Related papers: Robust Table Structure Recognition with Dynamic Qu…

Complex reasoning over tabular data is crucial in real-world data analysis, yet large language models (LLMs) often underperform due to complex queries, noisy data, and limited numerical capabilities. To address these issues, we propose…

Automated visual inspection of locomotive coil springs presents significant challenges due to the morphological diversity of surface defects, substantial scale variations, and complex industrial backgrounds. This paper proposes MSD-DETR…

Symbolic regression (SR) is a challenging task in machine learning that involves finding a mathematical expression for a function based on its values. Recent advancements in SR have demonstrated the effectiveness of pre-trained…

We propose an efficient linear-time graph-based divisive cluster analysis approach called Reductive Clustering. The approach tries to reveal the hierarchical structural information through reducing the graph into a more concise one…

Dynamic Bayesian Networks (DBNs), renowned for their interpretability, have become increasingly vital in representing complex stochastic processes in various domains such as gene expression analysis, healthcare, and traffic prediction.…

Point scene understanding is a challenging task to process real-world scene point cloud, which aims at segmenting each object, estimating its pose, and reconstructing its mesh simultaneously. Recent state-of-the-art method first segments…

We propose a novel deep symbolic regression approach to enhance the robustness and interpretability of data-driven mathematical expression discovery. Our work is aligned with the popular DSR framework which focuses on learning a…

Accurate liver segmentation from CT scans is essential for effective diagnosis and treatment planning. Computer-aided diagnosis systems promise to improve the precision of liver disease diagnosis, disease progression, and treatment…

Transformer has achieved satisfactory results in the field of hyperspectral image (HSI) classification. However, existing Transformer models face two key challenges when dealing with HSI scenes characterized by diverse land cover types and…

The recently proposed end-to-end transformer detectors, such as DETR and Deformable DETR, have a cascade structure of stacking 6 decoder layers to update object queries iteratively, without which their performance degrades seriously. In…

Recent studies show that deep learning (DL) based MRI reconstruction outperforms conventional methods, such as parallel imaging and compressed sensing (CS), in multiple applications. Unlike CS that is typically implemented with…

Neural architecture for named entity recognition has achieved great success in the field of natural language processing. Currently, the dominating architecture consists of a bi-directional recurrent neural network (RNN) as the encoder and a…

We propose RoTaR, a row-based table representation learning method, to address the efficiency and scalability issues faced by existing table representation learning methods. The key idea of RoTaR is to generate query-agnostic row…

In this report, we present RT-DETRv2, an improved Real-Time DEtection TRansformer (RT-DETR). RT-DETRv2 builds upon the previous state-of-the-art real-time detector, RT-DETR, and opens up a set of bag-of-freebies for flexibility and…

In this paper, we propose a new class of metric for table structure recognition (TSR) evaluation, called grid table similarity (GriTS). Unlike prior metrics, GriTS evaluates the correctness of a predicted table directly in its natural form…

Tensor train (TT) decomposition is a powerful representation for high-order tensors, which has been successfully applied to various machine learning tasks in recent years. However, since the tensor product is not commutative, permutation of…

The challenging task of 3D planar reconstruction from images involves several sub-tasks including frame-wise plane detection, segmentation, parameter regression and possibly depth prediction, along with cross-frame plane correspondence and…

Dimensionality reduction is an essential technique for multi-way large-scale data, i.e., tensor. Tensor ring (TR) decomposition has become popular due to its high representation ability and flexibility. However, the traditional TR…

End-to-end object detection is rapidly progressed after the emergence of DETR. DETRs use a set of sparse queries that replace the dense candidate boxes in most traditional detectors. In comparison, the sparse queries cannot guarantee a high…

Research in scene graph generation (SGG) usually considers two-stage models, that is, detecting a set of entities, followed by combining them and labeling all possible relationships. While showing promising results, the pipeline structure…