Results 191 to 200 of about 13,592 (226)
Some of the next articles are maybe not open access.
Bidirectional LSTM with Extended Input Context
2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP), 2018Long short-term memory (LSTM) unit has been widely used in speech recognition tasks, both for acoustic model and language model. For offline speech recognition task, bidirectional LSTM (BLSTM) is the state-of-the-art acoustic model. In this paper, we propose the BLSTM with extended input context (BLSTM-E), which achieves higher speech recognition ...
Gaofeng Cheng +3 more
openaire +1 more source
Attention augmentation with multi-residual in bidirectional LSTM
Neurocomputing, 2020Abstract Recurrent neural networks (RNNs) have been proven to be efficient in processing sequential data. However, the traditional RNNs have suffered from the gradient diminishing problem until the advent of Long Short-Term Memory (LSTM). However, LSTM is weak in capturing long-time dependency in sequential data due to the inadequacy of memory ...
Ye Wang 0006 +4 more
openaire +1 more source
Anomaly Detection Using Bidirectional LSTM
2020This paper presents an anomaly detection approach based on deep learning techniques. A bidirectional long-short-term memory (Bi-LSTM) was applied on the UNSW-NB15 dataset to detect the anomalies. UNSW-NB15 represents raw network packets that contains both the normal activities and anomalies.
Sarah Aljbali, Kaushik Roy
openaire +1 more source
Indoor Localization Using Bidirectional LSTM Networks
2021 13th International Conference on Advanced Computational Intelligence (ICACI), 2021Indoor localization witnessed the flourishing development in location based service for indoor environments. Regarding the availability of access points (AP) and its low cost for industry popularization, one of promising tool for localization is based on WiFi fingerprints.
Dong Pang, Xinyi Le
openaire +1 more source
Bidirectional LSTM for Author Gender Identification
2018Author profiling consists in inferring the authors’ gender, age, native language, dialects or personality by examining his/her written text. This important task is a very active research area because of its utility in crime, marketing and business.
Bassem Bsir, Mounir Zrigui
openaire +1 more source
Improvement of image description using bidirectional LSTM
International Journal of Multimedia Information Retrieval, 2018As a high-level technique, automatic image description combines linguistic and visual information in order to extract an appropriate caption for an image. In this paper, we have proposed a method based on a recurrent neural network to synthesize descriptions in multimodal space.
Vahid Chahkandi +2 more
openaire +1 more source
Bidirectional Convolutional LSTM for the Detection of Violence in Videos
2019The field of action recognition has gained tremendous traction in recent years. A subset of this, detection of violent activity in videos, is of great importance, particularly in unmanned surveillance or crowd footage videos. In this work, we explore this problem on three standard benchmarks widely used for violence detection: the Hockey Fights, Movies,
Alex Hanson 0002 +3 more
openaire +1 more source
Describing Video With Attention-Based Bidirectional LSTM
IEEE Transactions on Cybernetics, 2019Video captioning has been attracting broad research attention in the multimedia community. However, most existing approaches heavily rely on static visual information or partially capture the local temporal knowledge (e.g., within 16 frames), thus hardly describing motions accurately from a global view.
Yi Bin +5 more
openaire +2 more sources
Online News Emotion Prediction with Bidirectional LSTM
2016Recent years have brought a significant growth in the volume of user generated data. Sentiment analysis is a crucial tool in the mining of such data, which is of great value for both improving particular services and assisting organizations’ decision making process. Existing research focuses on identifying sentiment polarity on subjective text, such as
Xue Zhao 0001 +4 more
openaire +1 more source
Integrating Bidirectional LSTM with Inception for Text Classification
2017 4th IAPR Asian Conference on Pattern Recognition (ACPR), 2017A novel neural network architecture, BLSTM-Inception v1, is proposed for text classification. It mainly consists of the BLSTM-Inception module, which has two parts, and a global max pooling layer. In the first part, forward and backward sequences of hidden states of BLSTM are concatenated as double channels, rather than added as single channel.
Wei Jiang, Zhong Jin
openaire +1 more source