• Publications
  • Influence
Bidirectional LSTM-CRF Models for Sequence Tagging
TLDR
This work is the first to apply a bidirectional LSTM CRF model to NLP benchmark sequence tagging data sets and it is shown that the BI-LSTM-CRF model can efficiently use both past and future input features thanks to a biddirectional L STM component.
Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
TLDR
The m-RNN model directly models the probability distribution of generating a word given previous words and an image, and achieves significant performance improvement over the state-of-the-art methods which directly optimize the ranking objective function for retrieval.
Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks
TLDR
An approach that exploits hierarchical Recurrent Neural Networks to tackle the video captioning problem, i.e., generating one or multiple sentences to describe a realistic video, significantly outperforms the current state-of-the-art methods.
Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question
TLDR
The mQA model, which is able to answer questions about the content of an image, is presented, which contains four components: a Long Short-Term Memory (LSTM), a Convolutional Neural Network (CNN), an LSTM for storing the linguistic context in an answer, and a fusing component to combine the information from the first three components and generate the answer.
Taint-Enhanced Policy Enforcement: A Practical Approach to Defeat a Wide Range of Attacks
TLDR
This paper presents a new approach to strengthen policy enforcement by augmenting security policies with information about the trustworthiness of data used in securitysensitive operations, and evaluated this technique using 9 available exploits involving several popular software packages containing the above types of vulnerabilities.
Explain Images with Multimodal Recurrent Neural Networks
TLDR
The m-RNN model directly models the probability distribution of generating a word given previous words and the image, and achieves significant performance improvement over the state-of-the-art methods which directly optimize the ranking objective function for retrieval.
Towards Optimal One Pass Large Scale Learning with Averaged Stochastic Gradient Descent
  • W. Xu
  • Computer Science
    ArXiv
  • 13 July 2011
TLDR
A finite sample analysis for the method of Polyak and Juditsky (1992) shows that it indeed usually takes a huge number of samples for ASGD to reach its asymptotic region for improperly chosen learning rate, and a simple way to properly set learning rate is proposed.
Advances and challenges in log analysis
TLDR
Logs contain a wealth of information to help manage systems and can be used to improve the quality and efficiency of systems and improve the user experience.
Performance evaluation of color correction approaches for automatic multi-view image and video stitching
  • W. Xu, J. Mulligan
  • Computer Science
    IEEE Computer Society Conference on Computer…
  • 13 June 2010
TLDR
Experimental results show that both parametric and non-parametric approaches have members that are effective at transferring colors, while parametric approaches are generally better than non- Parametric approaches in extendability.
Multicell MIMO Communications Relying on Intelligent Reflecting Surfaces
TLDR
This paper proposes to invoke an IRS at the cell boundary of multiple cells to assist the downlink transmission to cell-edge users, whilst mitigating the inter-cell interference, which is a crucial issue in multicell communication systems.
...
1
2
3
4
5
...