The attention mechanism has become the \emph{de facto} module in scene text recognition (STR) methods, due to its capability of extracting character-level representations. These methods can be summarized into implicit attention based and supervised attention based, depended on how the attention is computed, i.e., implicit attention and supervised attention are learned from sequence-level text annotations and or character-level bounding box annotations, respectively. Implicit attention, as it may extract coarse or even incorrect spatial regions as character attention, is prone to suffering from an alignment-drifted issue. Supervised attention can alleviate the above issue, but it is character category-specific, which requires extra laborious character-level bounding box annotations and would be memory-intensive when handling languages with larger character categories. To address the aforementioned issues, we propose a novel attention mechanism for STR, self-supervised implicit glyph attention (SIGA). SIGA delineates the glyph structures of text images by jointly self-supervised text segmentation and implicit attention alignment, which serve as the supervision to improve attention correctness without extra character-level annotations. Experimental results demonstrate that SIGA performs consistently and significantly better than previous attention-based STR methods, in terms of both attention correctness and final recognition performance on publicly available context benchmarks and our contributed contextless benchmarks.
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）
Scene text recognition (STR) has been extensively studied in last few years. Many recently-proposed methods are specially designed to accommodate the arbitrary shape, layout and orientation of scene texts, but ignoring that various font (or writing) styles also pose severe challenges to STR. These methods, where font features and content features of characters are tangled, perform poorly in text recognition on scene images with texts in novel font styles. To address this problem, we explore font-independent features of scene texts via attentional generation of glyphs in a large number of font …
In this paper, we present a novel implicit glyph shape representation, which models glyphs as shape primitives enclosed by quadratic curves, and naturally enables generating glyph images at arbitrary high resolutions. Experiments on font reconstruction and interpolation tasks verified that this structured implicit representation is suitable for describing both structure and style features of glyphs. Furthermore, based on the proposed representation, we design a simple yet effective disentangled network for the challenging one-shot font style transfer problem, and achieve the best results compa…
Institute of Computer Science and Technology, Peking University（北京大学计算机科学技术研究所）
As one of the fundamental problems in document analysis, scene character recognition has attracted considerable interests in recent years. But the problem is still considered to be extremely challenging due to many uncontrollable factors including glyph transformation, blur, noisy background, uneven illumination, etc. In this paper, we propose a novel methodology for boosting scene character recognition by learning canonical forms of glyphs, based on the fact that characters appearing in scene images are all derived from their corresponding canonical forms. Our key observation is that more dis…
Hikvision Research Institute（海康威视研究院）；Zhejiang University（浙江大学）
Text recognition is a popular topic for its broad applications. In this work, we excavate the implicit task, character counting within the traditional text recognition, without additional labor annotation cost. The implicit task plays as an auxiliary branch for complementing the sequential recognition. We design a two-branch reciprocal feature learning framework in order to adequately utilize the features from both the tasks. Through exploiting the complementary effect between explicit and implicit tasks, the feature is reliably enhanced. Extensive experiments on 7 benchmarks show the advantag…
Center for Visual Information Technology, IIIT Hyderabad（海得拉巴国际信息技术研究所视觉信息技术中心）
Building robust recognizers for Arabic has always been challenging. We demonstrate the effectiveness of an end-to-end trainable CNN-RNN hybrid architecture in recognizing Arabic text in videos and natural scenes. We outperform previous state-of-the-art on two publicly available video text datasets - ALIF and ACTIV. For the scene text recognition task, we introduce a new Arabic scene text dataset and establish baseline results. For scripts like Arabic, a major challenge in developing robust recognizers is the lack of large quantity of annotated data. We overcome this by synthesising millions of…
Extremely Fine-Grained Visual Classification over Resembling Glyphs in the Wild
School of Computer and Information Engineering, Henan University（河南大学计算机与信息工程学院）；UPV/EHU（巴斯克大学）；IKERBASQUE, Basque Foundation for Science（巴斯克科学基金会（IKERBASQUE））
