Related papers: RAPTOR: Refined Approach for Product Table Object …
We present a machine learning approach for predicting the organisation of corneal, glial and fibroblast cells in 3D cultures used for tissue engineering. Our machine-learning-based method uses a powerful generative adversarial network…
Retrieving evidences from tabular and textual resources is essential for open-domain question answering (OpenQA), which provides more comprehensive information. However, training an effective dense table-text retriever is difficult due to…
Table structure recognition is necessary for a comprehensive understanding of documents. Tables in unstructured business documents are tough to parse due to the high diversity of layouts, varying alignments of contents, and the presence of…
Many real-world datasets are labeled with natural orders, i.e., ordinal labels. Ordinal regression is a method to predict ordinal labels that finds a wide range of applications in data-rich domains, such as natural, health and social…
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…
Trajectory representation learning (TRL) maps trajectories to vectors that can then be used for various downstream tasks, including trajectory similarity computation, trajectory classification, and travel-time estimation. However, existing…
The generation of synthetic tabular data that preserves differential privacy is a problem of growing importance. While traditional marginal-based methods have achieved impressive results, recent work has shown that deep learning-based…
Recent advances in trajectory replanning have enabled quadrotor to navigate autonomously in unknown environments. However, high-speed navigation still remains a significant challenge. Given very limited time, existing methods have no strong…
This paper presents a general scheme for enhancing the convergence and performance of DETR (DEtection TRansformer). We investigate the slow convergence problem in transformers from a new perspective, suggesting that it arises from the…
A table is an object that captures structured and informative content within a document, and recognizing a table in an image is challenging due to the complexity and variety of table layouts. Many previous works typically adopt a two-stage…
Current challenges in developing foundational models for volumetric imaging data, such as magnetic resonance imaging (MRI), stem from the computational complexity of training state-of-the-art architectures in high dimensions and curating…
Detection Transformers (DETR) are increasingly adopted in autonomous vehicle (AV) perception systems due to their superior accuracy over convolutional networks. However, concurrently executing multiple DETR tasks presents significant…
We propose a higher-order dimensionality reduction framework based on the Trace Ratio (TR) optimization problem. We establish conditions for existence and uniqueness of solutions and clarify the theoretical connection between the Trace…
Detection Transformer (DETR) directly transforms queries to unique objects by using one-to-one bipartite matching during training and enables end-to-end object detection. Recently, these models have surpassed traditional detectors on COCO…
There is a niche of companies responsible for intermediating the purchase of large batches of varied products for other companies, for which the main challenge is to perform product description standardization, i.e., matching an item…
Recently, DETR pioneered the solution of vision tasks with transformers, it directly translates the image feature map into the object detection result. Though effective, translating the full feature map can be costly due to redundant…
Semi-structured table question answering (QA) is a challenging task that requires (1) precise extraction of cell contents and positions and (2) accurate recovery of key implicit logical structures, hierarchical relationships, and semantic…
Visual Multi-Object Tracking (MOT) is a crucial component of robotic perception, yet existing Tracking-By-Detection (TBD) methods often rely on 2D cues, such as bounding boxes and motion modeling, which struggle under occlusions and…
Unstructured data is pervasive, but analytical queries demand structured representations, creating a significant extraction challenge. Existing methods like RAG lack schema awareness and struggle with cross-document alignment, leading to…
Tabular data, structured as rows and columns, is among the most prevalent data types in machine learning classification and regression applications. Models for learning from tabular data have continuously evolved, with Deep Neural Networks…