Bidirectional LSTM-CRF Models for Sequence Tagging
- Zhiheng Huang, W. Xu, Kai Yu
- Computer ScienceArXiv
- 9 August 2015
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)
- Junhua Mao, W. Xu, Yi Yang, Jiang Wang, A. Yuille
- Computer ScienceInternational Conference on Learning…
- 20 December 2014
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
- Haonan Yu, Jiang Wang, Zhiheng Huang, Yi Yang, W. Xu
- Computer ScienceComputer Vision and Pattern Recognition
- 26 October 2015
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
- Haoyuan Gao, Junhua Mao, Jie Zhou, Zhiheng Huang, Lei Wang, W. Xu
- Computer ScienceNIPS
- 21 May 2015
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.
Explain Images with Multimodal Recurrent Neural Networks
- Junhua Mao, W. Xu, Yi Yang, Jiang Wang, A. Yuille
- Computer ScienceArXiv
- 4 October 2014
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.
Taint-Enhanced Policy Enforcement: A Practical Approach to Defeat a Wide Range of Attacks
- W. Xu, S. Bhatkar, R. Sekar
- Computer ScienceUSENIX Security Symposium
- 31 July 2006
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.
Multicell MIMO Communications Relying on Intelligent Reflecting Surfaces
- Cunhua Pan, Hong Ren, L. Hanzo
- Computer ScienceIEEE Transactions on Wireless Communications
- 25 July 2019
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.
Performance evaluation of color correction approaches for automatic multi-view image and video stitching
- W. Xu, J. Mulligan
- Computer ScienceIEEE Computer Society Conference on Computer…
- 13 June 2010
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.
CFO: Conditional Focused Neural Question Answering with Large-scale Knowledge Bases
- Zihang Dai, Lei Li, W. Xu
- Computer ScienceAnnual Meeting of the Association for…
- 7 June 2016
This work proposes CFO, a Conditional Focused neural-network-based approach to answering factoid questions with knowledge bases that outperforms the current state of the art by an absolute margin of 11.8%.
Advances and challenges in log analysis
- A. Oliner, A. Ganapathi, W. Xu
- Computer ScienceCommunications of the ACM
- 1 December 2011
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.
...
...