Sitemap
- Home
- Research
- Departments
- Algorithms and Complexity
- Computer Vision and Machine Learning
- People
- Bernt Schiele
- Connie Balzert
- Jonas Fischer
- Margret Keuper
- Jan Eric Lenssen
- Gerard Pons-Moll
- Ahmed Abbas
- Eyad Alshami
- Alaa Anani
- Mohammad Asim
- Niklas Berndt
- Wolfgang Böttcher
- Xinya Chen
- Julian Chibane
- Anurag Das
- Yue Fan
- Siddhartha Gairola
- Ada Görgün
- Xinting Hu
- Steffen Jung
- Muhammad Gulzain Ali Khan
- Anna Kukleva
- Selim Kuzucu
- Verica Lazova
- Zhi Li
- Sweta Mahajan
- Amin Parchami Araghi
- Nhi Pham
- Sukrut Rao
- Mattia Segu
- Garvita Tiwari
- Haoran Wang
- Christopher Wewer
- Thomas Wimmer
- Jiahao Xie
- Xianghui Xie
- Raza Yunus
- Xiaohan Zhang
- Alumni and Former Members
- Zeynep Akata
- Stephan Alaniz
- Thiemo Alldieck
- Bjoern Andres
- Mykhaylo Andriluka
- Stavros Antifakos
- Rodrigo Benenson
- Bharat Lal Bhatnagar
- Apratim Bhattacharyya
- Ulf Blanke
- Moritz Böhle
- Andreas Bulling
- Victoria Carlsson
- Di Chen
- Walon Wei-Chen Chiu
- Dengxin Dai
- Alina Dima
- Jiangxin Dong
- Gyuri Dorko
- Sandra Ebert
- Mario Fritz
- Fabio Galasso
- Peter Gehler
- Yong Guo
- Vladimir Guzov
- Hossein Hajipour
- Yang He
- Xudong Hong
- Sabrina Hoppe
- Andrea Hornakova
- Jan Hosang
- Michael Huang
- Tam Huynh
- Eldar Insafutdinov
- Jiaxi Jiang
- Li Jiang
- Qiuhong Ke
- Nicky Kern
- Anna Khoreva
- Hannes Kruppa
- Jan-Hendrik Lange
- Maksim Lapin
- Diane Larlus
- Bastian Leibe
- Evgeny Levinkov
- Wenbin Li
- Yaoyao Liu
- Max Losch
- Jovita Lukasik
- Nikodem Majer
- Mateusz Malinowski
- Florian Michahelles
- Krystian Mikolajczyk
- Aymen Mir
- Philipp Müller
- Seong Joon Oh
- Mohamed Omran
- Tribhuvanesh Orekondy
- Bojan Pepik
- Leonid Pishchulin
- Andrea Ramazzina
- Farzaneh Rezaeianaran
- Anna Rohrbach
- Marcus Rohrbach
- Hosnieh Sattar
- Dominik Scheuble
- Paul Schnitzpan
- Edgar Seemann
- Gaurav Sharma
- Saurabh Sharma
- Rakshith Shetty
- Shaoshuai Shi
- Martin Šimonovský
- Martin Spengler
- Michael Stark
- Julian Steil
- Ulrich Steinhoff
- Maja Stikic
- David Stutz
- Yusuke Sugano
- Qianru Sun
- Paul Swoboda
- Siyu Tang
- Elena Tretyak
- Kristof Van Laerhoven
- Julia Vogel
- Stefan Walk
- Stefanie Walz
- Haiyang Wang
- Christian Wojek
- Yongqin Xian
- Wenjia Xu
- Ning Yu
- Shanshan Zhang
- Xucong Zhang
- Keyang Zhou
- Andreas Zinnen
- Research
- People Detection, Pose Estimation and Tracking
- How Far are We from Solving Pedestrian Detection?
