Sciweavers

376 search results - page 43 / 76
» Salient Frame Extraction for Structure from Motion
Sort
View
ICPR
2002
IEEE
14 years 8 months ago
A Bayesian Approach to Video Object Segmentation via Merging 3D Watershed Volumes
In this paper, we propose a Bayesian approach to video object segmentation. Our method consists of two stages. In the first stage, we partition the video data into a set of 3D wate...
Yi-Ping Hung, Yu-Pao Tsai, Chih-Chuan Lai
AMFG
2005
IEEE
162views Biometrics» more  AMFG 2005»
14 years 1 months ago
Facial Expression Representation Based on Timing Structures in Faces
Abstract. This paper presents a method for interpreting facial expressions based on temporal structures among partial movements in facial image sequences. To extract the structures...
Masahiro Nishiyama, Hiroaki Kawashima, Takatsugu H...
ISMAR
2007
IEEE
14 years 1 months ago
Feature Tracking for Mobile Augmented Reality Using Video Coder Motion Vectors
We propose a novel, low-complexity, tracking scheme that uses motion vectors directly from a video coder. We compare our tracking algorithm against ground truth data, and show tha...
Gabriel Takacs, Vijay Chandrasekhar, Bernd Girod, ...
ECCV
2010
Springer
14 years 27 days ago
Convolutional learning of spatio-temporal features
Abstract. We address the problem of learning good features for understanding video data. We introduce a model that learns latent representations of image sequences from pairs of su...
IROS
2009
IEEE
164views Robotics» more  IROS 2009»
14 years 2 months ago
Visual steering of UAV in unknown environments
— In this paper, we propose a novel approach for the visual navigation of unmanned aerial vehicles (UAV). In contrast to most available methods, a single perspective camera is us...
Chunrong Yuan, Fabian Recktenwald, Hanspeter A. Ma...