Results 1 - 10 of 404

Designing Category-Level Attributes for Discriminative Visual Recognition ∗

by Felix X. Yu, Liangliang Cao, Rogerio S. Feris, John R. Smith, Shih-fu Chang
"... Attribute-based representation has shown great promises for visual recognition due to its intuitive interpretation and cross-category generalization property. However, human efforts are usually involved in the attribute designing process, making the representation costly to obtain. In this paper, we ..."
Abstract - Cited by 25 (1 self) - Add to MetaCart
, we propose a novel formulation to automatically design discriminative “category-level attributes”, which can be efficiently encoded by a compact category-attribute matrix. The formulation allows us to achieve intuitive and critical design criteria (category-separability, learnability) in a principled

Designing Category-Level Attributes for Discriminative Visual Recognition∗

by unknown authors
"... Attribute-based representation has shown great promis-es for visual recognition due to its intuitive interpretation and cross-category generalization property. However, hu-man efforts are usually involved in the attribute designing process, making the representation costly to obtain. In this paper, ..."
Abstract - Add to MetaCart
, we propose a novel formulation to automatically de-sign discriminative “category-level attributes”, which can be efficiently encoded by a compact category-attribute ma-trix. The formulation allows us to achieve intuitive and crit-ical design criteria (category-separability, learnability) in a

Designing Category-Level Attributes for Discriminative Visual Recognition∗

by unknown authors
"... Attribute-based representation has shown great promises for visual recognition due to its intuitive interpretation and cross-category generalization property. However, human efforts are usually involved in the attribute designing pro-cess, making the representation costly to obtain. In this paper, w ..."
Abstract - Add to MetaCart
, we propose a novel formulation to automatically de-sign discriminative “category-level attributes”, which can be efficiently encoded by a compact category-attribute ma-trix. The formulation allows us to achieve intuitive and crit-ical design criteria (category-separability, learnability) in a

Additional remarks on designing category-level attributes for discriminative visual recognition

by Felix X. Yu, Liangliang Cao, Rogerio S. Feris, John R. Smith, Shih-fu Chang , 2013
"... This is the supplementary material for Designing Category-Level Attributes for Discriminative Visual Recognition [3]. We first provide an overview of the proposed approach in Section 1. The proof of the theorem is shown in Section 2. Additional remarks of the proposed attribute design algorithm are ..."
Abstract - Cited by 3 (1 self) - Add to MetaCart
This is the supplementary material for Designing Category-Level Attributes for Discriminative Visual Recognition [3]. We first provide an overview of the proposed approach in Section 1. The proof of the theorem is shown in Section 2. Additional remarks of the proposed attribute design algorithm

Additional Remarks on Designing Category-Level Attributes for Discriminative Visual Recognition∗

by unknown authors
"... This is the supplementary material for Designing Category-Level Attributes for Dis-criminative Visual Recognition [3]. We first provide an overview of the proposed ap-proach in Section 1. The proof of the theorem is shown in Section 2. Additional remarks of the proposed attribute design algorithm ar ..."
Abstract - Add to MetaCart
This is the supplementary material for Designing Category-Level Attributes for Dis-criminative Visual Recognition [3]. We first provide an overview of the proposed ap-proach in Section 1. The proof of the theorem is shown in Section 2. Additional remarks of the proposed attribute design algorithm

Evaluating Color Descriptors for Object and Scene Recognition

by Koen E. A. van de Sande, Theo Gevers, Cees G. M. Snoek , 2010
"... Image category recognition is important to access visual information on the level of objects and scene types. So far, intensity-based descriptors have been widely used for feature extraction at salient points. To increase illumination invariance and discriminative power, color descriptors have been ..."
Abstract - Cited by 423 (33 self) - Add to MetaCart
Image category recognition is important to access visual information on the level of objects and scene types. So far, intensity-based descriptors have been widely used for feature extraction at salient points. To increase illumination invariance and discriminative power, color descriptors have

Describing objects by their attributes

by Ali Farhadi, Ian Endres, Derek Hoiem, David Forsyth - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR , 2009
"... We propose to shift the goal of recognition from naming to describing. Doing so allows us not only to name familiar objects, but also: to report unusual aspects of a familiar object (“spotty dog”, not just “dog”); to say something about unfamiliar objects (“hairy and four-legged”, not just “unknown” ..."
Abstract - Cited by 347 (17 self) - Add to MetaCart
”); and to learn how to recognize new objects with few or no visual examples. Rather than focusing on identity assignment, we make inferring attributes the core problem of recognition. These attributes can be semantic (“spotty”) or discriminative (“dogs have it but sheep do not”). Learning attributes presents a

Understanding Convolutional Neural Networks in Terms of Category-level Attributes

by Makoto Ozeki, Takayuki Okatani
"... Abstract. It has been recently reported that convolutional neural net-works (CNNs) show good performances in many image recognition tasks. They significantly outperform the previous approaches that are not based on neural networks particularly for object category recognition. These performances are ..."
Abstract - Add to MetaCart
such good representations. In this study, we conjecture that the learned representation can be interpreted as category-level attributes that have good properties. We conducted sev-eral experiments by using the dataset AwA (Animals with Attributes) and a CNN trained for ILSVRC-2012 in a fully supervised

Shape quantization and recognition with randomized trees

by Yali Amit, Donald Geman - NEURAL COMPUTATION , 1997
"... We explore a new approach to shape recognition based on a virtually infinite family of binary features ("queries") of the image data, designed to accommodate prior information about shape invariance and regularity. Each query corresponds to a spatial arrangement ofseveral local topographic ..."
Abstract - Cited by 263 (18 self) - Add to MetaCart
We explore a new approach to shape recognition based on a virtually infinite family of binary features ("queries") of the image data, designed to accommodate prior information about shape invariance and regularity. Each query corresponds to a spatial arrangement ofseveral local

On feature combination for multiclass object classification

by Peter Gehler, Sebastian Nowozin - IN ICCV
"... A key ingredient in the design of visual object classification systems is the identification of relevant class specific aspects while being robust to intra-class variations. While this is a necessity in order to generalize beyond a given set of training images, it is also a very difficult problem du ..."
Abstract - Cited by 259 (5 self) - Add to MetaCart
due to the high variability of visual appearance within each class. In the last years substantial performance gains on challenging benchmark datasets have been reported in the literature. This progress can be attributed to two developments: the design of highly discriminative and robust image features
Results 1 - 10 of 404