We introduce FontCode, an information embedding technique for text documents. Provided a text document with specific fonts, our method embeds user-specified information in the text by perturbing the glyphs of text characters while preserving the text content. We devise an algorithm to chooses unobtrusive yet machine-recognizable glyph perturbations, leveraging a recently developed generative model that alters the glyphs of each character continuously on a font manifold. We then introduce an algorithm that embeds a user-provided message in the text document and produces an encoded document whos…
South China University of Technology（华南理工大学）；Alibaba Group（阿里巴巴集团）；Guangdong Artificial Intelligence and Digital Economy Laboratory（广东省人工智能与数字经济实验室）
Text recognition is a popular research subject with many associated challenges. Despite the considerable progress made in recent years, the text recognition task itself is still constrained to solve the problem of reading cropped line text images and serves as a subtask of optical character recognition (OCR) systems. As a result, the final text recognition result is limited by the performance of the text detector. In this paper, we propose a simple, elegant and effective paradigm called Implicit Feature Alignment (IFA), which can be easily integrated into current text recognizers, resulting in…
Class-Aware Mask-Guided Feature Refinement for Scene Text Recognition
School of Electronic Information and Communications, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院）；School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（华中科技大学人工智能与自动化学院）；Huawei Inc.（华为公司）；School of Software Engineering, Huazhong University of Science and Technology（华中科技大学软件学院）
Jilin University（吉林大学）；University of Trento（特伦托大学）；ETH Zurich（苏黎世联邦理工学院）
Degraded images commonly exist in the general sources of character images, leading to unsatisfactory character recognition results. Existing methods have dedicated efforts to restoring degraded character images. However, the denoising results obtained by these methods do not appear to improve character recognition performance. This is mainly because current methods only focus on pixel-level information and ignore critical features of a character, such as its glyph, resulting in character-glyph damage during the denoising process. In this paper, we introduce a novel generic framework based on g…
DDVR-Net: Degradation-Aware Decoupling and Visibility-Guided Restoration for Historical Document Recognition
Institute of National Security, Minzu University of China（中央民族大学国家安全研究院）；School of Information Engineering, Minzu University of China（中央民族大学信息工程学院）；School of Artificial Intelligence and Computer Science, North China University of Technology（北方工业大学人工智能与计算机学院）
Masked and Permuted Implicit Context Learning for Scene Text Recognition
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Tomorrow Advancing Life；Lenovo Research（联想研究院）
TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition
College of Computer Science and Artificial Intelligence, Fudan University, China（计算机科学与人工智能学院，复旦大学）；Institute of Trustworthy Embodied AI, Fudan University, China（可信具身人工智能研究院，复旦大学）
GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering
Institute of Big Data, College of Computer Science and Artificial Intelligence, Fudan University（大数据研究院，计算机科学与人工智能学院，复旦大学）；Generative AI Lab, College of Computing and Data Science, Nanyang Technological University（生成式人工智能实验室，计算与数据科学学院，南洋理工大学）
Scene text recognition (STR) enables computers to recognize and read the text in various real-world scenes. Recent STR models benefit from taking linguistic information in addition to visual cues into consideration. We propose a novel Masked Vision-Language Transformers (MVLT) to capture both the explicit and the implicit linguistic information. Our encoder is a Vision Transformer, and our decoder is a multi-modal Transformer. MVLT is trained in two stages: in the first stage, we design a STR-tailored pretraining method based on a masking strategy; in the second stage, we fine-tune our model a…
In this paper, we address the task of Optical Character Recognition(OCR) for the Telugu script. We present an end-to-end framework that segments the text image, classifies the characters and extracts lines using a language model. The segmentation is based on mathematical morphology. The classification module, which is the most challenging task of the three, is a deep convolutional neural network. The language is modelled as a third degree markov chain at the glyph level. Telugu script is a complex alphasyllabary and the language is agglutinative, making the problem hard. In this paper we apply…
Blame Errant Words, Not the Canvas: Defect-Aware Spatial Credit Assignment for Visual Text Generation
The Hong Kong University of Science and Technology（香港科技大学）；Tsinghua University（清华大学）；Zhejiang University（浙江大学）；Peking University（北京大学）；Dalian University of Technology（大连理工大学）；Weixin, Tencent（腾讯微信事业群）
University of Pisa（比萨大学）；University College Dublin（都柏林大学学院）
The Transformer architecture is shown to provide a powerful framework as an end-to-end model for building expression trees from online handwritten gestures corresponding to glyph strokes. In particular, the attention mechanism was successfully used to encode, learn and enforce the underlying syntax of expressions creating latent representations that are correctly decoded to the exact mathematical expression tree, providing robustness to ablated inputs and unseen glyphs. For the first time, the encoder is fed with spatio-temporal data tokens potentially forming an infinitely large vocabulary, w…
