Heterogeneous feature machines for visual recognition

By Liangliang Cao, Jiebo Luo, Feng Liang, Thomas S. Huang. 2009

93 citations recorded by the source corpus.

With the recent efforts made by computer vision researchers, more and more types of features have been designed to describe various aspects of visual characteristics. Modeling such heterogeneous features has become an increasingly critical issue. In this paper, we propose a machinery called the Heterogeneous Feature Machine (HFM) to effectively solve visual recognition tasks in need of multiple types of features. Our HFM builds a kernel logistic regression model based on similarities that combine different features and distance metrics. Different from existing approaches that use a linear weighting scheme to combine different features, HFM does not require the weights to remain the same across different samples, and therefore can effectively handle features of different types with different metrics. To prevent the model from overfitting, we employ the so-called group LASSO constraints to reduce model complexity. In addition, we propose a fast algorithm based on co-ordinate gradient descent to efficiently train a HFM. The power of the proposed scheme is demonstrated across a wide variety of visual recognition tasks including scene, event and action recognition.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. K. Müller
2. Wojciech Samek
3. Luc Van Gool
4. Xiaogang Wang
5. Dacheng Tao
6. Yi Yang
7. Yu-Gang Jiang
8. Zuxuan Wu

Citations in the corpus

• Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks (2015, methodology): “works, multiple kernel learning (MKL) [23] was adopted to estimate the fusion weights [24], [25].”
• Jointly Learning Heterogeneous Features for RGB-D Activity Recognition (2015, methodology): “HFM [4] 84.44 SVM 88.32 MPCCA [3] 90.76 MTDA [51] 92.07 JOULE 94.24”
• Insights from Classifying Visual Concepts with Multiple Kernel Learning (2011, background): “Further competitors include, for example, [31], who use logistic regression as base criterion; their approach results in a number of optimization parameters equal to the number of samples times the number of input features.”
• A Survey on Object Detection in Optical Remote Sensing Images (2016, unknown): “Furthermore, some non-linear feature fusion methods were also proposed such as heterogeneous feature machines (HFM) (Cao et al., 2009) and sparse multimodal learning (SMML) approach (Wang et al., 2013).”