相关论文: DOTA: Deformable Optimized Transformer Architectur…

Deformable image registration establishes non-linear spatial correspondences between fixed and moving images. Deep learning-based deformable registration methods have been widely studied in recent years due to their speed advantage over…

Recent Transformer-based visual tracking models have showcased superior performance. Nevertheless, prior works have been resource-intensive, requiring prolonged GPU training hours and incurring high GFLOPs during inference due to…

We propose a registration algorithm for 2D CT/MRI medical images with a new unsupervised end-to-end strategy using convolutional neural networks. The contributions of our algorithm are threefold: (1) We transplant traditional image…

Plenty of face detection and recognition methods have been proposed and got delightful results in decades. Common face recognition pipeline consists of: 1) face detection, 2) face alignment, 3) feature extraction, 4) similarity calculation,…

Writer identification due to its widespread application in various fields has gained popularity over the years. In scenarios where optimum handwriting samples are available, whether they be in the form of a single line, a sentence, or an…

Transformer-based models have achieved strong performance in remote sensing image captioning by capturing long-range dependencies and contextual information. However, their practical deployment is hindered by high computational costs,…

Recent advances in unsupervised domain adaptation (UDA) techniques have witnessed great success in cross-domain computer vision tasks, enhancing the generalization ability of data-driven deep learning architectures by bridging the domain…

State-of-the-art methods for text classification include several distinct steps of pre-processing, feature extraction and post-processing. In this work, we focus on end-to-end neural architectures and show that the best performance in text…

With an unprecedented increase in the number of agents and systems that aim to navigate the real world using visual cues and the rising impetus for 3D Vision Models, the importance of depth estimation is hard to understate. While supervised…

End-to-end text spotting aims to jointly optimize text detection and recognition within a unified framework. Despite significant progress, designing an accurate and efficient end-to-end text spotter for arbitrary-shaped text remains…

Recently, DETR and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors. However, their performance on…

In this paper, we propose to exploit the rich hierarchical features of deep convolutional neural networks to improve the accuracy and robustness of visual tracking. Deep neural networks trained on object recognition datasets consist of…

Recent deep learning models have demonstrated strong capabilities for classifying text and non-text components in natural images. They extract a high-level feature computed globally from a whole image component (patch), where the cluttered…

Vision Transformers have achieved great success in computer visions, delivering exceptional performance across various tasks. However, their inherent reliance on sequential input enforces the manual partitioning of images into patch…

Incidental scene text spotting is considered one of the most difficult and valuable challenges in the document analysis community. Most existing methods treat text detection and recognition as separate tasks. In this work, we propose a…

Transformer has achieved great success in computer vision, while how to split patches in an image remains a problem. Existing methods usually use a fixed-size patch embedding which might destroy the semantics of objects. To address this…

Robustness to out-of-distribution data is crucial for deploying modern neural networks. Recently, Vision Transformers, such as SegFormer for semantic segmentation, have shown impressive robustness to visual corruptions like blur or noise…

This paper proposes a new method, OFA-OCR, to transfer multimodal pretrained models to text recognition. Specifically, we recast text recognition as image captioning and directly transfer a unified vision-language pretrained model to the…

Time Delay Neural Networks (TDNNs) are widely used in both DNN-HMM based hybrid speech recognition systems and recent end-to-end systems. Nevertheless, the receptive fields of TDNNs are limited and fixed, which is not desirable for tasks…

We introduce dense vision transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks. We assemble tokens from various stages of the vision transformer into…