Related papers: Leveraging Text Localization for Scene Text Remova…

Self-supervised learning (SSL) methods have become a dominant paradigm for creating general purpose models whose capabilities can be transferred to downstream supervised learning tasks. However, most such methods rely on vast amounts of…

Autonomous mobile robots deployed in urban environments must be context-aware, i.e., able to distinguish between different semantic entities, and robust to occlusions. Current approaches like semantic scene completion (SSC) require…

Masked image modeling has demonstrated great potential to eliminate the label-hungry problem of training large-scale vision Transformers, achieving impressive performance on various downstream tasks. In this work, we propose a unified view…

Video-Text pre-training aims at learning transferable representations from large-scale video-text pairs via aligning the semantics between visual and textual information. State-of-the-art approaches extract visual features from raw pixels…

Developing effective scene text detection and recognition models hinges on extensive training data, which can be both laborious and costly to obtain, especially for low-resourced languages. Conventional methods tailored for Latin characters…

Scene text spotting is a challenging task, especially for inverse-like scene text, which has complex layouts, e.g., mirrored, symmetrical, or retro-flexed. In this paper, we propose a unified end-to-end trainable inverse-like antagonistic…

Product embedding serves as a cornerstone for a wide range of applications in eCommerce. The product embedding learned from multiple modalities shows significant improvement over that from a single modality, since different modalities…

Image and text retrieval is one of the foundational tasks in the vision and language domain with multiple real-world applications. State-of-the-art approaches, e.g. CLIP, ALIGN, represent images and texts as dense embeddings and calculate…

Masked image modeling (MIM) as pre-training is shown to be effective for numerous vision downstream tasks, but how and where MIM works remain unclear. In this paper, we compare MIM with the long-dominant supervised pre-trained models from…

Scene text recognition is an important and challenging task in computer vision. However, most prior works focus on recognizing pre-defined words, while there are various out-of-vocabulary (OOV) words in real-world applications. In this…

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…

Text Image Machine Translation (TIMT) aims to translate texts embedded within an image into another language. Current TIMT studies primarily focus on providing translations for all the text within an image, while neglecting to provide…

Recently, scene text detection has been a challenging task. Texts with arbitrary shape or large aspect ratio are usually hard to detect. Previous segmentation-based methods can describe curve text more accurately but suffer from over…

Scene text detection remains a grand challenge due to the variation in text curvatures, orientations, and aspect ratios. One of the hardest problems in this task is how to represent text instances of arbitrary shapes. Although many methods…

Localizing text in low-light environments is challenging due to visual degradations. Although a straightforward solution involves a two-stage pipeline with low-light image enhancement (LLE) as the initial step followed by detector, LLE is…

The prevalent perspectives of scene text recognition are from sequence to sequence (seq2seq) and segmentation. Nevertheless, the former is composed of many components which makes implementation and deployment complicated, while the latter…

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…

Masked image modeling (MIM) has become a leading self-supervised learning strategy. MIMs such as Masked Autoencoder (MAE) learn strong representations by randomly masking input tokens for the encoder to process, with the decoder…

Self-supervised learning has emerged as a powerful approach for leveraging large-scale unlabeled data to improve model performance in various domains. In this paper, we explore masked self-supervised pre-training for text recognition…

Comprehensive semantic segmentation is one of the key components for robust scene understanding and a requirement to enable autonomous driving. Driven by large scale datasets, convolutional neural networks show impressive results on this…