State-of-the-art text spotting systems typically aim to detect isolated words or word-by-word text in images of natural scenes and ignore the semantic coherence within a region of text. However, when interpreted together, seemingly isolated words may be easier to recognize. On this basis, we propose a novel "semantic-based text recognition" (STR) deep learning model that reads text in images with the help of understanding context. STR consists of several modules. We introduce the Text Grouping and Arranging (TGA) algorithm to connect and order isolated text regions. A text-recognition network interprets isolated words. Benefiting from semantic information, a sequenceto-sequence network model efficiently corrects inaccurate and uncertain phrases produced earlier in the STR pipeline. We present experiments on two new distinct datasets that contain scanned catalog images of interior designs and photographs of protesters with hand-written signs, respectively. Our results show that our STR model outperforms a baseline method that uses state-of-the-art single-wordrecognition techniques on both datasets. STR yields a high accuracy rate of 90% on the catalog images and 71% on the more difficult protest images, suggesting its generality in recognizing text.
Linguistic knowledge has brought great benefits to scene text recognition by providing semantics to refine character sequences. However, since linguistic knowledge has been applied individually on the output sequence, previous methods have not fully utilized the semantics to understand visual clues for text recognition. This paper introduces a novel method, called Multi-modAl Text Recognition Network (MATRN), that enables interactions between visual and semantic features for better recognition performances. Specifically, MATRN identifies visual and semantic feature pairs and encodes spatial in…
Scene text image contains two levels of contents: visual texture and semantic information. Although the previous scene text recognition methods have made great progress over the past few years, the research on mining semantic information to assist text recognition attracts less attention, only RNN-like structures are explored to implicitly model semantic information. However, we observe that RNN based methods have some obvious shortcomings, such as time-dependent decoding manner and one-way serial transmission of semantic context, which greatly limit the help of semantic information and the co…
Ping An Property & Casualty Insurance Company（平安财产保险股份有限公司）
Modeling semantic information is helpful for scene text recognition. In this work, we propose to model semantic and visual information jointly with a Visual-Semantic Transformer (VST). The VST first explicitly extracts primary semantic information from visual feature maps with a transformer module and a primary visual-semantic alignment module. The semantic information is then joined with the visual feature maps (viewed as a sequence) to form a pseudo multi-domain sequence combining visual and semantic information, which is subsequently fed into an transformer-based interaction module to enabl…
Huazhong University of Science and Technology（华中科技大学）；Alibaba Group（阿里巴巴集团）
Semantic information has been proved effective in scene text recognition. Most existing methods tend to couple both visual and semantic information in an attention-based decoder. As a result, the learning of semantic features is prone to have a bias on the limited vocabulary of the training set, which is called vocabulary reliance. In this paper, we propose a novel Visual-Semantic Decoupling Network (VSDN) to address the problem. Our VSDN contains a Visual Decoder (VD) and a Semantic Decoder (SD) to learn purer visual and semantic feature representation respectively. Besides, a Semantic Encode…
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）
Scene text recognition is a hot research topic in computer vision. Recently, many recognition methods based on the encoder-decoder framework have been proposed, and they can handle scene texts of perspective distortion and curve shape. Nevertheless, they still face lots of challenges like image blur, uneven illumination, and incomplete characters. We argue that most encoder-decoder methods are based on local visual features without explicit global semantic information. In this work, we propose a semantics enhanced encoder-decoder framework to robustly recognize low-quality scene texts. The sem…
CMFN: Cross-Modal Fusion Network for Irregular Scene Text Recognition
Intelligent Software Research Center, Institute of Software Chinese Academy of Sciences（中国科学院软件研究所智能软件研究中心）；University of Chinese Academy of Sciences（中国科学院大学）；The Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所复杂系统认知与决策智能实验室）；State Key Laboratory of Computer Science, Institute of Software Chinese Academy of Sciences（中国科学院软件研究所计算机科学国家重点实验室）
Fraunhofer IAIS（弗劳恩霍夫智能分析和信息系统研究所）；University of Bonn（波恩大学）；University of Cologne（科隆大学）
Table extraction is an important but still unsolved problem. In this paper, we introduce a flexible and modular table extraction system. We develop two rule-based algorithms that perform the complete table recognition process, including table detection and segmentation, and support the most frequent table formats. Moreover, to incorporate the extraction of semantic information, we develop a graph-based table interpretation method. We conduct extensive experiments on the challenging table recognition benchmarks ICDAR 2013 and ICDAR 2019, achieving results competitive with state-of-the-art appro…
