Add to ORKGWe present a novel algorithm for image classification that is targeted to capture class variability. A single model is often not sufficient to represent a category since categories can vary from large semantic classes to fine-grained sub-categories. Instead, we develop a representation based on discovering visually similar sub-categories within a given class. We introduce a novel Clustered Exemplar SVM clas-sifier which incorporates data-driven and exemplar focused discovery. Semi-supervised learning is employed for training each C-eSVM classifier. We evaluate our approach on two datasets and demonstrate the efficacy of our method over standard Exemplar SVM. Index Terms — visual recognition, sub-categories 1
Ensembles of Exemplar-SVMs have been introduced as a framework for Object Detection but have rapidly...
Sub-semantic space Structure regularized SVM Sparse coding a b s t r a c t Due to the semantic gap, ...
Recent works in object recognition often use visual words, i.e. vector quantized local descriptors e...
Recognizing and reasoning about the objects found in an image is one of the key problems in computer...
Recognizing and reasoning about the objects found in an image is one of the key problems in computer...
Ensembles of Exemplar-SVMs have been used for a wide variety of tasks, such as object detection, seg...
Ensembles of Exemplar-SVMs have been used for a wide variety of tasks, such as object detection, seg...
Ensembles of Exemplar-SVMs have been used for a wide variety of tasks, such as object detection, seg...
Ensembles of Exemplar-SVMs have been used for a wide variety of tasks, such as object detection, seg...
Computer vision tasks are traditionally defined and eval-uated using semantic categories. However, i...
Computer vision tasks are traditionally defined and eval-uated using semantic categories. However, i...
Computer vision tasks are traditionally defined and eval-uated using semantic categories. However, i...
Computer vision tasks are traditionally defined and eval-uated using semantic categories. However, i...
Ensembles of Exemplar-SVMs have been introduced as a framework for Object Detection but have rapidly...
Computer vision tasks are traditionally defined and eval-uated using semantic categories. However, i...
Ensembles of Exemplar-SVMs have been introduced as a framework for Object Detection but have rapidly...
Sub-semantic space Structure regularized SVM Sparse coding a b s t r a c t Due to the semantic gap, ...
Recent works in object recognition often use visual words, i.e. vector quantized local descriptors e...
Recognizing and reasoning about the objects found in an image is one of the key problems in computer...
Recognizing and reasoning about the objects found in an image is one of the key problems in computer...
Ensembles of Exemplar-SVMs have been used for a wide variety of tasks, such as object detection, seg...
Ensembles of Exemplar-SVMs have been used for a wide variety of tasks, such as object detection, seg...
Ensembles of Exemplar-SVMs have been used for a wide variety of tasks, such as object detection, seg...
Ensembles of Exemplar-SVMs have been used for a wide variety of tasks, such as object detection, seg...
Computer vision tasks are traditionally defined and eval-uated using semantic categories. However, i...
Computer vision tasks are traditionally defined and eval-uated using semantic categories. However, i...
Computer vision tasks are traditionally defined and eval-uated using semantic categories. However, i...
Computer vision tasks are traditionally defined and eval-uated using semantic categories. However, i...
Ensembles of Exemplar-SVMs have been introduced as a framework for Object Detection but have rapidly...
Computer vision tasks are traditionally defined and eval-uated using semantic categories. However, i...
Ensembles of Exemplar-SVMs have been introduced as a framework for Object Detection but have rapidly...
Sub-semantic space Structure regularized SVM Sparse coding a b s t r a c t Due to the semantic gap, ...
Recent works in object recognition often use visual words, i.e. vector quantized local descriptors e...