Task-oriented learning of structured probability distributions
Explore this paper's citation graph
Summary
This thesis introduces a novel type of model to perform probabilistic structured output prediction for structured object prediction that takes into account the task at hand, and empirically demonstrates the ability of the model to capture distributions over complex objects.
- Type
- dissertation
- Published
- 2017-01-01
- Cited by
- 6
- References
- 126
- Access
- Open access
- OpenAlex
- https://openalex.org/W2809088500
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:125827727
Keywords
Probabilistic logic, Latent variable, Computer science, Pointwise, Machine learning
References
- Maximum Likelihood Theory for Incomplete Data from an Exponential Family
- Combinatorial Stochastic Processes
- Hands Deep in Deep Learning for Hand Pose Estimation
- Constrained Convolutional Neural Networks for Weakly Supervised Segmentation
- Bayesian data analysis.
- Some methods of speeding up the convergence of iteration methods
- Efficient Nonlinear Markov Models for Human Motion
- Charakterisierung der Entropien positiver Ordnung und der shannonschen Entropie
- Is object localization for free? - Weakly-supervised learning with convolutional neural networks
- Instructing people for training gestural interactive systems
- Empirical Minimum Bayes Risk Prediction: How to Extract an Extra Few % Performance from Vision Models with Just Three More Parameters
- Strictly Proper Scoring Rules, Prediction, and Estimation
- Cutting-plane training of structural SVMs
- A proof for the positive definiteness of the Jaccard index matrix
- Basic Concepts in Information Theory and Statistics: Axiomatic Foundations and Applications
- Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper
- A General Coefficient of Similarity and Some of Its Properties
- Expected Information as Expected Utility
- Real-Time Continuous Pose Recovery of Human Hands Using Convolutional Networks
- Optimizing Average Precision Using Weakly Supervised Data
Cited by
- Dissimilarity Coefficient Based Weakly Supervised Object Detection
- Weakly Supervised Instance Segmentation by Learning Annotation Consistent Instances
- Moment-Matching Graph-Networks for Causal Inference
- A Study of Inductive Biases for Unsupervised Speech Representation Learning
- Unsupervised speech representation learning
- Dissimilarity Coefficient based Weakly Supervised Object Detection - Supplementary Material
Related papers
- Wasserstein Generative Learning with Kinematic Constraints for Probabilistic Interactive Driving Behavior Prediction
- Improved Conditional VRNNs for Video Prediction
- A deep probabilistic framework for heterogeneous self-supervised learning of affordances
- Aspects of probabilistic modelling for data analysis
- Multi-output Gaussian Processes for Uncertainty-aware Recommender Systems
- Amortized Bayesian Model Comparison With Evidential Deep Learning