Recent works in the text recognition area have pushed forward the recognition results to the new horizons. But for a long time a lack of large human-labeled natural text recognition datasets has been forcing researchers to use synthetic data for training text recognition models. Even though synthetic datasets are very large (MJSynth and SynthTest, two most famous synthetic datasets, have several million images each), their diversity could be insufficient, compared to natural datasets like ICDAR and others. Fortunately, the recently released text-recognition annotation for OpenImages V5 dataset…
Scene text recognition plays an important role in many computer vision applications. The small size of available public available scene text datasets is the main challenge when training a text recognition CNN model. In this paper, we propose a CNN based Chinese text recognition algorithm. To enlarge the dataset for training the CNN model, we design a synthetic data engine for Chinese scene character generation, which generates representative character images according to the fonts use frequency of Chinese texts. As the Chinese text is more complex, the English text recognition CNN architecture…
Unconstrained text recognition is an important computer vision task, featuring a wide variety of different sub-tasks, each with its own set of challenges. One of the biggest promises of deep neural networks has been the convergence and automation of feature extractors from input raw signals, allowing for the highest possible performance with minimum required domain knowledge. To this end, we propose a data-efficient, end-to-end neural network model for generic, unconstrained text recognition. In our proposed architecture we strive for simplicity and efficiency without sacrificing recognition a…
E.SUN Financial Holding CO., LTD.（玉山金融控股股份有限公司）；National Kaohsiung Normal University（高雄师范大学）
Scene text recognition (STR) has been widely studied in academia and industry. Training a text recognition model often requires a large amount of labeled data, but data labeling can be difficult, expensive, or time-consuming, especially for Traditional Chinese text recognition. To the best of our knowledge, public datasets for Traditional Chinese text recognition are lacking. This paper presents a framework for a Traditional Chinese synthetic data engine which aims to improve text recognition model performance. We generated over 20 million synthetic data and collected over 7,000 manually label…
Recent approaches for end-to-end text spotting have achieved promising results. However, most of the current spotters were plagued by the inconsistency problem between text detection and recognition. In this work, we introduce and prove the existence of the inconsistency problem and analyze it from two aspects: (1) inconsistency of text recognition features between training and testing, and (2) inconsistency of optimization targets between text detection and recognition. To solve the aforementioned issues, we propose a differentiable Auto-Rectification Module (ARM) together with a new training…
Beihang University（北京航空航天大学）；Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）
Deep learning based methods have achieved surprising progress in Scene Text Recognition (STR), one of classic problems in computer vision. In this paper, we propose a feasible framework for multi-lingual arbitrary-shaped STR, including instance segmentation based text detection and language model based attention mechanism for text recognition. Our STR algorithm not only recognizes Latin and Non-Latin characters, but also supports arbitrary-shaped text recognition. Our method wins the championship on Scene Text Spotting Task (Latin Only, Latin and Chinese) of ICDAR2019 Robust Reading Challenge …
Extraction and recognition of Bangla text from video frame images is challenging due to complex color background, low-resolution etc. In this paper, we propose an algorithm for extraction and recognition of Bangla text form such video frames with complex background. Here, a two-step approach has been proposed. First, the text line is segmented into words using information based on line contours. First order gradient value of the text blocks are used to find the word gap. Next, a local binarization technique is applied on each word and text line is reconstructed using those words. Secondly, thi…
This paper proposes a new method, OFA-OCR, to transfer multimodal pretrained models to text recognition. Specifically, we recast text recognition as image captioning and directly transfer a unified vision-language pretrained model to the end task. Without pretraining on large-scale annotated or synthetic text recognition data, OFA-OCR outperforms the baselines and achieves state-of-the-art performance in the Chinese text recognition benchmark. Additionally, we construct an OCR pipeline with OFA-OCR, and we demonstrate that it can achieve competitive performance with the product-level API. The …
Shanghai Institute for Advanced Communication and Data Science, Shanghai University（上海大学上海先进通信与数据科学研究院）
Although recent works based on deep learning have made progress in improving recognition accuracy on scene text recognition, how to handle low-quality text images in end-to-end deep networks remains a research challenge. In this paper, we propose an Iterative Fusion based Recognizer (IFR) for low quality scene text recognition, taking advantage of refined text images input and robust feature representation. IFR contains two branches which focus on scene text recognition and low quality scene text image recovery respectively. We utilize an iterative collaboration between two branches, which can…
