Hledat
Zobrazují se záznamy 11-20 z 40
Improving Descriptors for Fast Tree Matching by Optimal Linear Projection
(IEEE, 2007-10)
In this paper we propose to transform an image descriptor so that nearest neighbor (NN) search for correspondences becomes the optimal matching strategy under the assumption that inter-image deviations of corresponding ...
Linear Predictors for Fast Simultaneous Modeling and Tracking
(IEEE, 2007-10)
An approach for fast tracking of arbitrary image features with no prior model and no offline learning stage is presented. Fast tracking is achieved using banks of linear displacement predictors learnt online. A multi-modal ...
Efficient Sequential Correspondence Selection by Cosegmentation
(IEEE, 2010-09)
In many retrieval, object recognition, and wide-baseline stereo methods, correspondences of interest points (distinguished regions) are commonly established by matching compact descriptors such as SIFTs. We show that a ...
P-N Learning: Bootstrapping Binary Classifiers by Structural Constraints
(IEEE, 2010-06)
This paper shows that the performance of a binary classifier can be significantly improved by the processing of structured unlabeled data, i.e. data are structured if knowing the label of one example restricts the labeling ...
Online learning of robust object detectors during unstable tracking
(IEEE, 2009-09)
This work investigates the problem of robust, longterm visual tracking of unknown objects in unconstrained environments. It therefore must cope with frame-cuts, fast camera movements and partial/total object occlusions/d ...
Efficient Representation of Local Geometry for Large Scale Object Retrieval
(IEEE, 2009-06)
State of the art methods for image and object retrieval exploit both appearance (via visual words) and local geometry (spatial extent, relative pose). In large scale problems, memory becomes a limiting factor - local ...
Tracking the Invisible: Learning Where the Object Might be
(IEEE, 2010-06)
Objects are usually embedded into context. Visual context has been successfully used in object detection tasks, however, it is often ignored in object tracking. We propose a method to learn supporters which are, be it only ...
Construction of Precise Local Affine Frames
(IEEE, 2010-08)
We propose a novel method for the refinement of Maximally Stable Extremal Region (MSER) boundaries to sub-pixel precision by taking into account the intensity function in the 2 × 2 neighborhood of the contour points. The ...
Face-TLD: Tracking-Learning-Detection applied to faces
(IEEE, 2010-09)
A novel system for long-term tracking of a human face in unconstrained videos is built on Tracking-Learning-Detection (TLD) approach. The system extends TLD with the concept of a generic detector and a validator which is ...
Forward-Backward Error: Automatic Detection of Tracking Failures
(IEEE, 2010-08)
This paper proposes a novel method for tracking failure detection. The detection is based on the Forward-Backward error, i.e. the tracking is performed forward and backward in time and the discrepancies between these two ...