no code implementations • 1 Apr 2024 • Ruikun Hou, Tim Fütterer, Babette Bühler, Efe Bozkir, Peter Gerjets, Ulrich Trautwein, Enkelejda Kasneci
Our findings provide insights into using advanced, multimodal techniques for automated classroom observation, aiming to foster teacher training through frequent and valuable feedback.
1 code implementation • 26 Feb 2024 • Michael Kirchhof, Mark Collier, Seong Joon Oh, Enkelejda Kasneci
Similar to standard pretraining this enables the zero-shot transfer of uncertainties learned on a large pretraining dataset to specialized downstream datasets.
1 code implementation • 24 Feb 2024 • Zilong Zhao, Yao Rong, Dongyang Guo, Emek Gözlüklü, Emir Gülboy, Enkelejda Kasneci
SSC-CoT employs a strategy of selecting intermediate steps based on the intersection of various reasoning chains.
no code implementations • 6 Feb 2024 • Efe Bozkir, Süleyman Özdel, Ka Hei Carrie Lau, Mengdi Wang, Hong Gao, Enkelejda Kasneci
Lastly, we speculate that combining the information provided to LLM-powered environments by the users and the biometric data obtained through the sensors might lead to novel privacy invasions.
1 code implementation • 22 Jan 2024 • Mengdi Wang, Anna Bodonhelyi, Efe Bozkir, Enkelejda Kasneci
Federated learning is a distributed collaborative machine learning paradigm that has gained strong momentum in recent years.
no code implementations • 1 Jan 2024 • Arne Bewersdorff, Christian Hartmann, Marie Hornberger, Kathrin Seßler, Maria Bannert, Enkelejda Kasneci, Gjergji Kasneci, Xiaoming Zhai, Claudia Nerdel
The integration of Artificial Intelligence (AI), particularly Large Language Model (LLM)-based systems, in education has shown promise in enhancing teaching and learning experiences.
1 code implementation • 19 Dec 2023 • Yao Rong, Peizhu Qian, Vaibhav Unhelkar, Enkelejda Kasneci
Informed by existing work, I-CEE explains the decisions of image classification models by providing the user with an informative subset of training data (i. e., example images), corresponding local explanations, and model decisions.
no code implementations • 14 Nov 2023 • Virmarie Maquiling, Sean Anthony Byrne, Diederick C. Niehorster, Marcus Nyström, Enkelejda Kasneci
The advent of foundation models signals a new era in artificial intelligence.
1 code implementation • 12 Sep 2023 • Sean Anthony Byrne, Virmarie Maquiling, Marcus Nyström, Enkelejda Kasneci, Diederick C. Niehorster
This problem is exacerbated by both hardware-induced variations in eye images and inherent biological differences across the recorded participants, leading to both feature and pixel-level variance that hinders the generalizability of models trained on specific datasets.
no code implementations • 11 Aug 2023 • Arne Bewersdorff, Kathrin Seßler, Armin Baur, Enkelejda Kasneci, Claudia Nerdel
The AI system can accurately identify many fundamental student errors, for instance, the AI system identifies when a student is focusing the hypothesis not on the dependent variable but solely on an expected observation (acc.
1 code implementation • 10 Jun 2023 • Philipp Hallgarten, David Bethge, Ozan Özdenizci, Tobias Grosse-Puppendahl, Enkelejda Kasneci
Limited availability of labeled physiological data often prohibits the use of powerful supervised deep learning models in the biomedical machine intelligence domain.
no code implementations • 9 Jun 2023 • Yao Rong, Guanchu Wang, Qizhang Feng, Ninghao Liu, Zirui Liu, Enkelejda Kasneci, Xia Hu
A strategy of subgraph sampling is designed in LARA to improve the scalability of the training process.
no code implementations • 24 May 2023 • Yao Rong, Xiangyu Wei, Tianwei Lin, Yueyu Wang, Enkelejda Kasneci
In this work, we propose a novel feature fusion strategy, DynStaF (Dynamic-Static Fusion), which enhances the rich semantic information provided by the multi-frame (dynamic branch) with the accurate location information from the current single-frame (static branch).
no code implementations • 23 May 2023 • Efe Bozkir, Süleyman Özdel, Mengdi Wang, Brendan David-John, Hong Gao, Kevin Butler, Eakta Jain, Enkelejda Kasneci
Latest developments in computer hardware, sensor technologies, and artificial intelligence can make virtual reality (VR) and virtual spaces an important part of human everyday life.