- Person Recognition in Personal Photo Collections
- Taking a Deeper Look at Pedestrians
- Poselet Conditioned Pictorial Structures
- Articulated People Detection and Pose Estimation
- Leveraging 3D Body Model for Training Data Generation
- Multi-view Pictorial Structures for 3D Human Pose Estimation
- Learning People Detectors for Tracking in Crowded Scenes
- People Detection and Tracking
- Multi-Cue Onboard Pedestrian Detection
- Pictorial Structures Revisited: People Dectection and Articulated Pose Estimation
- Monocular 3D Pose Estimation and Tracking by Detection
- People-Tracking-by-Detection and People-Detection-by-Tracking
- Multiple People Tracking with Lifted Multicut and Person Re-identification
- Visual Privacy
- Adversarial Robustness
- Zero-Shot Learning
- f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning
- Semantic Projection Network for Zero- and Few-Label Semantic Segmentation
- Gaze Embeddings for Zero-Shot Image Classification
- Feature Generating Networks for Zero-Shot Learning
- Evaluation of Output Embeddings for Fine-Grained Image Classification
- Learning Deep Representations of Fine-Grained Visual Descriptions
- Multi-Cue Zero-Shot Learning with Strong Supervision
- Latent Embeddings for Zero-shot Classification
- Zero-Shot Learning - The Good, the Bad and the Ugly
- Generative Models
- Vision and Language
- Human Activity Recognition
- Social Relation Recognition
- Discovery of Everyday Human Activities From Long-term Visual Behaviour Using Topic Models
- MPII Cooking 2 Dataset
- MPII Cooking Activities Dataset
- MPII Cooking Composite Activities
- MPIIEmo Dataset
- Activity Spotting & Composite Activities
- Recognition of Ongoing Complex Activities by Sequence Prediction over a Hierarchical Label Space
- Knowledge Transfer and Semi-supervised Learning
- Weakly Supervised Learning
- Image Segmentation
- Video Segmentation
- VSB100: A Unified Video Segmentation Benchmark
- Video Segmentation with Superpixels
- Learning Must-Link Constraints for Video Segmentation
- Spectral graph reduction
- Classifier Based Graph Construction for Video Segmentation
- Improved Image Boundaries for Better Video Segmentation
- Multi-Class Video Co-Segmentation
- RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling
- Learning Video Object Segmentation from Static Images
- Lucid Data Dreaming for Object Tracking
- Video Object Segmentation with Language Referring Expressions
- Object Recognition and Scene Understanding
- Learning Non-Maximum Suppression
- Loss Functions for Top-k Error
- Top-k Multiclass SVM
- Output Kernel Learning
- Cityscapes Dataset
- What makes for effective detection proposals?
- Object Disambiguation for Augmented Reality Applications
- Differentiating HOG
- Cross-Modal Stereo by Using Kinect
- Scalable Multitask Representation Learning for Scene Classification
- Learning Using Privileged Information: SVM+ and Weighted SVM
- Learning Smooth Pooling Regions for Visual Recognition
- Recognizing Materials from Virtual Examples
- MPII Multi-Kinect Dataset
- Teaching 3D Geometry to Deformable Part Models
- Image Warping For Face Recognition
- Addressing scalability in object recognition
- Monocular Scene Understanding from Moving Platforms
- Gaze-Based Human-Computer Interaction
- Forecasting User Attention During Everyday Mobile Interactions Using Device-Integrated and Wearable Sensors
- Fixation Detection for Head-Mounted Eye Tracking Based on Visual Similarity of Gaze Targets
- InvisibleEye: Mobile Eye Tracking Using Multiple Low-Resolution Cameras and Learning-Based Gaze Estimation
- Towards High-Frequency SSVEP-Based Target Discrimination with an Extended Alphanumeric Keyboard
- Deep Gaze Pooling: Inferring and Reconstructing Search Intent From Human Fixations
- 3D Gaze Estimation from 2D Pupil Positions on Monocular Head-Mounted Eye Trackers
- Prediction of Search Targets From Fixations in Open-World Settings
- Appearance-Based Gaze Estimation in the Wild
- Revisiting Data Normalization for Appearance-Based Gaze Estimation
- It’s Written All Over Your Face: Full-Face Appearance-Based Gaze Estimation
- Labelled Pupils in the Wild (LPW)
- 3D Reconstruction and Perception of People
