检索结果-内蒙古大学图书馆

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yang, Fan Xiao, Liang Yang, Jingxiang Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing Peoples R China

ISBN: (纸本)9781509066315

Camera shake and target movement often leads to undesirable image blurring in videos. How to exploit spatial-temporal information of adjacent frames and reduce the processing time of deblurring are two major issues in video deblurring. In this paper, we propose a simple yet effective Fourier accumulation embedded 3D convolutional encoder-decoder network for video deblurring. Firstly, a 3D convolutional encoder-decoder module is constructed to extract multiscale spatial-temporal deep features and generate intermediate de-blurred frames with complementary information which is beneficial for the deblurring of each frame. Then we embed a Fourier accumulation module following the 3D convolutional encoder-decoder, the Fourier accumulation module could fuse intermediate deblurred frames with learned weights in Fourier domain and then produce shaper deblurred frames. Experimental results show that our method has competitive performance compared with other state-of-the-art methods.

关键词： video deblurring encoder-decoder 3D convolution Fourier accumulation

来源：评论

学校读者我要写书评

暂无评论

AlphaNet: An Attention Guided Deep Network for Automatic Image Matting

AlphaNet: An Attention Guided Deep Network for Automatic Ima...

引用

2nd IEEE International Conference on Omni-Iayer Intelligent Systems (IEEE COINS)

作者： Sharma, Rishab Deora, Rahul Vishvakarma, Anirudha Fynd Mumbai Maharashtra India

ISBN: (纸本)9781728163710

In this paper, we propose an end to end solution for image matting i.e high-precision extraction of foreground objects from natural images. Image matting and background detection can be achieved easily through chroma keying in a studio setting when the background is either pure green or blue. Nonetheless, image matting in natural scenes with complex and uneven depth backgrounds remains a tedious task that requires human intervention. To achieve complete automatic foreground extraction in natural scenes, we propose a method that assimilates semantic segmentation and deep image matting processes into a single network to generate detailed semantic mattes for image composition task. The contribution of our proposed method is two-fold, firstly it can be interpreted as a fully automated semantic image matting method and secondly as a refinement of existing semantic segmentation models. We propose a novel model architecture as a combination of segmentation and matting that unifies the function of upsampling and downsampling operators with the notion of attention. As shown in our work, attention guided downsampling and upsampling can extract high-quality boundary details, unlike other normal downsampling and upsampling techniques. For achieving the same, we utilized an attention guided encoder-decoder framework which does unsupervised learning for generating an attention map adaptively from the data to serve and direct the upsampling and downsampling operators. We also construct a fashion e-commerce focused dataset with high-quality alpha mattes to facilitate the training and evaluation for image matting.

关键词： matting background removal encoder-decoder fully-automated trimap image matting deep image matting

来源：评论

学校读者我要写书评

暂无评论

Attention based Multi-Modal New Product Sales Time-series Forecasting 20

Attention based Multi-Modal New Product Sales Time-series Fo...

引用

26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)

作者： Ekambaram, Vijay Manglik, Kushagra Mukherjee, Sumanta Sajja, Surya Shravan Kumar Dwivedi, Satyam Raykar, Vikas IBM Res Yorktown Hts NY 10598 USA

ISBN: (纸本)9781450379984

Trend driven retail industries such as fashion, launch substantial new products every season. In such a scenario, an accurate demand forecast for these newly launched products is vital for efficient downstream supply chain planning like assortment planning and stock allocation. While classical time-series forecasting algorithms can be used for existing products to forecast the sales, new products do not have any historical time-series data to base the forecast on. In this paper, we propose and empirically evaluate several novel attention-based multi-modal encoder-decoder models to forecast the sales for a new product purely based on product images, any available product attributes and also external factors like holidays, events, weather, and discount. We experimentally validate our approaches on a large fashion dataset and report the improvements in achieved accuracy and enhanced model interpretability as compared to existing k-nearest neighbor based baseline approaches.

关键词： New product sales forecast Image based forecasting Multi-modal embeddings RNNs encoder-decoder Attention

来源：评论

学校读者我要写书评

暂无评论

Controllable neural text-to-speech synthesis using intuitive prosodic features 21

Controllable neural text-to-speech synthesis using intuitive...