In this work, our objective is to address the problems of generalization and flexibility for text recognition in documents. We introduce a new model that exploits the repetitive nature of characters in languages, and decouples the visual representation learning and linguistic modelling stages. By doing this, we turn text recognition into a shape matching problem, and thereby achieve generalization in appearance and flexibility in classes. We evaluate the new model on both synthetic and real datasets across different alphabets and show that it can handle challenges that traditional architecture…
Department of Artificial Intelligence（人工智能系）；Kyungpook National University（庆尚国立大学）；Department of Electrical and Computer Engineering（电气电子工程系）；Queen’s University（皇后大学）；Department of Information and Communications Engineering（信息与通信工程系）；Pukyong National University（浦项国立大学）
Image super-resolution(SR) is fundamental to many vision system-from surveillance and autonomy to document analysis and retail analytics-because recovering high-frequency details, especially scene-text, enables reliable downstream perception. Scene-text, i.e., text embedded in natural images such as signs, product labels, and storefronts, often carries the most actionable information; when characters are blurred or hallucinated, optical character recognition(OCR) and subsequent decisions fail even if the rest of the image appears sharp. Yet previous SR research has often been tuned to distorti…
University of Bristol（布里斯托大学）；Zhejiang University（浙江大学）
We describe a novel approach to indoor place recognition from RGB point clouds based on aggregating low-level colour and geometry features with high-level implicit semantic features. It uses a 2-stage deep learning framework, in which the first stage is trained for the auxiliary task of semantic segmentation and the second stage uses features from layers in the first stage to generate discriminate descriptors for place recognition. The auxiliary task encourages the features to be semantically meaningful, hence aggregating the geometry and colour in the RGB point cloud data with implicit semant…
Beijing University of Posts and Telecommunications（北京邮电大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Oracle bone script is the earliest-known Chinese writing system of the Shang dynasty and is precious to archeology and philology. However, real-world scanned oracle data are rare and few experts are available for annotation which make the automatic recognition of scanned oracle characters become a challenging task. Therefore, we aim to explore unsupervised domain adaptation to transfer knowledge from handprinted oracle data, which are easy to acquire, to scanned domain. We propose a structure-texture separation network (STSN), which is an end-to-end learning framework for joint disentanglement…
Few-shot learning aims to recognize instances from novel classes with few labeled samples, which has great value in research and application. Although there has been a lot of work in this area recently, most of the existing work is based on image classification tasks. Video-based few-shot action recognition has not been explored well and remains challenging: 1) the differences of implementation details among different papers make a fair comparison difficult; 2) the wide variations and misalignment of temporal sequences make the video-level similarity comparison difficult; 3) the scarcity of la…
Multi-Representation Geometric Hierarchy Fusion: An Implicit-Submap Driven Framework for Resilient 3D Place Recognition
College of Information and Technology, Beijing University of Chemical Technology（信息与技术学院，北京化工大学）；School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学）；Research Institute of Mine Artificial Intelligence, China Coal Research Institute（矿山人工智能研究院，中国煤炭科研院）
South China University of Technology（华南理工大学）；Ludwig Maximilian University of Munich（慕尼黑大学）；Swiss Federal Institute of Technology（苏黎世联邦理工学院）；CRRC Institute（中车研究院）；The Hong Kong Polytechnic University（香港理工大学）；Anyang Normal University（安阳师范学院）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）
The study of ancient writings has great value for archaeology and philology. Essential forms of material are photographic characters, but manual photographic character recognition is extremely time-consuming and expertise-dependent. Automatic classification is therefore greatly desired. However, the current performance is limited due to the lack of annotated data. Data generation is an inexpensive but useful solution for data scarcity. Nevertheless, the diverse glyph shapes and complex background textures of photographic ancient characters make the generation task difficult, leading to the uns…
Spoofing attacks are a threat to modern face recognition systems. In this work we present a simple yet effective liveness detection approach to enhance 2D face recognition methods and make them robust against spoofing attacks. We show that the risk to spoofing attacks can be re- duced through the use of an additional source of light, for example a flash. From a pair of input images taken under different illumination, we define discriminative features that implicitly contain facial three-dimensional in- formation. Furthermore, we show that when multiple sources of light are considered, we are a…
