Xiyang Dai

  • Citations Per Year
Learn More
Polymerization of glycinamide-conjugated monomer alone in concentrated aqueous solution enables facile formation of a mechanically strong and a highly stable supramolecular polymer (SP) hydrogel because of the cooperatively hydrogen-bonded crosslinking and strengthening effect from dual amide motifs. This SP hydrogel exhibits thermoplastic processability,(More)
Deep networks have shown impressive performance on many computer vision tasks. Recently, deep convolutional neural networks (CNNs) have been used to learn discriminative texture representations. One of the most successful approaches is Bilinear CNN model that explicitly captures the second order statistics within deep features. However, these networks cut(More)
In this year’s competition, we use Temporal Context Network (TCN) for precise temporal localization of human activities. To improve performance for the metric used for evaluating proposals (i.e. area under the Average Recall vs. Average Number of Proposals per Video (AR-AN) curve with 100 proposals), we study the influence of two major hyper-parameters: the(More)
Fine-grained classification of objects such as vehicles, natural objects and other classes is an important problem in visual recognition. It is a challenging task because small and localized differences between similar looking objects indicate the specific fine-grained label. At the same time, accurate classification needs to discount spurious changes in(More)
Sparse representations have been successfully applied to signal processing, computer vision and machine learning. Currently there is a trend to learn sparse models directly on structure data, such as region covariance. However, such methods when combined with region covariance often require complex computation. We present an approach to transform a(More)
We present a Temporal Context Network (TCN) for precise temporal localization of human activities. Similar to the Faster-RCNN architecture, proposals are placed at equal intervals in a video which span multiple temporal scales. We propose a novel representation for ranking these proposals. Since pooling features only inside a segment is not sufficient to(More)
  • 1