引用

Interspeech Conference

作者： Raitio, Tuomo Rasipuram, Ramya Castellani, Dan Apple Cupertino CA 95014 USA

ISBN: (纸本)9781713820697

Modern neural text-to-speech (TTS) synthesis can generate speech that is indistinguishable from natural speech. However, the prosody of generated utterances often represents the average prosodic style of the database instead of having wide prosodic variation. Moreover, the generated prosody is solely defined by the input text, which does not allow for different styles for the same sentence. In this work, we train a sequence-to-sequence neural network conditioned on acoustic speech features to learn a latent prosody space with intuitive and meaningful dimensions. Experiments show that a model conditioned on sentence wise pitch, pitch range, phone duration, energy, and spectral tilt can effectively control each prosodic dimension and generate a wide variety of speaking styles, while maintaining similar mean opinion score (4:23) to our Tacotron baseline (4:26).

关键词： Prosody control end-to-end neural speech synthesis sequence-to-sequence attention encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Semantic Features Aided Multi-Scale Reconstruction of Inter-Modality Magnetic Resonance Images 33

Semantic Features Aided Multi-Scale Reconstruction of Inter-...

引用

33rd IEEE International Symposium on Computer-Based Medical Systems (CBMS)

作者： Srinivasan, Preethi Kaur, Prabhjot Nigam, Aditya Bhavsar, Arnav Indian Inst Technol Sch Comp & Elect Engn Mandi Himachal Prades India

ISBN: (纸本)9781728194295

Long acquisition time (AQT) due to series acquisition of multi-modality MR images (especially T2 weighted images (T2WI) with longer AQT), though beneficial for disease diagnosis, is practically undesirable. We propose a novel deep network based solution to reconstruct T2W images from T1W images (T1WI) using an encoder-decoder architecture. The proposed learning is aided with semantic features by using multi-channel input with intensity values and gradient of image in two orthogonal directions. A reconstruction module (RM) augmenting the network along with a domain adaptation module (DAM) which is an encoder-decoder model built-in with sharp bottleneck module (SBM) is trained via modular training. The proposed network significantly reduces the total AQT with negligible qualitative artifacts and quantitative loss (reconstructs one volume in similar to 1 second). The testing is done on publicly available dataset with real MR images, and the proposed network shows (similar to 1dB) increase in PSNR over SOTA.

关键词： Inter-modality Transformation-Learning encoder-decoder T1-T2 Reconstruction

来源：评论

学校读者我要写书评

暂无评论

Machine Translation Using Improved Attention-based Transformer with Hybrid Input 6

Machine Translation Using Improved Attention-based Transform...

引用

6th International Conference on Web Research (ICWR)

作者： Abrishami, Mahsa Rashti, Mohammad Javad Naderan, Marjan Shahid Chamran Univ Ahvaz Dept Comp Engn Ahvaz Iran

ISBN: (纸本)9781728110516

Machine Translation (MT) refers to the automated software-based translation of natural language text. The embedded complexities and incompatibilities of natural languages have made MT a daunting task facing numerous challenges, especially when it is to be compared to a manual translation. With the emergence of deep-learning AI approaches, the Neural Machine Translation (NMT) has pushed MT results closer to human expectations. One of the newest deep learning approaches is the sequence-to-sequence approach based on Recurrent Neural Networks (RNN), complex convolutions, and transformers, and employing encoders/decoder pairs. In this study, an attention-based deep learning architecture is proposed for MT, with all layers focused exclusively on multi-head attention and based on a transformer that includes multi-layer encoders/decoders. The main contributions of the proposed model lie in the weighted combination of layers' primary input and output of the previous layers, feeding into the next layer. This mechanism results in a more accurate transformation compared to non-hybrid inputs. The model is evaluated using two datasets for German/English translation, the WMT'14 dataset for training, and the newstest' 2012 dataset for testing. The experiments are run on GPU-equipped Google Colab instances and the results show an accuracy of 36.7 BLEU, a 5% improvement over the previous work without the hybrid-input technique.

关键词： Neural Machine Translation Self-Attention Multi-Head Attention encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

End-to-End Neural Transformer Based Spoken Language Understanding 21

End-to-End Neural Transformer Based Spoken Language Understa...

引用

Interspeech Conference

作者： Radfar, Martin Mouchtaris, Athanasios Kunzmann, Siegfried Amazon Alexa Machine Learning Seattle WA 98109 USA

ISBN: (纸本)9781713820697

Spoken language understanding (SLU) refers to the process of inferring the semantic information from audio signals. While the neural transformers consistently deliver the best performance among the state-of-the-art neural architectures in field of natural language processing (NLP), their merits in a closely related field, i.e., spoken language understanding (SLU) have not been investigated. In this paper, we introduce an end-to-end neural transformer-based SLU model that can predict the variable-length domain, intent, and slots vectors embedded in an audio signal with no intermediate token prediction architecture. This new architecture leverages the self-attention mechanism by which the audio signal is transformed to various subsubspaces allowing to extract the semantic context implied by an utterance. Our end-to-end transformer SLU predicts the domains, intents and slots in the Fluent Speech Commands dataset with accuracy equal to 98.1 %, 99.6 %, and 99.6 %, respectively and outperforms the SLU models that leverage a combination of recurrent and convolutional neural networks by 1.4 % while the size of our model is 25% smaller than that of these architectures. Additionally, due to independent sub-space projections in the self-attention layer, the model is highly parallelizable which makes it a good candidate for on-device SLU.

