相关论文: SRFormer: Text Detection Transformer with Incorpor…

Recently, segmentation-based methods are quite popular in scene text detection, as the segmentation results can more accurately describe scene text of various shapes such as curve text. However, the post-processing of binarization is…

Offline handwritten text recognition from images is an important problem for enterprises attempting to digitize large volumes of handmarked scanned documents/reports. Deep recurrent models such as Multi-dimensional LSTMs have been shown to…

The astounding performance of transformers in natural language processing (NLP) has motivated researchers to explore their applications in computer vision tasks. DEtection TRansformer (DETR) introduces transformers to object detection tasks…

Algorithms for the action segmentation task typically use temporal models to predict what action is occurring at each frame for a minute-long daily activity. Recent studies have shown the potential of Transformer in modeling the relations…

Transformers have excelled in many tasks including vision. However, efficient deployment of transformer models in low-latency or high-throughput applications is hindered by the computation in the attention mechanism which involves expensive…

Utilizing transformer architectures for semantic segmentation of high-resolution images is hindered by the attention's quadratic computational complexity in the number of tokens. A solution to this challenge involves decreasing the number…

Text images contain both visual and linguistic information. However, existing pre-training techniques for text recognition mainly focus on either visual representation learning or linguistic knowledge learning. In this paper, we propose a…

While visual autoregressive modeling (VAR) strategies have shed light on image generation with the autoregressive models, their potential for segmentation, a task that requires precise low-level spatial perception, remains unexplored.…

Multi-task learning has proven to be effective in improving the performance of correlated tasks. Most of the existing methods use a backbone to extract initial features with independent branches for each task, and the exchange of…

Generative transformers have shown their superiority in synthesizing high-fidelity and high-resolution images, such as good diversity and training stability. However, they suffer from the problem of slow generation since they need to…

The recently proposed MaskFormer gives a refreshed perspective on the task of semantic segmentation: it shifts from the popular pixel-level classification paradigm to a mask-level classification method. In essence, it generates paired…

Image segmentation is about grouping pixels with different semantics, e.g., category or instance membership, where each choice of semantics defines a task. While only the semantics of each task differ, current research focuses on designing…

Extracting dense representations for terms and phrases is a task of great importance for knowledge discovery platforms targeting highly-technical fields. Dense representations are used as features for downstream components and have multiple…

Transformers have recently achieved state-of-the-art performance in speech separation. These models, however, are computationally demanding and require a lot of learnable parameters. This paper explores Transformer-based speech separation…

This work proposes an attention-based sequence-to-sequence model for handwritten word recognition and explores transfer learning for data-efficient training of HTR systems. To overcome training data scarcity, this work leverages models…

Recent end-to-end scene text spotters have achieved great improvement in recognizing arbitrary-shaped text instances. Common approaches for text spotting use region of interest pooling or segmentation masks to restrict features to single…

Understanding the morphological structure of medical images and precisely segmenting the region of interest or abnormality is an important task that can assist in diagnosis. However, the unique properties of medical imaging make clear…

In recent years, end-to-end scene text spotting approaches are evolving to the Transformer-based framework. While previous studies have shown the crucial importance of the intrinsic synergy between text detection and recognition, recent…

Medical image segmentation is crucial for many healthcare tasks, including disease diagnosis and treatment planning. One key area is the segmentation of skin lesions, which is vital for diagnosing skin cancer and monitoring patients. In…

In this paper, we present TExt Spotting TRansformers (TESTR), a generic end-to-end text spotting framework using Transformers for text detection and recognition in the wild. TESTR builds upon a single encoder and dual decoders for the joint…