Search

in terms of the normalized cut and of its spectral clustering relaxation. The proposed method reduces runtime and memory consumption and yields on par results in image and video segmentation. Further, it [...] segmentation and that is large enough to avoid overfitting. Consequently, there is little analysis of video segmentation which generalizes across subtasks, and it is not yet clear which and how video s [...] hierarchies, and that reflects the tradeoff between over-segmentation and segmentation accuracy. Video Segmentation with Superpixels This work contributes a thorough analysis of various within- and between-frame

We explore different algorithms and their dependency on the underlying graph structure given by different image descriptors and distance measures. We provide several unsupervised and supervised graph improvement [...] Research Departments Computer Vision and Machine Learning Research Knowledge Transfer and Semi-supervised Learning Knowledge Transfer and Semi-supervised Learning Semi-supervised Learning in Image Collections [...] dataset-independent and good labeling. Large-Scale Knowledge Transfer We explore knowledge transfer and sharing in a large scale classification setting. We compare hierarchical, attribute-based, and direct transfer

to have significant potential for activity recognition and computational behaviour analysis but previous works focused on supervisedmethods and recognition of predefined activity classes basedon short-term [...] representation of visual behaviour encoding saccades, fixations, and blinks with a latent Dirichlet allocation (LDA) topic model. We further propose and evaluate different methods to encode saccades for use in [...] reading, computer work, watching media, and eating. In addition, we include periods with no specific activity. We show the ability of our method to model and discover these activities with competitive

Research Departments Computer Vision and Machine Learning Research People Detection, Pose Estimation and Tracking People Detection, Pose Estimation and Tracking How Far are We from Solving Pedestrian Detection [...] convnets, and discuss which factors affect their performance. Other than our in-depth analysis, we report top performance on the Caltech dataset, and provide a new sanitized set of training and test annotations [...] people in personal photo albums in the presence of occluded faces and appearance changes. The method is simple and is built on open source and open data, yet it improves the state of the art results on a large

Computing Fine-Grained Complexity and Algorithm Design Graph Algorithms Learning-Augmented Algorithms Optimization Parameterized and Counting Algorithms and Complexity String Algorithms and Data Compression [...] navigation Institute D1 Algorithms & Complexity D2 Computer Vision and Machine Learning D3 Internet Architecture D4 Computer Graphics D5 Databases and Information Systems D6 Visual Computing and Artificial Intelligence [...] Structure, Algorithms, Applications, and Open Problems (Kanazawa Talk) , Erice School on Graph Theory, Algorithms, and Applications, July 2008 ; Japan Conference on Computational Geometry and Graphs, November

Computing Fine-Grained Complexity and Algorithm Design Graph Algorithms Learning-Augmented Algorithms Optimization Parameterized and Counting Algorithms and Complexity String Algorithms and Data Compression [...] navigation Institute D1 Algorithms & Complexity D2 Computer Vision and Machine Learning D3 Internet Architecture D4 Computer Graphics D5 Databases and Information Systems D6 Visual Computing and Artificial Intelligence [...] Automation of Logic RG2 Network and Cloud Systems RG3 Multimodal Language Processing Algorithms & Complexity People Current Members Former Members Research Algorithmic Game Theory Clustering Distributed

Computer Vision and Machine Learning Research People Detection, Pose Estimation and Tracking People-Tracking-by-Detection and People-Detection-by-Tracking People-Tracking-by-Detection and People-Detecti [...] Abstract: Both detection and tracking people are challenging problems, especially in complex real world scenes that commonly involve multiple people, complicated occlusions, and cluttered or even moving [...] show detection and tracking of people on the "TUD Campus" sequence (left) and "TUD Crossing" sequence (right). Tracks of each person are visualized using unique combination of color and line type. The

the corresponding publications [1],[2] and code. Please contact us if you have questions Download License The data is only to be used for scientific purposes and must not be republished other than by the [...] Max Planck Institute for Informatics. The scientific use includes processing the data and showing it in publications and presentations. When using it please cite [1]. Activity Recognition dataset README Raw [...] Pinkal and B. Schiele, European Conference on Computer Vision (ECCV), October, (2012) [2] A Database for Fine Grained Activity Detection of Cooking Activities , M. Rohrbach, S. Amin, M. Andriluka and B. Schiele

scientific purposes and must not be republished other than by the Max Planck Institute for Informatics. The scientific use includes processing the data and showing it in publications and presentations. When [...] intermediate pose features (pose, tracks, 138 MB) Evaluation Code and data code (version 1.0) data (version 1.0): includes our classification and detection results to produce the tables in the paper ground truth [...] s, and evaluation code (version 1.2, 360 MB) 3D pose challenge [2] Continous pose challenge Continous frames labeled with human pose (no published results on this so far). Images, annotations, and evaluation

Departments Computer Vision and Machine Learning Research People Detection, Pose Estimation and Tracking People Detection and Tracking People Detection and Tracking Finding and following people is a key [...] problems in computer vision and remains a scientific challenge for realistic and challenging scenes. We developed a new approach for detecting people and estimating their poses in complex street scenes with multiple [...] a novel and generic procedure for people detection and 2D pose estimation [1] that is based on the pictorial structures model and also enables to estimate viewpoints of people from monocular and single