Related papers: Evaluating Table Structure Recognition: A New Pers…
Most existing point cloud based 3D object detectors focus on the tasks of classification and box regression. However, another bottleneck in this area is achieving an accurate detection confidence for the Non-Maximum Suppression (NMS)…
Spreadsheet table detection is the task of detecting all tables on a given sheet and locating their respective ranges. Automatic table detection is a key enabling technique and an initial step in spreadsheet data intelligence. However, the…
Modern detection transformers (DETRs) use a set of object queries to predict a list of bounding boxes, sort them by their classification confidence scores, and select the top-ranked predictions as the final detection results for the given…
Tables contain valuable knowledge in a structured form. We employ neural language modeling approaches to embed tabular data into vector spaces. Specifically, we consider different table elements, such caption, column headings, and cells,…
This paper presents an efficient way of detecting directed objects by predicting their center coordinates and direction angle. Since the objects are of uniform size, the proposed model works without predicting the object's width and height.…
Text detection enables us to extract rich information from images. In this paper, we focus on how to generate bounding boxes that are appropriate to grasp text areas on books to help implement automatic text detection. We attempt not to…
Traditional methods for identifying structurally similar spreadsheets fail to capture the spatial layouts and type patterns defining templates. To quantify spreadsheet similarity, we introduce a hybrid distance metric that combines semantic…
Current anchor-free object detectors are quite simple and effective yet lack accurate label assignment methods, which limits their potential in competing with classic anchor-based models that are supported by well-designed assignment…
Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects and an additional rotation angle parameter is used for rotated objects. We argue that such a mechanism has fundamental…
Recent deep learning approaches in table detection achieved outstanding performance and proved to be effective in identifying document layouts. Currently, available table detection benchmarks have many limitations, including the lack of…
We present ModelTables, a benchmark of tables in Model Lakes that captures the structured semantics of performance and configuration tables often overlooked by text only retrieval. The corpus is built from Hugging Face model cards, GitHub…
Out-of-distribution (OOD) detection remains challenging in text-rich networks, where textual features intertwine with topological structures. Existing methods primarily address label shifts or rudimentary domain-based splits, overlooking…
Stacking, a potent ensemble learning method, leverages a meta-model to harness the strengths of multiple base models, thereby enhancing prediction accuracy. Traditional stacking techniques typically utilize established learning models, such…
We propose a novel method for representing oriented objects in aerial images named Adaptive Period Embedding (APE). While traditional object detection methods represent object with horizontal bounding boxes, the objects in aerial images are…
Structured data extraction from tables plays a crucial role in document image analysis for scanned documents and digital archives. Although many methods have been proposed to detect table structures and extract cell contents, accurately…
Tables are everywhere, from scientific journals, papers, websites, and newspapers all the way to items we buy at the supermarket. Detecting them is thus of utmost importance to automatically understanding the content of a document. The…
Bounding box regression (BBR) has been widely used in object detection and instance segmentation, which is an important step in object localization. However, most of the existing loss functions for bounding box regression cannot be…
Unknown Object Detection (UOD) aims to identify objects of unseen categories, differing from the traditional detection paradigm limited by the closed-world assumption. A key component of UOD is learning a generalized representation, i.e.…
This paper discusses current methods and trends for 3D bounding box detection in volumetric medical image data. For this purpose, an overview of relevant papers from recent years is given. 2D and 3D implementations are discussed and…
Edge detection has long been an important problem in the field of computer vision. Previous works have explored category-agnostic or category-aware edge detection. In this paper, we explore edge detection in the context of object instances.…