Learn More
In this paper, we propose a novel formulation for multi-feature clustering using minimax optimization. To find a consensus clustering result that is agreeable to all feature modalities, our objective is to find a universal feature embedding , which not only fits each individual feature modality well, but also unifies different feature modalities by(More)
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 regions , 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(More)
—The co-occurrence features are the composition of base features that have more discriminative power than individual base features. Although they show promising performance in visual recognition applications such as object, scene and action recognition, the discovery of optimal co-occurrence features is usually a computational demanding task. Unlike(More)
The co-occurrence features are the composition of base features that have more discriminative power than individual base features. Although they show promising performance in visual recognition applications such as object and scene recognition, the discovery of discriminative co-occurrence features is usually a computational demanding task. Unlike previous(More)
Local feature extraction, coding, pooling, and image classification are the four typical steps for the state-of-the-art visual recognition systems. Unlike previous work that treats feature pooling and image classification as separated steps, we propose to jointly learn the geometric pooling and image classi-fier by support tensor machine. Inspired by(More)
  • 1