Ommen, M.L.
Co Author Listing * Detection and Localization of Ultrasound Scatterers Using Convolutional Neural Networks
Ommer, B.[Bjoern]
Co Author Listing * Home Page.
* email: Ommer, B.[Bjoern]: bjoern ommer AT iwr uni-heidelberg de
* Behavior-Driven Synthesis of Human Dynamics
* Beyond Bounding-Boxes: Learning Object Shape by Model-Driven Grouping
* Beyond straight lines: Object detection using curvature
* Beyond the Sum of Parts: Voting with Groups of Dependent Entities
* Compositional Object Recognition, Segmentation, and Tracking in Video
* Content and Style Disentanglement for Artistic Style Transfer
* Content Transformation Block for Image Style Transfer, A
* Contour-based object detection
* Cross and Learn: Cross-Modal Self-supervision
* Cross-Image-Attention for Conditional Embeddings in Deep Metric Learning
* Deep Semantic Feature Matching
* Deep unsupervised learning of visual similarities
* Deep Unsupervised Similarity Learning Using Partially Ordered Sets
* Detecting gestures in medieval images
* Disentangling Invertible Interpretation Network for Explaining Latent Representations, A
* Diva: Diverse Visual Feature Aggregation for Deep Metric Learning
* Divide and Conquer the Embedding Space for Metric Learning
* Efficient Clustering Earth Mover's Distance
* Exploiting Low-Level Image Segmentation for Object Recognition
* From Meaningful Contours to Discriminative Object Shape
* Generative regularization with latent topics for discriminative object recognition
* Geometry-Free View Synthesis: Transformers and no 3D Priors
* High-Resolution Image Synthesis with Latent Diffusion Models
* Improving Deep Metric Learning by Divide and Conquer
* Improving Spatiotemporal Self-supervision by Deep Reinforcement Learning
* iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis
* Learning Compositional Categorization Models
* Learning Discriminative Chamfer Regularization
* Learning Latent Constituents for Recognition of Group Activities in Video
* Learning Multi-Scale Photo Exposure Correction
* Learning the Compositional Nature of Visual Object Categories for Recognition
* Learning the Compositional Nature of Visual Objects
* Learning Top-Down Grouping of Compositional Hierarchies for Recognition
* Learning Where to Drive by Watching Others
* Less Is More: Video Trimming for Action Recognition
* LSTM Self-Supervision for Detailed Behavior Analysis
* Making Sense of CNNs: Interpreting Deep Representations and Their Invariances with INNs
* Max-Margin Regularization for Reducing Accidentalness in Chamfer Matching
* MIC: Mining Interclass Characteristics for Improved Metric Learning
* Morphological analysis for investigating artistic images
* Multi-scale object detection by clustering lines
* Object Categorization by Compositional Graphical Models
* Offline learning of prototypical negatives for efficient online Exemplar SVM
* PADS: Policy-Adapted Sampling for Visual Similarity Learning
* Per-Sample Kernel Adaptation for Visual Recognition and Grouping
* Randomized Max-Margin Compositions for Visual Recognition
* Recognition and Analysis of Objects in Medieval Images
* Reconstructing the drawing process of reproductions from medieval images
* Reflecting on How Artworks Are Processed and Analyzed by Computer Vision
* Regularizing max-margin exemplars by reconstruction and generative models
* Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes
* Robust Multiple-Instance Learning with Superbags
* SceneGenie: Scene Graph Guided Diffusion Models for Image Synthesis
* Seeing the Objects Behind the Dots: Recognition in Videos from a Moving Camera
* Self-Supervised Learning of Pose Embeddings from Spatiotemporal Relations in Videos
* Shaping Art with Art: Morphological Analysis for Investigating Artistic Reproductions
* Sharing Matters for Generalization in Deep Metric Learning
* SLIM: Self-Supervised LiDAR Scene Flow and Motion Segmentation
* Stochastic Image-to-Video Synthesis using cINNs
* Style-Aware Content Loss for Real-Time HD Style Transfer, A
* Taming Transformers for High-Resolution Image Synthesis
* Towards Learning a Realistic Rendering of Human Behavior
* Understanding Object Dynamics for Interactive Image-to-Video Synthesis
* Unsupervised Magnification of Posture Deviations Across Subjects
* Unsupervised Part Discovery by Unsupervised Disentanglement
* Unsupervised Part-Based Disentangling of Object Shape and Appearance
* Unsupervised representation learning by discovering reliable image relations
* Unsupervised Robust Disentangling of Latent Characteristics for Image Synthesis
* Unsupervised Video Understanding by Reconciliation of Posture Similarities
* Video parsing for abnormality detection
* Voting by Grouping Dependent Parts
* Weakly Supervised Learning of Dense Semantic Correspondences and Segmentation
* X-GAN: Improving Generative Adversarial Networks with ConveX Combinations
Includes: Ommer, B.[Bjoern] Ommer, B.[Björn] Ommer, B.[Bjorn] Ommer, B.
75 for Ommer, B.