- Generative Models of 3D People
- Human Pose Estimation from Video and IMU
- People Detection, Pose Estimation and Tracking
- Application
- Teaching at Saarland University (UdS)
- Publications
- Software and Datasets
- D2 Wiki
- People
- Internet Architecture
- People
- Anja Feldmann
- Ali Rasaii
- Cristian Munteanu
- Danesh Zeynali
- Emilia Ndilokelwa Weyulu
- Fahad Hilal
- Fariba Osali
- Florian Steurer
- Friedemann Lipphardt
- Ha Dao Thi Thu
- Iman Alipour
- Iris Wagner
- Johannes Zirngibl
- Jörg Dorchain
- Mannat Kaur
- Mahsa Ghaderan
- Moonis Ali
- Pascal Hennen
- Qi Guo
- Rainer May
- Sadia Nourin
- Sebastian Kappes
- Seifeddine Fathalli
- Simran Munot
- Sina Rostami
- Taha Albakour
- Tiago Heinrich
- Tobias Fiebig
- Vaishnavi Raghavajosyula
- Zubair Sediqi
- Research
- Analysis of the Covid-19 pandemic
- Benchmarking congestion-control algorithms
- Care, People, Gender, Culture
- Digital Infrastructure
- Emerging Platforms and Communities on the Web
- Flow queries
- Future-proof the Internet
- Internet Security
- Online content moderation
- Online hate speech & conspiracy theories
- Routing & Network Management
- Understanding, Detecting, and Mitigating Weaponized Information
- Port 0
- Verification of Programmable Networks
- Video streaming
- VPN
- Software
- Teaching
- Data Networks - Summer 2025
- Data Networks - Summer 2024
- Data Networks - Summer 2023
- Data Networks - Summer 2022
- Data Networks - Summer 2021
- Data Networks - Summer 2020
- Data Networks - Winter 2019
- Hot Topics in Data Networks - Winter 2025
- Hot Topics in Data Networks - Winter 2024
- Hot Topics in Data Networks - Winter 2023
- Hot Topics in Data Networks - Winter 2022
- Hot Topics in Data Networks - Winter 2021
- Router Lab - Winter 2025
- On the Practice of System and Network Engineering - Winter 2024
- Student projects / Bachelor or Master Thesis Projects
- Offers
- Publications
- INET Group Wiki
- People
- Computer Graphics
- Databases and Information Systems
- People
- Research
- Commonsense Knowledge
- Question Answering
- Personal Knowledge
- Neural Information Retrieval
- YAGO-NAGA
- Knowledge Base Recall
- LM4KBC
- Document Coverage Prediction
- Interesting negations in Knowledge Bases
- Count Knowledge
- Recoin
- CINEX
- Completeness rule mining
- COOL-WD
- Machine Knowledge: Creation and Curation of Comprehensive Knowledge Bases
- Tutorials
- Completeness, Recall, and Negation in Open-World Knowledge Bases - KR 2021 tutorial
- Completeness, Recall, and Negation in Open-World Knowledge Bases - ISWC'21 Tutorial
- Completeness, Recall, and Negation in Open-World Knowledge Bases - VLDB'21 Tutorial
- Completeness, Recall, and Negation in Open-World Knowledge Bases - WWW'22 Tutorial
- Google Award
- imPACT
- Counterfactual Explanations for Recommenders
- Credibility Analysis in News Communities
- Credibility Analysis in Health Communities
- Probabilistic Graphical Models for Credibility Analysis
- Deep Learning based Credibility Analysis
- Web Credibility Analysis
- R-Susceptibility
- Fair Data Representations
- Mediator Accounts
- Relationships between Actions and Feeds
- Learning from Feedback on Explanations
- ExFAKT: Explainable Fact Checking
- AmbiverseNLU
- Teaching
- News & Events
- Publications
- Software
- Demo Systems
- Visual Computing and Artificial Intelligence
- Automation of Logic
- People
- Research Areas
- Offers
- Teaching
- Talks & Events
- Projects
- Publications
- Software
- Useful Links
- Intranet
- Network and Cloud Systems
- Multimodal Language Processing
- Publications
- Research Coordination
- Ombudsperson for Good Scientific Practice and Doctoral Research
- Open Science
- Departments
- Collaborations
- Research
- Graduate Programs
- International Max Planck Research School on Trustworthy Computing
- Maryland Max Planck Ph.D. Program in Computer Science
- Max Planck Graduate Center for Computer and Information Science
- Konrad Zuse School of Excellence in Learning and Intelligent Systems (ELIZA)
- Research Training Group on Neuroexplicit Models
- Saarbrücken Graduate School of Computer Science
- News & Events
- People
- Services
- Career
- Software
- About Us
- COVID-19
- Sitemap
- Imprint
- Data Protection