Automated recognition of texts in scenes has been a research challenge for years, largely due to the arbitrary variation of text appearances in perspective distortion, text line curvature, text styles and different types of imaging artifacts. The recent deep networks are capable of learning robust representations with respect to imaging artifacts and text style changes, but still face various problems while dealing with scene texts with perspective and curvature distortions. This paper presents an end-to-end trainable scene text recognition system (ESIR) that iteratively removes perspective di…
University of Edinburgh（爱丁堡大学）；Imperial College London（帝国理工学院）
Scene Text Recognition (STR) models have achieved high performance in recent years on benchmark datasets where text images are presented with minimal noise. Traditional STR recognition pipelines take a cropped image as sole input and attempt to identify the characters present. This infrastructure can fail in instances where the input image is noisy or the text is partially obscured. This paper proposes using semantic information from the greater scene to contextualise predictions. We generate semantic vectors using object tags and fuse this information into a transformer-based architecture. Th…
We present an end-to-end trainable multi-task network that addresses the problem of lexicon-free text extraction from complex documents. This network simultaneously solves the problems of text localization and text recognition and text segments are identified with no post-processing, cropping, or word grouping. A convolutional backbone and Feature Pyramid Network are combined to provide a shared representation that benefits each of three model heads: text localization, classification, and text recognition. To improve recognition accuracy, we describe a dynamic pooling mechanism that retains hi…
Zero-shot recognition aims to accurately recognize objects of unseen classes by using a shared visual-semantic mapping between the image feature space and the semantic embedding space. This mapping is learned on training data of seen classes and is expected to have transfer ability to unseen classes. In this paper, we tackle this problem by exploiting the intrinsic relationship between the semantic space manifold and the transfer ability of visual-semantic mapping. We formalize their connection and cast zero-shot recognition as a joint optimization problem. Motivated by this, we propose a nove…
U.S. Army Research Laboratory（美国陆军研究实验室）；Booz Allen Hamilton Inc.（博思艾伦汉密尔顿公司）
Many previous methods have demonstrated the importance of considering semantically relevant objects for carrying out video-based human activity recognition, yet none of the methods have harvested the power of large text corpora to relate the objects and the activities to be transferred into learning a unified deep convolutional neural network. We present a novel activity recognition CNN which co-learns the object recognition task in an end-to-end multitask learning scheme to improve upon the baseline activity recognition performance. We further improve upon the multitask learning approach by e…
This paper demonstrates a novel approach to improve face-recognition pose-invariance using semantic-segmentation features. The proposed Seg-Distilled-ID network jointly learns identification and semantic-segmentation tasks, where the segmentation task is then "distilled" (MobileNet encoder). Performance is benchmarked against three state-of-the-art encoders on a publicly available data-set emphasizing head-pose variations. Experimental evaluations show the Seg-Distilled-ID network shows notable robustness benefits, achieving 99.9% test-accuracy in comparison to 81.6% on ResNet-101, 96.1% on VG…
This paper presents a novel method for learning a pose lexicon comprising semantic poses defined by textual instructions and their associated visual poses defined by visual features. The proposed method simultaneously takes two input streams, semantic poses and visual pose candidates, and statistically learns a mapping between them to construct the lexicon. With the learned lexicon, action recognition can be cast as the problem of finding the maximum translation probability of a sequence of semantic poses given a stream of visual pose candidates. Experiments evaluating pre-trained and zero-sho…
Polytechnic University of Turin（都灵理工大学）；CINI - Consorzio Interuniversitario Nazionale per l’Informatica（意大利国家大学信息学联盟）
In this paper we address the task of visual place recognition (VPR), where the goal is to retrieve the correct GPS coordinates of a given query image against a huge geotagged gallery. While recent works have shown that building descriptors incorporating semantic and appearance information is beneficial, current state-of-the-art methods opt for a top down definition of the significant semantic content. Here we present the first VPR algorithm that learns robust global embeddings from both visual appearance and semantic content of the data, with the segmentation process being dynamically guided b…
The number of categories for action recognition is growing rapidly. It is thus becoming increasingly hard to collect sufficient training data to learn conventional models for each category. This issue may be ameliorated by the increasingly popular 'zero-shot learning' (ZSL) paradigm. In this framework a mapping is constructed between visual features and a human interpretable semantic description of each category, allowing categories to be recognised in the absence of any training data. Existing ZSL studies focus primarily on image data, and attribute-based semantic representations. In this pap…