Towards Implicit Aggregation: Robust Image Representation for Place Recognition in the Transformer Era
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学）；Pengcheng Laboratory（鹏城实验室）；Shenyang Institute of Automation, Chinese Academy of Sciences（沈阳自动化研究所，中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；Pazhou Laboratory (Huangpu)（琶洲实验室（黄埔））
National Institute of Technology Karnataka（卡纳塔克国家理工学院）
We describe a method for classification of handwritten Kannada characters using Hidden Markov Models (HMMs). Kannada script is agglutinative, where simple shapes are concatenated horizontally to form a character. This results in a large number of characters making the task of classification difficult. Character segmentation plays a significant role in reducing the number of classes. Explicit segmentation techniques suffer when overlapping shapes are present, which is common in the case of handwritten text. We use HMMs to take advantage of the agglutinative nature of Kannada script, which allow…
Current state-of-the-art approaches in the field of Handwritten Text Recognition are predominately single task with unigram, character level target units. In our work, we utilize a Multi-task Learning scheme, training the model to perform decompositions of the target sequence with target units of different granularity, from fine to coarse. We consider this method as a way to utilize n-gram information, implicitly, in the training process, while the final recognition is performed using only the unigram output. % in order to highlight the difference of the internal Unigram decoding of such a mul…
Face recognition (FR) using deep convolutional neural networks (DCNNs) has seen remarkable success in recent years. One key ingredient of DCNN-based FR is the appropriate design of a loss function that ensures discrimination between various identities. The state-of-the-art (SOTA) solutions utilise normalised Softmax loss with additive and/or multiplicative margins. Despite being popular, these Softmax+margin based losses are not theoretically motivated and the effectiveness of a margin is justified only intuitively. In this work, we utilise an alternative framework that offers a more direct me…
Camera-based implicit mind reading by capturing higher-order semantic dynamics of human gaze within environmental context
China University of Petroleum (East China)（中国石油大学（华东））；the Qingdao Institute of Software（青岛软件研究所）；the College of Computer Science and Technology（计算机科学与技术学院）；Shandong Key Laboratory of Intelligent Oil & Gas Industrial Software（山东省智能油气工业软件重点实验室）；College of Information Science and Technology（信息科学与技术学院）
We propose a novel deep supervised neural network for the task of action recognition in videos, which implicitly takes advantage of visual tracking and shares the robustness of both deep Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). In our method, a multi-branch model is proposed to suppress noise from background jitters. Specifically, we firstly extract multi-level deep features from deep CNNs and feed them into 3d-convolutional network. After that we feed those feature cubes into our novel joint LSTM module to predict labels and to generate attention regularization. …
Harbin Institute of Technology（哈尔滨工业大学）；Meituan（美团）
Single online handwritten Chinese character recognition~(single OLHCCR) has achieved prominent performance. However, in real application scenarios, users always write multiple Chinese characters to form one complete sentence and the contextual information within these characters holds the significant potential to improve the accuracy, robustness and efficiency of sentence-level OLHCCR. In this work, we first propose a simple and straightforward end-to-end network, namely vanilla compositional network~(VCN) to tackle the sentence-level OLHCCR. It couples convolutional neural network with sequen…
LITIS（信息与图像处理实验室）；Rouen University（鲁昂大学）；Normandy University（诺曼底大学）；INSA of Rouen（鲁昂国立应用科学学院）
Unconstrained handwritten text recognition remains challenging for computer vision systems. Paragraph text recognition is traditionally achieved by two models: the first one for line segmentation and the second one for text line recognition. We propose a unified end-to-end model using hybrid attention to tackle this task. This model is designed to iteratively process a paragraph image line by line. It can be split into three modules. An encoder generates feature maps from the whole paragraph image. Then, an attention module recurrently generates a vertical weighted mask enabling to focus on th…
Corporate Research and Development Center, Toshiba Corporation（东芝公司企业研发中心）；The University of Tokyo（东京大学）；RIKEN（理化学研究所）
In recent years, deep neural networks (DNNs) have been applied to various machine leaning tasks, including image recognition, speech recognition, and machine translation. However, large DNN models are needed to achieve state-of-the-art performance, exceeding the capabilities of edge devices. Model reduction is thus needed for practical use. In this paper, we point out that deep learning automatically induces group sparsity of weights, in which all weights connected to an output channel (node) are zero, when training DNNs under the following three conditions: (1) rectified-linear-unit (ReLU) ac…