1 code implementation • 12 Apr 2023 • Sean Anthony Byrne, Marcus Nyström, Virmarie Maquiling, Enkelejda Kasneci, Diederick C. Niehorster
Our method outperformed state-of-the-art algorithmic methods on real eye images with a 35% reduction in terms of spatial precision, and performed on par with state-of-the-art on simulated images in terms of spatial accuracy. We conclude that our method provides a precise method for CR center localization and provides a solution to the data availability problem which is one of the important common roadblocks in the development of deep learning models for gaze estimation.
1 code implementation • 6 Feb 2023 • Michael Kirchhof, Enkelejda Kasneci, Seong Joon Oh
We prove that these distributions recover the correct posteriors of the data-generating process, including its level of aleatoric uncertainty, up to a rotation of the latent space.
1 code implementation • 20 Oct 2022 • Yao Rong, Tobias Leemann, Thai-trang Nguyen, Lisa Fiedler, Peizhu Qian, Vaibhav Unhelkar, Tina Seidel, Gjergji Kasneci, Enkelejda Kasneci
A better understanding of the needs of XAI users, as well as human-centered evaluations of explainable models are both a necessity and a challenge.
Explainable Artificial Intelligence (XAI) Explainable Models +2
no code implementations • 1 Sep 2022 • Chen Xin, Thomas Motz, Wolfgang Fuhl, Andreas Hartel, Enkelejda Kasneci
A typical traditional method is to excite electromagnetic waves in the cylinder structure and analytically solve the piston position based on the scattering parameters measured by a sensor.
1 code implementation • 8 Jul 2022 • Michael Kirchhof, Karsten Roth, Zeynep Akata, Enkelejda Kasneci
We model images as directional von Mises-Fisher (vMF) distributions on the hypersphere that can reflect image-intrinsic uncertainties.
1 code implementation • 28 Jun 2022 • Tobias Leemann, Michael Kirchhof, Yao Rong, Enkelejda Kasneci, Gjergji Kasneci
Interest in understanding and factorizing learned embedding spaces through conceptual explanations is steadily growing.
2 code implementations • 26 Apr 2022 • Yao Rong, Naemi-Rebecca Kassautzki, Wolfgang Fuhl, Enkelejda Kasneci
Human drivers use their attentional mechanisms to focus on critical objects and make decisions while driving.
no code implementations • 29 Mar 2022 • Daniel Weber, Wolfgang Fuhl, Andreas Zell, Enkelejda Kasneci
For this purpose, we explore different sizes of temporal windows, which serve as a basis for the computation of heatmaps, i. e., the spatial distribution of the gaze data.
1 code implementation • 1 Feb 2022 • Yao Rong, Tobias Leemann, Vadim Borisov, Gjergji Kasneci, Enkelejda Kasneci
With a variety of local feature attribution methods being proposed in recent years, follow-up work suggested several evaluation strategies.
1 code implementation • 2 Nov 2021 • Yao Rong, Wenjia Xu, Zeynep Akata, Enkelejda Kasneci
The way humans attend to, process and classify a given image has the potential to vastly benefit the performance of deep learning models.
Ranked #41 on Fine-Grained Image Classification on CUB-200-2011
no code implementations • 29 Sep 2021 • Vadim Borisov, Klaus Broelemann, Enkelejda Kasneci, Gjergji. Kasneci
Although deep neural networks (DNNs) constitute the state-of-the-art in many tasks based on image, audio, or text data, their performance on heterogeneous, tabular data is typically inferior to that of decision tree ensembles.
no code implementations • 11 Jun 2021 • Benedikt Hosp, Myat Su Yin, Peter Haddawy, Ratthapoom Watcharporas, paphon Sa-ngasoonsong, Enkelejda Kasneci
During arthroscopic surgeries, surgeons are faced with challenges like cognitive re-projection of the 2D screen output into the 3D operating site or navigation through highly similar tissue.