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…
In this paper, we propose the use of a semantic image, an improved representation for video analysis, principally in combination with Inception networks. The semantic image is obtained by applying localized sparse segmentation using global clustering (LSSGC) prior to the approximate rank pooling which summarizes the motion characteristics in single or multiple images. It incorporates the background information by overlaying a static background from the window onto the subsequent segmented frames. The idea is to improve the action-motion dynamics by focusing on the region which is important for…
University of Science and Technology Beijing（北京科技大学）
Naturally, fine-grained recognition, e.g., vehicle identification or bird classification, has specific hierarchical labels, where fine categories are always harder to be classified than coarse categories. However, most of the recent deep learning based methods neglect the semantic structure of fine-grained objects and do not take advantage of the traditional fine-grained recognition techniques (e.g. coarse-to-fine classification). In this paper, we propose a novel framework with a two-branch network (coarse branch and fine branch), i.e., semantic bilinear pooling, for fine-grained recognition …
Zhejiang University（浙江大学）；Nanyang Technological University（南洋理工大学）；Tencent AI Lab（腾讯人工智能实验室）；Columbia University（哥伦比亚大学）
We propose a novel framework called Semantics-Preserving Adversarial Embedding Network (SP-AEN) for zero-shot visual recognition (ZSL), where test images and their classes are both unseen during training. SP-AEN aims to tackle the inherent problem --- semantic loss --- in the prevailing family of embedding-based ZSL, where some semantics would be discarded during training if they are non-discriminative for training classes, but could become critical for recognizing test classes. Specifically, SP-AEN prevents the semantic loss by introducing an independent visual-to-semantic space embedder whic…
Scene recognition is currently one of the top-challenging research fields in computer vision. This may be due to the ambiguity between classes: images of several scene classes may share similar objects, which causes confusion among them. The problem is aggravated when images of a particular scene class are notably different. Convolutional Neural Networks (CNNs) have significantly boosted performance in scene recognition, albeit it is still far below from other recognition tasks (e.g., object or image recognition). In this paper, we describe a novel approach for scene recognition based on an en…
Tianjin University（天津大学）；University of Wollongong（伍伦贡大学）
Zero-Shot Action Recognition (ZSAR) aims to recognize video actions that have never been seen during training. Most existing methods assume a shared semantic space between seen and unseen actions and intend to directly learn a mapping from a visual space to the semantic space. This approach has been challenged by the semantic gap between the visual space and semantic space. This paper presents a novel method that uses object semantics as privileged information to narrow the semantic gap and, hence, effectively, assist the learning. In particular, a simple hallucination network is proposed to i…
We present a system for object recognition based on a semantic graph representation, which the system can learn from image examples. This graph is based on intrinsic properties of objects such as structure and geometry, so it is more robust than the current machine learning methods that can be fooled by changing a few pixels. Current methods have proved to be powerful but brittle because they ignore the structure and semantics of the objects. We define semantics as a form of abstraction, in terms of the intrinsic properties of the object, not in terms of human perception. Thus, it can be learn…
International Institute of Information Technology, Hyderabad（海得拉巴国际信息技术学院）
Handwritten Text Recognition (HTR) is more interesting and challenging than printed text due to uneven variations in the handwriting style of the writers, content, and time. HTR becomes more challenging for the Indic languages because of (i) multiple characters combined to form conjuncts which increase the number of characters of respective languages, and (ii) near to 100 unique basic Unicode characters in each Indic script. Recently, many recognition methods based on the encoder-decoder framework have been proposed to handle such problems. They still face many challenges, such as image blur a…
Tsinghua University（清华大学）；Virginia Tech（弗吉尼亚理工大学）；University of California, Merced（加利福尼亚大学默塞德分校）
Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between the corresponding images and texts in the embedding space but do not explicitly optimize the underlying structure. Our key observation is that modeling the pairwise image-image relationship improves the discrimination ability of the embedding model. In this paper, we propose the structured discriminative and difference constraints to learn visual-semantic embeddings. First, we exploit the discriminative constraints …
