Related papers: Self-supervised Implicit Glyph Attention for Text …

Scene text image super-resolution (STISR), aiming to improve image quality while boosting downstream scene text recognition accuracy, has recently achieved great success. However, most existing methods treat the foreground (character…

Vision Language Models (VLMs) have rapidly advanced and show strong promise for text-based person search (TBPS), a task that requires capturing fine-grained relationships between images and text to distinguish individuals. Previous methods…

This paper presents the first comprehensive interpretability analysis of a Transformer-based Sign Language Translation (SLT) model, focusing on the translation from video-based Greek Sign Language to glosses and text. Leveraging the Greek…

The paper approaches the task of handwritten text recognition (HTR) with attentional encoder-decoder networks trained on sequences of characters, rather than words. We experiment on lines of text from popular handwriting datasets and…

Scene text recognition (STR) has been an active research topic in computer vision for years. To tackle this challenging problem, numerous innovative methods have been successively proposed and incorporating linguistic knowledge into STR…

Supervised deep learning requires massive labeled datasets, but obtaining annotations is not always easy or possible, especially for dense tasks like semantic segmentation. To overcome this issue, numerous works explore Unsupervised Domain…

Attention is a general reasoning mechanism than can flexibly deal with image information, but its memory requirements had made it so far impractical for high resolution image generation. We present Grid Partitioned Attention (GPA), a new…

Unsupervised Domain Adaptation (UDA) aims to enhance the generalization of the learned model to other domains. The domain-invariant knowledge is transferred from the model trained on labeled source domain, e.g., video game, to unlabeled…

Unsupervised semantic segmentation aims to discover and localize semantically meaningful categories within image corpora without any form of annotation. To solve this task, algorithms must produce features for every pixel that are both…

Example-guided image synthesis has been recently attempted to synthesize an image from a semantic label map and an exemplary image. In the task, the additional exemplary image serves to provide style guidance that controls the appearance of…

Class-Incremental Learning (CIL) enables models to continuously integrate new knowledge while mitigating catastrophic forgetting. Driven by the remarkable generalization of CLIP, leveraging pre-trained vision-language models has become a…

Deep learning-based image manipulation localization (IML) methods have achieved remarkable performance in recent years, but typically rely on large-scale pixel-level annotated datasets. To address the challenge of acquiring high-quality…

Generative graph self-supervised learning (SSL) aims to learn node representations by reconstructing the input graph data. However, most existing methods focus on unsupervised learning tasks only and very few work has shown its superiority…

In recent years, the long-range attention mechanism of vision transformers has driven significant performance breakthroughs across various computer vision tasks. However, the traditional self-attention mechanism, which processes both…

Stable diffusion has demonstrated strong image synthesis ability to given text descriptions, suggesting it to contain strong semantic clue for grouping objects. The researchers have explored employing stable diffusion for training-free…

Scene text recognition (STR) is an important bridge between images and text, attracting abundant research attention. While convolutional neural networks (CNNS) have achieved remarkable progress in this task, most of the existing works need…

Efficient inference on GPUs using large language models remains challenging due to memory bandwidth limitations, particularly during data transfers between High Bandwidth Memory (HBM) and SRAM in attention computations. Approximate…

Text-driven image editing has advanced rapidly, but reliably localizing these manipulations requires image manipulation localization (IML) models trained on large pixel-annotated datasets, and there is still no low-cost way to obtain such…

Existing deep embedding clustering works only consider the deepest layer to learn a feature embedding and thus fail to well utilize the available discriminative information from cluster assignments, resulting performance limitation. To this…

Text images are unique in their dual nature, encompassing both visual and linguistic information. The visual component encompasses structural and appearance-based features, while the linguistic dimension incorporates contextual and semantic…