no code implementations • 6 May 2021 • Ömer Sümer, Cigdem Beyan, Fabian Ruth, Olaf Kramer, Ulrich Trautwein, Enkelejda Kasneci
One approach that can promote efficient development of presentation competence is the automated analysis of human behavior during a speech based on visual and audio features and machine learning.
no code implementations • 11 Feb 2021 • Benedikt Hosp, Myat Su Yin, Peter Haddawy, Paphon Sa-Ngasoongsong, Enkelejda Kasneci
In this study, we present a model for classifying experts, 4th-year residents and 3rd-year residents, using only eye movements.
no code implementations • 3 Feb 2021 • Wolfgang Fuhl, Gjergji Kasneci, Enkelejda Kasneci
The data set includes 2D and 3D landmarks, semantic segmentation, 3D eyeball annotation and the gaze vector and eye movement types for all images.
no code implementations • 12 Jan 2021 • Wolfgang Fuhl, Enkelejda Kasneci
We present a new dataset with annotated eye movements.
no code implementations • 11 Jan 2021 • Ömer Sümer, Patricia Goldberg, Sidney D'Mello, Peter Gerjets, Ulrich Trautwein, Enkelejda Kasneci
To best examine student visual engagement in the classroom, we conducted a study utilizing the audiovisual recordings of classes at a secondary school over one and a half month's time, acquired continuous engagement labeling per student (N=15) in repeated sessions, and explored computer vision methods to classify engagement levels from faces in the classroom.
Facial Expression Recognition Facial Expression Recognition (FER) +1
no code implementations • 6 Jan 2021 • Yao Rong, Chao Han, Christian Hellert, Antje Loyal, Enkelejda Kasneci
As interest in autonomous driving increases, efforts are being made to meet requirements for the high-level automation of vehicles.
no code implementations • 2 Oct 2020 • Wolfgang Fuhl, Yao Rong, Thomas Motz, Michael Scheidt, Andreas Hartel, Andreas Koch, Enkelejda Kasneci
The presented algorithm based on conditional probabilities is also online capable and requires only a fraction of memory compared to the kNN algorithm.
no code implementations • 2 Oct 2020 • Wolfgang Fuhl, Enkelejda Kasneci
We also discuss the influence of purely rotational invariant features on accuracy.
no code implementations • 2 Oct 2020 • Wolfgang Fuhl, Enkelejda Kasneci
Batch normalization is currently the most widely used variant of internal normalization for deep neural networks.
no code implementations • 28 Sep 2020 • Mariella Dreissig, Mohamed Hedi Baccour, Tim Schaeck, Enkelejda Kasneci
A concluding analysis of the best performing feature sets yields valuable insights about the influence of drowsiness on the driver's blink behavior and head movements.
no code implementations • 23 Sep 2020 • Benedikt Hosp, Florian Schultz, Oliver Höner, Enkelejda Kasneci
The latest research in expertise assessment of soccer players has affirmed the importance of perceptual skills (especially for decision making) by focusing either on high experimental control or on a realistic presentation.
1 code implementation • 20 Jun 2020 • Yao Rong, Zeynep Akata, Enkelejda Kasneci
Numerous car accidents are caused by improper driving maneuvers.
no code implementations • 12 Jun 2020 • Wolfgang Fuhl, Enkelejda Kasneci
This kind of pooling allows for the integration of multi-layer neural networks directly into a model as a pooling operation by restructuring the data and, as a result, learnin complex pooling operations.
no code implementations • 31 Mar 2020 • Nora Castner, Thomas Kübler, Katharina Scheiter, Juilane Richter, Thérése Eder, Fabian Hüttig, Constanze Keutel, Enkelejda Kasneci
Modeling eye movement indicative of expertise behavior is decisive in user evaluation.
no code implementations • 20 Feb 2020 • Efe Bozkir, Onur Günlü, Wolfgang Fuhl, Rafael F. Schaefer, Enkelejda Kasneci
New generation head-mounted displays, such as VR and AR glasses, are coming into the market with already integrated eye tracking and are expected to enable novel ways of human-computer interaction in numerous applications.
