Related papers: Meta-DAN: towards an efficient prediction strategy…
Non-autoregressive translation (NAT) models achieve comparable performance and superior speed compared to auto-regressive translation (AT) models in the context of sentence-level machine translation (MT). However, their abilities are…
Scene text recognition with arbitrary shape is very challenging due to large variations in text shapes, fonts, colors, backgrounds, etc. Most state-of-the-art algorithms rectify the input image into the normalized image, then treat the…
Two factors have proven to be very important to the performance of semantic segmentation models: global context and multi-level semantics. However, generating features that capture both factors always leads to high computational complexity,…
We present a novel facial expression recognition network, called Distract your Attention Network (DAN). Our method is based on two key observations. Firstly, multiple classes share inherently similar underlying facial appearance, and their…
Convolutional neural networks (CNNs) have recently emerged as a popular building block for natural language processing (NLP). Despite their success, most existing CNN models employed in NLP share the same learned (and static) set of filters…
Recently, scene text detection has been a challenging task. Texts with arbitrary shape or large aspect ratio are usually hard to detect. Previous segmentation-based methods can describe curve text more accurately but suffer from over…
Creating meta-embeddings for better performance in language modelling has received attention lately, and methods based on concatenation or merely calculating the arithmetic mean of more than one separately trained embeddings to perform…
Considerable research attention has been paid to table detection by developing not only rule-based approaches reliant on hand-crafted heuristics but also deep learning approaches. Although recent studies successfully perform table detection…
Document-level Neural Machine Translation (DocNMT) has been proven crucial for handling discourse phenomena by introducing document-level context information. One of the most important directions is to input the whole document directly to…
This paper is a contribution towards interpretability of the deep learning models in different applications of time-series. We propose a temporal attention layer that is capable of selecting the relevant information to perform various…
In (Yang et al. 2016), a hierarchical attention network (HAN) is created for document classification. The attention layer can be used to visualize text influential in classifying the document, thereby explaining the model's prediction. We…
Training deep neural networks from scratch on natural language processing (NLP) tasks requires significant amount of manually labeled text corpus and substantial time to converge, which usually cannot be satisfied by the customers. In this…
Our objective is language-based search of large-scale image and video datasets. For this task, the approach that consists of independently mapping text and vision to a joint embedding space, a.k.a. dual encoders, is attractive as retrieval…
Attention is typically used to select informative sub-phrases that are used for prediction. This paper investigates the novel use of attention as a form of feature augmentation, i.e, casted attention. We propose Multi-Cast Attention…
Ever since their conception, Transformers have taken over traditional sequence models in many tasks, such as NLP, image classification, and video/audio processing, for their fast training and superior performance. Much of the merit is…
The attention mechanism can refine the extracted feature maps and boost the classification performance of the deep network, which has become an essential technique in computer vision and natural language processing. However, the memory and…
Non-Autoregressive Neural Machine Translation (NAT) has achieved significant inference speedup by generating all tokens simultaneously. Despite its high efficiency, NAT usually suffers from two kinds of translation errors: over-translation…
Remote sensing image change detection is of great importance in disaster assessment and urban planning. The mainstream method is to use encoder-decoder models to detect the change region of two input images. Since the change content of…
Long-context understanding is crucial for many NLP applications, yet transformers struggle with efficiency due to the quadratic complexity of self-attention. Sparse attention methods alleviate this cost but often impose static, predefined…
Outdoor images often suffer from severe degradation due to rain, haze, and noise, impairing image quality and challenging high-level tasks. Current image restoration methods struggle to handle complex degradation while maintaining…