关键词： Spoken language understanding sequence-to-sequence neural transformer encoder-decoder domain-intent-slot

来源：评论

学校读者我要写书评

暂无评论

Automatic Recognition of Identification Schemes for IoT Identifiers via Sequence-to-Sequence Model 39

Automatic Recognition of Identification Schemes for IoT Iden...

引用

39th IEEE International Performance Computing and Communications Conference (IPCCC)

作者： Li, Xiaotao You, Shujuan Chen, Wai China Mobile Res Inst Beijing Peoples R China

ISBN: (纸本)9781728198293

In Internet of Things (IoT), each object requires a unique identifier to identify itself and index its detailed profile to support mutual recognitions among multiple objects. However, existing IoT identifiers belonging to different identification schemes are heterogeneous from each other, which create a great challenge for the applications that need to resolve the heterogeneous identifiers. To address this challenge, we propose an algorithm to automatically recognize the heterogeneous identification schemes used by various IoT identifiers, based on a sequence-to-sequence (seq2seq) model consisting of an encoder and a decoder. The encoder uses one Long Short-Term Memory (LSTM) to map the identifier sequence to a vector of fixed dimensionality, and the decoder uses another LSTM to unfold the vector into a target sequence representing the identification scheme of this identifier. To evaluate our algorithm, we create a new dataset named ID-20 with 20 categories of IoT identifiers and conduct experiments on it. The results demonstrate the superiority of our algorithm against other state-of-the-art methods, with an identifier recognition accuracy of up to 94.57%.

关键词： IoT heterogeneous identifiers sequence-to-sequence encoder-decoder automatic recognition

来源：评论

学校读者我要写书评

暂无评论

NLP Summarization : Abstractive Neural Headline Generation Over A News Articles Corpus 4

NLP Summarization : Abstractive Neural Headline Generation O...

引用

4th International Conference on Intelligent Computing in Data Sciences (ICDS)

作者： Erraki, Mehdi Youssfi, Mohamed Daaif, Abdelaziz Bouattane, Omar Univ Hassan 2 ENSET Mohammedia SSDIA Lab Casablanca Morocco

ISBN: (纸本)9781728180847

Most of NLP research fields (Translation, Classification, Dialogue Systems.) have been revolutionized by the rise of deep learning methods, which rely on the new dense and low-dimensional feature representation. We present in this article the basic training techniques of Word Embeddings as well as the recent works on Abstractive Neural Summarizers. We also introduce our trained French Word Embeddings, further used as the embedding layer to implement our baseline French Neural Summarizer for the headline generation task, using the RNN (Recurrent Neural Network) encoder-decoder architecture.

关键词： word embeddings summarization headline generation recurrent neural networks seq2seq encoder-decoder attention pointer reinforcement learning big data

来源：评论

学校读者我要写书评

暂无评论

Recurrent neural network for abstractive summarization of documents

引用

JOURNAL OF DISCRETE MATHEMATICAL SCIENCES & CRYPTOGRAPHY 2020年第1期23卷 65-72页

作者： Bansal, Neha Sharma, Arun Singh, R. K. Indira Gandhi Delhi Tech Univ Women Dept Informat Technol Delhi 110006 India

Automatic Text Summarization is the process which utilizes machine power to process large paragraphs in order to create brief and refined summary. Text summarization can be classified into two classes viz. extractive and abstractive. The pith of the extractive is a choice issue, which consequently picks significant sentences from the input content as indicated by different assessment measures;while abstractive requires a profound semantic and talk comprehension of the content to create a base rephrased summary. Deep learning gives an achievable system to create an abstractive summarizer. Intermittent neural system Recurrent Neural Network (RNN) based arrangement to-grouping number of layers for learning has made as rounding progress in different natural language processing errands. The proposed model principally comprises of two sections - an encoder and a decoder - each one of which is a Recurrent Neural Network (RNN). ROUGE assessment metric is utilized to assess the likeness between real feature and anticipated feature.

关键词： Abstractive Summarization RNN encoder-decoder Sequential Model

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：