no code implementations • 17 Feb 2020 • Wolfgang Fuhl, Yao Rong, Enkelejda Kasneci
In this paper, we use fully convolutional neural networks for the semantic segmentation of eye tracking data.
no code implementations • 17 Feb 2020 • Wolfgang Fuhl, Efe Bozkir, Enkelejda Kasneci
In this paper, we present an approach based on reinforcement learning for eye tracking data manipulation.
no code implementations • 14 Jan 2020 • Ömer Sümer, Peter Gerjets, Ulrich Trautwein, Enkelejda Kasneci
A possible solution would be to request permission to record the audio-visual recordings of all students (including those who do not voluntarily participate in the study) and to anonymise their data.
no code implementations • 12 Jan 2020 • Ömer Sümer, Peter Gerjets, Ulrich Trautwein, Enkelejda Kasneci
This paper addresses the problem of understanding joint attention in third-person social scene videos.
no code implementations • 6 Nov 2019 • Efe Bozkir, Ali Burak Ünal, Mete Akgün, Enkelejda Kasneci, Nico Pfeifer
Eye tracking is handled as one of the key technologies for applications that assess and evaluate human attention, behavior, and biometrics, especially using gaze, pupillary, and blink behaviors.
no code implementations • 24 May 2019 • Wolfgang Fuhl, Gjergji Kasneci, Wolfgang Rosenstiel, Enkelejda Kasneci
Our approach reduces the complexity of convolutions by replacing it with binary decisions.
no code implementations • 29 Jan 2019 • Wolfgang Fuhl, Enkelejda Kasneci
In addition, we evaluated the impact of the validation loss on the landmark accuracy based on uniform sampling.
no code implementations • 22 May 2018 • Ömer Sümer, Patricia Goldberg, Kathleen Stürmer, Tina Seidel, Peter Gerjets, Ulrich Trautwein, Enkelejda Kasneci
The ability for a teacher to engage all students in active learning processes in classroom constitutes a crucial prerequisite for enhancing students achievement.
no code implementations • 28 Mar 2018 • Wolfgang Fuhl, Thiago Santini, Thomas Kuebler, Nora Castner, Wolfgang Rosenstiel, Enkelejda Kasneci
Eye movements hold information about human perception, intention and cognitive state.
1 code implementation • 24 Dec 2017 • Thiago Santini, Wolfgang Fuhl, Enkelejda Kasneci
state-of-the-art algorithms by 25. 05 and 10. 94 percentage points, respectively, demonstrating the meaningfulness of PuRe's confidence measure.
no code implementations • 9 Nov 2017 • Wolfgang Fuhl, Thiago Santini, Enkelejda Kasneci
Many cameras implement auto-focus functionality.
no code implementations • 30 Oct 2017 • Wolfgang Fuhl, Thiago Santini, Gjergji Kasneci, Wolfgang Rosenstiel, Enkelejda Kasneci
Real-time, accurate, and robust pupil detection is an essential prerequisite for pervasive video-based eye-tracking.
no code implementations • 19 Jan 2016 • Wolfgang Fuhl, Thiago Santini, Gjergji Kasneci, Enkelejda Kasneci
Real-time, accurate, and robust pupil detection is an essential prerequisite for pervasive video-based eye-tracking.
no code implementations • 24 Nov 2015 • Thiago Santini, Wolfgang Fuhl, Thomas Kübler, Enkelejda Kasneci
Smooth pursuit eye movements provide meaningful insights and information on subject's behavior and health and may, in particular situations, disturb the performance of typical fixation/saccade classification algorithms.
no code implementations • 23 Nov 2015 • Thomas C. Kübler, Tobias Rittig, Judith Ungewiss, Christina Krauss, Enkelejda Kasneci
While for the evaluation of robustness of eye tracking algorithms the use of real-world data is essential, there are many applications where simulated, synthetic eye images are of advantage.
no code implementations • 20 Nov 2015 • Wolfgang Fuhl, Thiago C. Santini, Thomas Kuebler, Enkelejda Kasneci
Fast and robust pupil detection is an essential prerequisite for video-based eye-tracking in real-world settings.