J
Jana Kosecka
Researcher at George Mason University
Publications - 166
Citations - 10467
Jana Kosecka is an academic researcher from George Mason University. The author has contributed to research in topics: Object detection & Motion estimation. The author has an hindex of 45, co-authored 155 publications receiving 9087 citations. Previous affiliations of Jana Kosecka include Austrian Institute of Technology & University of Pennsylvania.
Papers
More filters
Proceedings ArticleDOI
Localization Based on Building Recognition
Wei Zhang,Jana Kosecka +1 more
TL;DR: A hierarchical approach for recognition of buildings is described, using a novel and efficient representation named localized color histograms that enables efficient retrieval of a small number of candidate matches from the database.
Proceedings ArticleDOI
Multiview RGB-D Dataset for Object Instance Detection
TL;DR: In this article, a new multi-view RGB-D dataset of nine kitchen scenes is presented, each containing several objects in realistic cluttered environments including a subset of objects from the Big Bird dataset.
Journal ArticleDOI
Hierarchical building recognition
Wei Zhang,Jana Kosecka +1 more
TL;DR: A hierarchical approach for building recognition using a method for selecting discriminative SIFT features and a simple probabilistic model for integration of the evidence from individual matches based on the match quality is proposed.
Posted Content
Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks
TL;DR: In this paper, a model for simultaneous depth estimation and semantic segmentation from a single RGB image is presented, which demonstrates the feasibility of training parts of the model for each task and then fine tuning the full, combined model on both tasks simultaneously using a single loss function.
Proceedings ArticleDOI
Generalized RANSAC Framework for Relaxed Correspondence Problems
Wei Zhang,Jana Kosecka +1 more
TL;DR: This paper considers multiple candidate matches for each feature, and integrates this choice with the robust estimation stage, thus avoiding the early commitment to the "best" one and yields a generalized RANSAC framework for identifying the true correspondences among sets of matches.