Sciweavers

CVPR
2008
IEEE
14 years 12 months ago
Spatio-temporal Saliency detection using phase spectrum of quaternion fourier transform
Salient areas in natural scenes are generally regarded as the candidates of attention focus in human eyes, which is the key stage in object detection. In computer vision, many mod...
Chenlei Guo, Qi Ma, Liming Zhang
CVPR
2008
IEEE
14 years 12 months ago
High-arity interactions, polyhedral relaxations, and cutting plane algorithm for soft constraint optimisation (MAP-MRF)
LP relaxation approach to soft constraint optimisation (i.e. MAP-MRF) has been mostly considered only for binary problems. We present its generalisation to n-ary problems, includi...
Tomás Werner
CVPR
2008
IEEE
14 years 12 months ago
Background subtraction in highly dynamic scenes
Vijay Mahadevan, Nuno Vasconcelos
CVPR
2008
IEEE
14 years 12 months ago
Recognizing human actions using multiple features
In this paper, we propose a framework that fuses multiple features for improved action recognition in videos. The fusion of multiple features is important for recognizing actions ...
Jingen Liu, Saad Ali, Mubarak Shah
CVPR
2008
IEEE
14 years 12 months ago
Recovering consistent video depth maps via bundle optimization
Guofeng Zhang, Jiaya Jia, Tien-Tsin Wong, Hujun Ba...
CVPR
2008
IEEE
14 years 12 months ago
Sparsity, redundancy and optimal image support towards knowledge-based segmentation
In this paper, we propose a novel approach to model shape variations. It encodes sparsity, exploits geometric redundancy, and accounts for the different degrees of local variation...
Salma Essafi, Georg Langs, Nikos Paragios
CVPR
2008
IEEE
14 years 12 months ago
Discovering class specific composite features through discriminative sampling with Swendsen-Wang Cut
This paper proposes a novel approach to discover a set of class specific "composite features" as the feature pool for the detection and classification of complex objects...
Feng Han, Ying Shan, Harpreet S. Sawhney, Rakesh K...
CVPR
2008
IEEE
14 years 12 months ago
Dynamic visual category learning
Dynamic visual category learning calls for efficient adaptation as new training images become available or new categories are defined, existing training images or categories becom...
Tom Yeh, Trevor Darrell
CVPR
2008
IEEE
14 years 12 months ago
Scale invariance without scale selection
In this work we construct scale invariant descriptors (SIDs) without requiring the estimation of image scale; we thereby avoid scale selection which is often unreliable. Our start...
Iasonas Kokkinos, Alan L. Yuille
CVPR
2008
IEEE
14 years 12 months ago
Radiometric calibration with illumination change for outdoor scene analysis
The images of an outdoor scene collected over time are valuable in studying the scene appearance variation which can lead to novel applications and help enhance existing methods t...
Seon Joo Kim, Jan-Michael Frahm, Marc Pollefeys