Related papers: CloudScan - A configuration-free invoice analysis …

Convolutional networks are at the core of most state-of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding substantial gains in various…

Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of…

In the Data-Centric Artificial Intelligence (AI) paradigm, improving data quality is essential for robust machine learning. However, many denoising methods rely on rigid statistical assumptions or require clean reference data, which limits…

The efficiency of natural language processing has improved dramatically with the advent of machine learning models, particularly neural network-based solutions. However, some tasks are still challenging, especially when considering specific…

Labeling visual data is expensive and time-consuming. Crowdsourcing systems promise to enable highly parallelizable annotations through the participation of monetarily or otherwise motivated workers, but even this approach has its limits.…

This paper focuses on the problem of visual saliency prediction, predicting regions of an image that tend to attract human visual attention, under a constrained computational budget. We modify and test various recent efficient convolutional…

Architecture plays an important role in deciding the performance of deep neural networks. However, the search for the optimal architecture is often hindered by the vast search space, making it a time-intensive process. Recently, a novel…

$\textbf{Objective}$ Develop an automatic diagnostic system which only uses textual admission information from Electronic Health Records (EHRs) and assist clinicians with a timely and statistically proved decision tool. The hope is that the…

Computer vision systems require large amounts of manually annotated data to properly learn challenging visual concepts. Crowdsourcing platforms offer an inexpensive method to capture human knowledge and understanding, for a vast number of…

Conventional Optical Character Recognition (OCR) systems are challenged by variant invoice layouts, handwritten text, and low-quality scans, which are often caused by strong template dependencies that restrict their flexibility across…

Despite existing work in machine learning inference serving, ease-of-use and cost efficiency remain challenges at large scales. Developers must manually search through thousands of model-variants -- versions of already-trained models that…

Convolutional neural networks show remarkable results in classification but struggle with learning new things on the fly. We present a novel rehearsal-free approach, where a deep neural network is continually learning new unseen object…

A deep clustering network is desired for data streams because of its aptitude in extracting natural features thus bypassing the laborious feature engineering step. While automatic construction of the deep networks in streaming environments…

In cloud-based endpoint auditing, security administrators often rely on the cloud to perform causality analysis over log-derived versioned provenance graphs to investigate suspicious attack behaviors. However, the cloud may be distrusted or…

Humans solving algorithmic (or) reasoning problems typically exhibit solution times that grow as a function of problem difficulty. Adaptive recurrent neural networks have been shown to exhibit this property for various language-processing…

We propose RainyScape, an unsupervised framework for reconstructing clean scenes from a collection of multi-view rainy images. RainyScape consists of two main modules: a neural rendering module and a rain-prediction module that incorporates…

Document analysis and understanding models often require extensive annotated data to be trained. However, various document-related tasks extend beyond mere text transcription, requiring both textual content and precise bounding-box…

Unsupervised graph representation learning aims to learn low-dimensional node embeddings without supervision while preserving graph topological structures and node attributive features. Previous graph neural networks (GNN) require a large…

Astronomical surveys of celestial sources produce streams of noisy time series measuring flux versus time ("light curves"). Unlike in many other physical domains, however, large (and source-specific) temporal gaps in data arise naturally…

Existing studies on comparative opinion mining have mainly focused on explicit comparative expressions, which are uncommon in real-world reviews. This leaves implicit comparisons - here users express preferences across separate reviews -…