Sciweavers

702 search results - page 68 / 141
» Long Image Sequence Motion Analysis Using Polynomial Motion ...
Sort
View
ECCV
2010
Springer
15 years 8 months 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...
154
Voted
NIPS
2003
15 years 4 months ago
Factorization with Uncertainty and Missing Data: Exploiting Temporal Coherence
The problem of “Structure From Motion” is a central problem in vision: given the 2D locations of certain points we wish to recover the camera motion and the 3D coordinates of ...
Amit Gruber, Yair Weiss
94
Voted
BMVC
2001
15 years 5 months ago
Finding Paths in Video Sequences
This paper investigates the task of identifying frequently-used pathways from video sequences of natural outdoor scenes. Path models are adaptively learnt from the accumulation of...
Dimitrios Makris, Tim Ellis
ECCV
2008
Springer
16 years 5 months ago
Segmentation and Recognition Using Structure from Motion Point Clouds
We propose an algorithm for semantic segmentation based on 3D point clouds derived from ego-motion. We motivate five simple cues designed to model specific patterns of motion and 3...
Gabriel J. Brostow, Jamie Shotton, Julien Fauqueur...
130
Voted
FGR
2008
IEEE
269views Biometrics» more  FGR 2008»
15 years 10 months ago
Real-time facial expression recognition with illumination-corrected image sequences
We present a real-time user-independent computer vision system that processes a sequence of images of a front-facing human face and recognises a set of facial expressions at 30 fp...
He Li, José Miguel Buenaposada, Luis Baumel...