In domain generalization, the knowledge learnt from one or multiple source domains is transferred to an unseen target domain. In this work, we propose a novel domain generalization approach for fine-grained scene recognition. We first propose a semantic scene descriptor that jointly captures the subtle differences between fine-grained scenes, while being robust to varying object configurations across domains. We model the occurrence patterns of objects in scenes, capturing the informativeness and discriminability of each object for each scene. We then transform such occurrences into scene prob…
University of Surrey（萨里大学）；iFlyTek-Surrey Joint Research Centre on Artificial Intelligence（讯飞-萨里人工智能联合研究中心）
Although text recognition has significantly evolved over the years, state-of-the-art (SOTA) models still struggle in the wild scenarios due to complex backgrounds, varying fonts, uncontrolled illuminations, distortions and other artefacts. This is because such models solely depend on visual information for text recognition, thus lacking semantic reasoning capabilities. In this paper, we argue that semantic information offers a complementary role in addition to visual only. More specifically, we additionally utilize semantic information by proposing a multi-stage multi-scale attentional decoder…
Fine-grained action recognition is a challenging task in computer vision. As fine-grained datasets have small inter-class variations in spatial and temporal space, fine-grained action recognition model requires good temporal reasoning and discrimination of attribute action semantics. Leveraging on CNN's ability in capturing high level spatial-temporal feature representations and Transformer's modeling efficiency in capturing latent semantics and global dependencies, we investigate two frameworks that combine CNN vision backbone and Transformer Encoder to enhance fine-grained action recognition…
Guangdong University of Technology（广东工业大学）；Sun Yat-Sen University（中山大学）
Multi-label image recognition is a fundamental yet practical task because real-world images inherently possess multiple semantic labels. However, it is difficult to collect large-scale multi-label annotations due to the complexity of both the input images and output label spaces. To reduce the annotation cost, we propose a structured semantic transfer (SST) framework that enables training multi-label recognition models with partial labels, i.e., merely some labels are known while other labels are missing (also called unknown labels) per image. The framework consists of two complementary transf…
We present a new embedding-based framework for zero-shot learning (ZSL). Most embedding-based methods aim to learn the correspondence between an image classifier (visual representation) and its class prototype (semantic representation) for each class. Motivated by the binary relevance method for multi-label classification, we propose to inversely learn the mapping between an image and a semantic classifier. Given an input image, the proposed Image-Guided Semantic Classification (IGSC) method creates a label classifier, being applied to all label embeddings to determine whether a label belongs …
We propose a novel Generalized Zero-Shot learning (GZSL) method that is agnostic to both unseen images and unseen semantic vectors during training. Prior works in this context propose to map high-dimensional visual features to the semantic domain, we believe contributes to the semantic gap. To bridge the gap, we propose a novel low-dimensional embedding of visual instances that is "visually semantic." Analogous to semantic data that quantifies the existence of an attribute in the presented instance, components of our visual embedding quantifies existence of a prototypical part-type in the pres…
The ultimate goal of video prediction is not forecasting future pixel-values given some previous frames. Rather, the end goal of video prediction is to discover valuable internal representations from the vast amount of available unlabeled video data in a self-supervised fashion for downstream tasks. One of the primary downstream tasks is interpreting the scene's semantic composition and using it for decision-making. For example, by predicting human movements, an observer can anticipate human activities and collaborate in a shared workspace. There are two main ways to achieve the same outcome, …
In this paper, we propose a novel single image action recognition algorithm which is based on the idea of semantic body part actions. Unlike existing bottom up methods, we argue that the human action is a combination of meaningful body part actions. In detail, we divide human body into five parts: head, torso, arms, hands and legs. And for each of the body parts, we define several semantic body part actions, e.g., hand holding, hand waving. These semantic body part actions are strongly related to the body actions, e.g., writing, and jogging. Based on the idea, we propose a deep neural network …
ShanghaiTech University（上海科技大学）；University of Chinese Academy of Sciences（中国科学院大学）
Zero-shot learning (ZSL) aims to recognize objects of novel classes without any training samples of specific classes, which is achieved by exploiting the semantic information and auxiliary datasets. Recently most ZSL approaches focus on learning visual-semantic embeddings to transfer knowledge from the auxiliary datasets to the novel classes. However, few works study whether the semantic information is discriminative or not for the recognition task. To tackle such problem, we propose a coupled dictionary learning approach to align the visual-semantic structures using the class prototypes, wher…
