Related papers: On Cropped versus Uncropped Training Sets in Tabul…

The effectiveness of machine learning algorithms arises from being able to extract useful features from large amounts of data. As model and dataset sizes increase, dataset distillation methods that compress large datasets into significantly…

Learning meaningful representations that disentangle the underlying structure of the data generating process is considered to be of key importance in machine learning. While disentangled representations were found to be useful for diverse…

Obtaining annotated table structure data for complex tables is a challenging task due to the inherent diversity and complexity of real-world document layouts. The scarcity of publicly available datasets with comprehensive annotations for…

Automatic Image Cropping is a challenging task with many practical downstream applications. The task is often divided into sub-problems - generating cropping candidates, finding the visually important regions, and determining aesthetics to…

We consider structure discovery of undirected graphical models from observational data. Inferring likely structures from few examples is a complex task often requiring the formulation of priors and sophisticated inference procedures.…

Tabular data is arguably one of the most commonly used data structures in various practical domains, including finance, healthcare and e-commerce. The inherent heterogeneity allows tabular data to store rich information. However, based on a…

To address the challenges of table structure recognition, we propose a novel Split-Merge-based top-down model optimized for large, densely populated tables. Our approach formulates row and column splitting as sequence labeling tasks,…

Deep learning for tabular data has garnered increasing attention in recent years, yet employing deep models for structured data remains challenging. While these models excel with unstructured data, their efficacy with structured data has…

Existing metrics used to evaluate table structure recognition algorithms have shortcomings with regard to capturing text and empty cells alignment. In this paper, we build on prior work and propose a new metric - TEDS based IOU similarity…

Object detection in high-resolution aerial images is a challenging task because of 1) the large variation in object size, and 2) non-uniform distribution of objects. A common solution is to divide the large aerial image into small (uniform)…

The rise of powerful generative models has sparked concerns over data authenticity. While detection methods have been extensively developed for images and text, the case of tabular data, despite its ubiquity, has been largely overlooked.…

Data for Image segmentation models can be costly to obtain due to the precision required by human annotators. We run a series of experiments showing the effect of different kinds of Dropout training on the DeepLabv3+ Image segmentation…

Table detection within document images is a crucial task in document processing, involving the identification and localization of tables. Recent strides in deep learning have substantially improved the accuracy of this task, but it still…

The non-uniform photoelectric response of infrared imaging systems results in fixed-pattern stripe noise being superimposed on infrared images, which severely reduces image quality. As the applications of degraded infrared images are…

We present a method for performing hierarchical object detection in images guided by a deep reinforcement learning agent. The key idea is to focus on those parts of the image that contain richer information and zoom on them. We train an…

Table detection is the task of classifying and localizing table objects within document images. With the recent development in deep learning methods, we observe remarkable success in table detection. However, a significant amount of labeled…

We present TNCR, a new table dataset with varying image quality collected from free websites. The TNCR dataset can be used for table detection in scanned document images and their classification into 5 different classes. TNCR contains 9428…

The vast network of bridges in the United States raises a high requirement for maintenance and rehabilitation. The massive cost of manual visual inspection to assess bridge conditions is a burden to some extent. Advanced robots have been…

Presentation of folded documents is not an uncommon case in modern society. Digitizing such documents by capturing them with a smartphone camera can be tricky since a crease can divide the document contents into separate planes. To unfold…

Despite tremendous progress over the past decade, deep learning methods generally fall short of human-level systematic generalization. It has been argued that explicitly capturing the underlying structure of data should allow connectionist…