Search results
I am Johannes Knittel, a Wojcicki Troper HDSI Postdoctoral Fellow and member of the Visual Computing Group at Harvard. I am passionate about researching new ways of combining visualization and machine learning to gain more comprehensive insights into textual and multivariate datasets, as well as to better explain and understand black box AI models.
Staff: Dr. Johannes Knittel, Doctoral Researcher, Research Group Graphical Interactive Systems, Institute for Visualization and Interactive Systems (VIS), University of Stuttgart
Aug 6, 2021 · View a PDF of the paper titled Real-Time Visual Analysis of High-Volume Social Media Posts, by Johannes Knittel and 6 other authors. Breaking news and first-hand reports often trend on social media platforms before traditional news outlets cover them.
Johannes Knittel's 14 research works with 56 citations and 499 reads, including: The Role of Interactive Visualization in Explaining (Large) NLP Models: from Data to Inference
Jul 30, 2021 · View a PDF of the paper titled Efficient Sparse Spherical k-Means for Document Clustering, by Johannes Knittel and 2 other authors. Spherical k-Means is frequently used to cluster document collections because it performs reasonably well in many settings and is computationally efficient.
no code implementations • 11 Jan 2023 • Richard Brath, Daniel Keim, Johannes Knittel, SHimei Pan, Pia Sommerauer, Hendrik Strobelt We motivate the use of visualization in relation to target users and common NLP pipelines.
Abstract—Temporal action localization aims to identify the boundaries and categories of actions in videos, such as scoring a goal in a football match. Single-frame supervision has emerged as a labor-eficient way to train action localizers as it requires only one annotated frame per action.
