Sciweavers

BMVC
2010
13 years 9 months ago
Active 3D Segmentation through Fixation of Previously Unseen Objects
We present an approach for active segmentation based on integration of several cues. It serves as a framework for generation of object hypotheses of previously unseen objects in n...
Mårten Björkman, Danica Kragic
BMVC
2010
13 years 9 months ago
Pose and Expression-Invariant 3D Face Recognition using Elastic Radial Curves
Hassen Drira, Boulbaba Ben Amor, Mohamed Daoudi, A...
BMVC
2010
13 years 9 months ago
Discriminative Topics Modelling for Action Feature Selection and Recognition
This paper presents a framework for recognising realistic human actions captured from unconstrained environments. The novelties of this work lie in three aspects. First, we propos...
Matteo Bregonzio, Jian Li, Shaogang Gong, Tao Xian...
BMVC
2010
13 years 9 months ago
Graph-based Analysis of Textured Images for Hierarchical Segmentation
The Texture Fragmentation and Reconstruction (TFR) algorithm has been recently introduced [9] to address the problem of image segmentation by textural properties, based on a suita...
Raffaele Gaetano, Giuseppe Scarpa, Tamás Sz...
BMVC
2010
13 years 9 months ago
Recognizing human actions in still images: a study of bag-of-features and part-based representations
Recognition of human actions is usually addressed in the scope of video interpretation. Meanwhile, common human actions such as "reading a book", "playing a guitar&...
Vincent Delaitre, Ivan Laptev, Josef Sivic
BMVC
2010
13 years 9 months ago
On-line Adaption of Class-specific Codebooks for Instance Tracking
Off-line trained class-specific object detectors are designed to detect any instance of the class in a given image or video sequence. In the context of object tracking, however, o...
Juergen Gall, Nima Razavi, Luc J. Van Gool
BMVC
2010
13 years 9 months ago
A principled approach to remove false alarms by modelling the context of a face detector
In this article we present a new method to enhance object detection by removing false alarms in a principled way with few parameters. The method models the output of an object cla...
Cosmin Atanasoaei, Chris McCool, Sébastien ...
BMVC
2010
13 years 9 months ago
Evaluation of dimensionality reduction methods for image auto-annotation
Image auto-annotation is a challenging task in computer vision. The goal of this task is to predict multiple words for generic images automatically. Recent state-of-theart methods...
Hideki Nakayama, Tatsuya Harada, Yasuo Kuniyoshi
BMVC
2010
13 years 9 months ago
Weakly Supervised Object Recognition and Localization with Invariant High Order Features
High order features have been proposed to incorporate geometrical information into the "bag of feature" representation. We propose algorithms to perform fast weakly supe...
Yimeng Zhang, Tsuhan Chen
BMVC
2010
13 years 9 months ago
Weighted Local Bundle Adjustment and Application to Odometry and Visual SLAM Fusion
Local Bundle Adjustments were recently introduced for visual SLAM (Simultaneous Localization and Mapping). In Monocular Visual SLAM, the scale factor is not observable and the rec...
Alexandre Eudes, Sylvie Naudet-Collette, Maxime Lh...