We propose a novel hierarchical sparse coding algorithm with spatial pooling and multi-feature fusion, to construct the low-level visual primitives, e.g., local image patches or region-s, into high-level visual phrases, e.g., image patterns. In the first layer we learn the sparse codes for the visual primitives and then pass them into the second layer by spatial pooling and multi-feature fusion. In the second layer we further learn the sparse codes for the visual phrases. In order to obtain the high-quality representations for visual phrases, our pro-posed algorithm iteratively optimizes over the two-layer s-parse codes, as well as the two-layer codebooks. Since we have explored both the spatial and multi-feature contextual information, mor...
Bag-of-Words lies at a heart of modern object category recognition systems. After descriptors are ex...
The recent advances in sparse coding and dictionary learning have shown extremely good performances ...
In this thesis a new type of representation for medium level vision operations is explored. We focus...
In this paper, we propose a new unsupervised feature learning framework, namely Deep Sparse Coding (...
Most recently the Bag-of-Features (BoF) representation has been well advocated for image search and ...
This paper presents a deep learning model of building up hierarchical image represen-tation. Each la...
A novel representation of images for image retrieval is in-troduced in this paper, by using a new ty...
Abstract In the face of huge amounts of image data, how to let the computer simulate human cognition...
Recent coding-based image classification systems generally adopt a key step of s-patial pooling oper...
Nonlinear encoding of SIFT features has recently shown good promise in image classification. This sc...
In this paper, we propose a hybrid architecture that combines the image modeling strengths of the Ba...
Nonlinear encoding of SIFT features has recently shown good promise in image classification. This sc...
This paper seeks to combine dictionary learning and hierarchical image representation in a principle...
International audienceThe purpose of this paper is segmenting objects in an image and assigning a pr...
© 2016 Elsevier Ltd The human visual system proves expert in discovering patterns in both global and...
Bag-of-Words lies at a heart of modern object category recognition systems. After descriptors are ex...
The recent advances in sparse coding and dictionary learning have shown extremely good performances ...
In this thesis a new type of representation for medium level vision operations is explored. We focus...
In this paper, we propose a new unsupervised feature learning framework, namely Deep Sparse Coding (...
Most recently the Bag-of-Features (BoF) representation has been well advocated for image search and ...
This paper presents a deep learning model of building up hierarchical image represen-tation. Each la...
A novel representation of images for image retrieval is in-troduced in this paper, by using a new ty...
Abstract In the face of huge amounts of image data, how to let the computer simulate human cognition...
Recent coding-based image classification systems generally adopt a key step of s-patial pooling oper...
Nonlinear encoding of SIFT features has recently shown good promise in image classification. This sc...
In this paper, we propose a hybrid architecture that combines the image modeling strengths of the Ba...
Nonlinear encoding of SIFT features has recently shown good promise in image classification. This sc...
This paper seeks to combine dictionary learning and hierarchical image representation in a principle...
International audienceThe purpose of this paper is segmenting objects in an image and assigning a pr...
© 2016 Elsevier Ltd The human visual system proves expert in discovering patterns in both global and...
Bag-of-Words lies at a heart of modern object category recognition systems. After descriptors are ex...
The recent advances in sparse coding and dictionary learning have shown extremely good performances ...
In this thesis a new type of representation for medium level vision operations is explored. We focus...