ab8f532fbb3a624ee49a/author/5"><span itemprop="name">D. Weiskopf</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/Book" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="name">ACM Symposium on Eye Tracking Research and Applications</span>, </em></span><em><span itemprop="publisher">Association for Computing Machinery</span>, </em>(<em><span>2020<meta content="2020" itemprop="datePublished"/></span></em>)</span>Tue Dec 22 15:56:00 CET 2020ACM Symposium on Eye Tracking Research and ApplicationsETRA ’20 AdjunctDemo of a Visual Gaze Analysis System for Virtual Board Games2020exc2075 myown peerreviewed pn6 VisME: Visual microsaccades explorerhttps://puma.ub.uni-stuttgart.de/bibtex/23dae0030c67daf0c2284d8ad7854e7f8/tanjamunztanjamunz2020-11-02T20:09:25+01:00EXC2075 myown peerReviewed pn6 vis(us) visus visus:munzta visus:weiskopf <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Tanja Munz" itemprop="url" href="/person/11c084a924f8af3fca651eb19fcfd520c/author/0"><span itemprop="name">T. Munz</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Lewis L. Chuang" itemprop="url" href="/person/11c084a924f8af3fca651eb19fcfd520c/author/1"><span itemprop="name">L. Chuang</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Sebastian Pannasch" itemprop="url" href="/person/11c084a924f8af3fca651eb19fcfd520c/author/2"><span itemprop="name">S. Pannasch</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Daniel Weiskopf" itemprop="url" href="/person/11c084a924f8af3fca651eb19fcfd520c/author/3"><span itemprop="name">D. Weiskopf</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/PublicationIssue" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="journal">Journal of Eye Movement Research</span>, </em> </span>(<em><span>December 2019<meta content="December 2019" itemprop="datePublished"/></span></em>)</span>Mon Nov 02 20:09:25 CET 2020Journal of Eye Movement ResearchDec.6VisME: Visual microsaccades explorer122019EXC2075 myown peerReviewed pn6 vis(us) visus visus:munzta visus:weiskopf Comparative Visual Gaze Analysis for Virtual Board Gameshttps://puma.ub.uni-stuttgart.de/bibtex/27f5535e5ea40af9aadd45c6f4833f393/tanjamunztanjamunz2020-10-24T18:24:44+02:00EXC2075 myown peerReviewed pn6 vis(us) visus visus:blaschta visus:munzta visus:weiskopf <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Tanja Munz" itemprop="url" href="/person/1cb2ff4ee5edc41ee8db9317d3c9acb99/author/0"><span itemprop="name">T. Munz</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Noel Schäfer" itemprop="url" href="/person/1cb2ff4ee5edc41ee8db9317d3c9acb99/author/1"><span itemprop="name">N. Schäfer</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Tanja Blascheck" itemprop="url" href="/person/1cb2ff4ee5edc41ee8db9317d3c9acb99/author/2"><span itemprop="name">T. Blascheck</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Kuno Kurzhals" itemprop="url" href="/person/1cb2ff4ee5edc41ee8db9317d3c9acb99/author/3"><span itemprop="name">K. Kurzhals</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Eugene Zhang" itemprop="url" href="/person/1cb2ff4ee5edc41ee8db9317d3c9acb99/author/4"><span itemprop="name">E. Zhang</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Daniel Weiskopf" itemprop="url" href="/person/1cb2ff4ee5edc41ee8db9317d3c9acb99/author/5"><span itemprop="name">D. Weiskopf</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/PublicationIssue" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="journal">The 13th International Symposium on Visual Information Communication and Interaction (VINCI 2020)</span>, </em> </span>(<em><span>2020<meta content="2020" itemprop="datePublished"/></span></em>)</span>Sat Oct 24 18:24:44 CEST 2020The 13th International Symposium on Visual Information Communication and Interaction (VINCI 2020)Comparative Visual Gaze Analysis for Virtual Board Games2020EXC2075 myown peerReviewed pn6 vis(us) visus visus:blaschta visus:munzta visus:weiskopf Overlap-Free Drawing of Generalized Pythagoras Trees for Hierarchy Visualizationhttps://puma.ub.uni-stuttgart.de/bibtex/2bfc8aa5f192ba5932034a88b1cb945df/tanjamunztanjamunz2020-10-16T18:11:44+02:00EXC2075 myown peerReviewed pn6 vis(us) visus visus:munzta visus:weiskopf <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Tanja Munz" itemprop="url" href="/person/17ef49c65ae0e8ce206a9e40206727c9e/author/0"><span itemprop="name">T. Munz</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Michael Burch" itemprop="url" href="/person/17ef49c65ae0e8ce206a9e40206727c9e/author/1"><span itemprop="name">M. Burch</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Toon van Benthem" itemprop="url" href="/person/17ef49c65ae0e8ce206a9e40206727c9e/author/2"><span itemprop="name">T. van Benthem</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Yoeri Poels" itemprop="url" href="/person/17ef49c65ae0e8ce206a9e40206727c9e/author/3"><span itemprop="name">Y. Poels</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Fabian Beck" itemprop="url" href="/person/17ef49c65ae0e8ce206a9e40206727c9e/author/4"><span itemprop="name">F. Beck</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Daniel Weiskopf" itemprop="url" href="/person/17ef49c65ae0e8ce206a9e40206727c9e/author/5"><span itemprop="name">D. Weiskopf</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/Book" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="name">2019 IEEE Visualization Conference (VIS)</span>, </em></span><em>page <span itemprop="pagination">251-255</span>. </em>(<em><span>October 2019<meta content="October 2019" itemprop="datePublished"/></span></em>)</span>Fri Oct 16 18:11:44 CEST 20202019 IEEE Visualization Conference (VIS)oct251-255Overlap-Free Drawing of Generalized Pythagoras Trees for Hierarchy Visualization2019EXC2075 myown peerReviewed pn6 vis(us) visus visus:munzta visus:weiskopf Generalized Pythagoras trees were developed for visualizing hierarchical data, producing organic, fractal-like representations. However, the drawback of the original layout algorithm is visual overlap of tree branches. To avoid such overlap, we introduce an adapted drawing algorithm using ellipses instead of circles to recursively place tree nodes representing the subhierarchies. Our technique is demonstrated by resolving overlap in diverse real-world and generated datasets, while comparing the results to the original approach.