Bingyuan Liu

Learn More
The discovery of key and distinctive parts is critical for scene parsing and understanding. However, it is a challenging problem due to the weakly supervised condition, i.e., no annotation for parts is available. To address above issues, we propose a unified framework for learning a representative and discriminative part model with deep convolutional(More)
In this paper, we describe the details of our participation in the ImageCLEF 2015 Scalable Image Annotation task. The task is to annotate and localize different concepts depicted in images. We propose a hybrid learning framework to solve the scalable annotation task, in which the supervised methods given limited annotated images and the searchbased(More)
Recently, many deep networks are proposed to learn hierarchical image representation to replace traditional hand-designed features. To enhance the ability of the generative model to tackle discriminative computer vision tasks (e.g. image classification), we propose a hierarchical deconvolutional network with two biologically inspired properties(More)
Deep learning models have gained significant interest as a way of building hierarchical image representation. However, current models still perform far behind human vision system because of the lack of selective property, the lack of high-level guidance for learning and the weakness to learn from few examples. To address these problems, we propose a(More)
The bag of feature model is one of the most successful model to represent an image for classification task. However, the discrimination loss in the local appearance coding and the lack of spatial information hinder its performance. To address these problems, we propose a deep appearance and spatial coding model to build more optimal image representation for(More)
The bag of visual words (BoW) model is one of the most successful model in image classification task. However, the major problem of the BoW model lies in the determination of visual words, which consists of codebook training and feature encoding phases. The traditional K-means and hard-assignment method completely ignore the structure of the local feature(More)
Use of ICT (Information and Communication Technology) or the computer communication using electronic messaging has increased tremendously in recent years. Also the modern networks that support ICT are robust, i.e., its failure due to links, routing protocols, congestion etc is rare and as a result, the estimation of the overall reliability of the(More)
  • 1