Related papers: Parallel Scale-wise Attention Network for Effectiv…
This paper focuses on the problem of script identification in scene text images. Facing this problem with state of the art CNN classifiers is not straightforward, as they fail to address a key characteristic of scene text instances: their…
Recently, scene text detection has received significant attention due to its wide application. However, accurate detection in complex scenes of multiple scales, orientations, and curvature remains a challenge. Numerous detection methods…
Recent advances in text recognition led to a paradigm shift for page-level recognition, from multi-step segmentation-based approaches to end-to-end attention-based ones. However, the na\"ive character-level autoregressive decoding process…
This study proposes a text classification algorithm based on large language models, aiming to address the limitations of traditional methods in capturing long-range dependencies, understanding contextual semantics, and handling class…
Scene Graph Generation, which generally follows a regular encoder-decoder pipeline, aims to first encode the visual contents within the given image and then parse them into a compact summary graph. Existing SGG approaches generally not only…
Crowd counting aims to predict the number of people and generate the density map in the image. There are many challenges, including varying head scales, the diversity of crowd distribution across images and cluttered backgrounds. In this…
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…
Self-attention-based models have achieved remarkable progress in short-text mining. However, the quadratic computational complexities restrict their application in long text processing. Prior works have adopted the chunking strategy to…
Traffic scene recognition, which requires various visual classification tasks, is a critical ingredient in autonomous vehicles. However, most existing approaches treat each relevant task independently from one another, never considering the…
We study the problem of extracting text instance contour information from images and use it to assist scene text detection. We propose a novel and effective framework for this and experimentally demonstrate that: (1) A CNN that can be…
Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-to-end (E2E) Automatic Speech Recognition (ASR). The joint CTC/Attention model has achieved great success by…
Scene Text Recognition (STR) remains challenging due to real-world complexities, where decoupled visual-linguistic optimization in existing frameworks amplifies error propagation through cross-modal misalignment. Visual encoders exhibit…
Street scene change detection continues to capture researchers' interests in the computer vision community. It aims to identify the changed regions of the paired street-view images captured at different times. The state-of-the-art network…
We propose a novel attention model that can accurately attends to target objects of various scales and shapes in images. The model is trained to gradually suppress irrelevant regions in an input image via a progressive attentive process…
This paper studies a text classification algorithm based on an improved Transformer to improve the performance and efficiency of the model in text classification tasks. Aiming at the shortcomings of the traditional Transformer model in…
Irregular scene text, which has complex layout in 2D space, is challenging to most previous scene text recognizers. Recently, some irregular scene text recognizers either rectify the irregular text to regular text image with approximate 1D…
In recent years, vision transformers with text decoder have demonstrated remarkable performance on Scene Text Recognition (STR) due to their ability to capture long-range dependencies and contextual relationships with high learning…
Lane detection is a crucial perception task for all levels of automated vehicles (AVs) and Advanced Driver Assistance Systems, particularly in mixed-traffic environments where AVs must interact with human-driven vehicles (HDVs) and…
Numerous scene text detection methods have been proposed in recent years. Most of them declare they have achieved state-of-the-art performances. However, the performance comparison is unfair, due to lots of inconsistent settings (e.g.,…
Semantic segmentation is a challenge in scene parsing. It requires both context information and rich spatial information. In this paper, we differentiate features for scene segmentation based on dedicated attention mechanisms (DF-DAM), and…