Learn More
This paper attacks the challenging problem of cross-media retrieval. That is, given an image find the text best describing its content, or the other way around. Different from existing works, which either rely on a joint space, or a text space, we propose to perform cross-media retrieval in a visual space only. We contribute Word2VisualVec, a deep neural(More)
The expression status of CD74 in breast cancer stem cells and its clinical implications was evaluated in order to lay a foundation for managing breast cancer. Five hundred and eighty breast cancer specimens were enrolled in the study. The relationship between the CD74 protein and clinicopathological parameters as well as prognosis was subsequently(More)
  • Jianfeng Dong
  • 2010
Network security situation evaluation and prediction is a new technology to monitor network security, and it is one of hot research domains in information security. The research situation of network security situation evaluation and prediction all over the world is analyzed. A network security situation evaluation and prediction model based on grey theory(More)
How to estimate cross-media relevance between a given query and an unlabeled image is a key question in the MSR-Bing Image Retrieval Challenge. We answer the question by proposing cross-media relevance fusion, a conceptually simple framework that exploits the power of individual methods for cross-media relevance estimation. Four base cross-media relevance(More)
A T CP –T CL model is established to describe the relationship between the thickness of the corrosion-filled paste (CP) and that of the corrosion layer (CL). This model can describe the phenomenon that the corrosion filling in the concrete pores and accumulating at the steel/concrete interface occur synchronously. Based on the T CP –T CL model, a(More)
This paper describes our solution for the MSR Video to Language Challenge. We start from the popular ConvNet + LSTM model, which we extend with two novel modules. One is early embedding, which enriches the current low-level input to LSTM by tag embeddings. The other is late reranking, for re-scoring generated sentences in terms of their relevance to a(More)
Convolutional neural networks (CNNs) have shown their power on many computer vision tasks. However, there are still some limitations, including their dependency to large scale labeled training data and sensitivity to weight initial-ization. In this paper, we try to address these two problems by proposing a simple yet powerful CNN based denoising(More)
This paper presents a novel method of constructing a tourism e-commerce platform based on semantic web services. In order to solve the puzzles of web services discovery, system adaptability, automatically assembling and calling caused by bad system semantic interoperability in tourism e-commerce based on traditional web services, we construct a novel(More)