Existing methods for scene text detection can be divided into two paradigms: segmentation-based and anchor-based. While Segmentation-based methods are well-suited for irregular shapes, they struggle with compact or overlapping layouts. Conversely, anchor-based approaches excel for complex layouts but suffer from irregular shapes. To strengthen their merits and overcome their respective demerits, we propose a Complementary Proposal Network (CPN) that seamlessly and parallelly integrates semantic and geometric information for superior performance. The CPN comprises two efficient networks for proposal generation: the Deformable Morphology Semantic Network, which generates semantic proposals employing an innovative deformable morphological operator, and the Balanced Region Proposal Network, which produces geometric proposals with pre-defined anchors. To further enhance the complementarity, we introduce an Interleaved Feature Attention module that enables semantic and geometric features to interact deeply before proposal generation. By leveraging both complementary proposals and features, CPN outperforms state-of-the-art approaches with significant margins under comparable computation cost. Specifically, our approach achieves improvements of 3.6%, 1.3% and 1.0% on challenging benchmarks ICDAR19-ArT, IC15, and MSRA-TD500, respectively. Code for our method will be released.

Contrastive learning-based video-language representation learning approaches, e.g., CLIP, have achieved outstanding performance, which pursue semantic interaction upon pre-defined video-text pairs. To clarify this coarse-grained global interaction and move a step further, we have to encounter challenging shell-breaking interactions for fine-grained cross-modal learning. In this paper, we creatively model video-text as game players with multivariate cooperative game theory to wisely handle the uncertainty during fine-grained semantic interaction with diverse granularity, flexible combination, and vague intensity. Concretely, we propose Hierarchical Banzhaf Interaction (HBI) to value possible correspondence between video frames and text words for sensitive and explainable cross-modal contrast. To efficiently realize the cooperative game of multiple video frames and multiple text words, the proposed method clusters the original video frames (text words) and computes the Banzhaf Interaction between the merged tokens. By stacking token merge modules, we achieve cooperative games at different semantic levels. Extensive experiments on commonly used text-video retrieval and video-question answering bench-marks with superior performances justify the efficacy of our HBI. More encouragingly, it can also serve as a visualization tool to promote the understanding of cross-modal interaction, which have a far-reaching impact on the community. Project page is available at https://jpthu17.github.io/HBI/.

Recently, numerous unsupervised cross-modal hashing methods have been proposed to deal the image-text retrieval tasks for the unlabeled cross-modal data. However, when these methods learn to generate hash codes, almost all of them lack modality-interaction in the following two aspects: 1) The instance similarity matrix used to guide the hashing networks training is constructed without image-text interaction, which fails to capture the fine-grained cross-modal cues to elaborately characterize the intrinsic semantic similarity among the datapoints. 2) The binary codes used for quantization loss are inferior because they are generated by directly quantizing a simple combination of continuous hash codes from different modalities without the interaction among these continuous hash codes. Such problems will cause the generated hash codes to be of poor quality and degrade the retrieval performance. Hence, in this paper, we propose a novel Unsupervised Cross-modal Hashing with Modality-interaction, termed UCHM. Specifically, by optimizing a novel hash-similarity-friendly loss, a modality-interaction-enabled (MIE) similarity generator is first trained to generate a superior MIE similarity matrix for the training set. Then, the generated MIE similarity matrix is utilized as guiding information to train the deep hashing networks. Furthermore, during the process of training the hashing networks, a novel bit-selection module is proposed to generate high-quality unified binary codes for the quantization loss with the interaction among continuous codes from different modalities, thereby further enhancing the retrieval performance. Extensive experiments on two widely used datasets show that the proposed UCHM outperforms state-of-the-art techniques on cross-modal retrieval tasks.

Hashing technology has been widely used in image retrieval due to its computational and storage efficiency. Recently, deep unsupervised hashing methods have attracted increasing attention due to the high cost of human annotations in the real world and the superiority of deep learning technology. However, most deep unsupervised hashing methods usually pre-compute a similarity matrix to model the pairwise relationship in the pre-trained feature space. Then this similarity matrix would be used to guide hash learning, in which most of the data pairs are treated equivalently. The above process is confronted with the following defects:1) The pre-computed similarity matrix is inalterable and disconnected from the hash learning process, which cannot explore the underlying semantic information. 2) The informative data pairs may be buried by the large number of less-informative data pairs. To solve the aforementioned problems, we propose a Deep Self-Adaptive Hashing(DSAH) model to adaptively capture the semantic information with two special designs: Adaptive Neighbor Discovery(AND) and Pairwise Information Content(PIC). Firstly, we adopt the AND to initially construct a neighborhood-based similarity matrix, and then refine this initial similarity matrix with a novel update strategy to further investigate the semantic structure behind the learned representation. Secondly, we measure the priorities of data pairs with PIC and assign adaptive weights to them, which is relies on the assumption that more dissimilar data pairs contain more discriminative information for hash learning. Extensive experiments on several datasets demonstrate that the above two technologies facilitate the deep hashing model to achieve superior performance.

The requiring of large amounts of annotated training data has become a common constraint on various deep learning systems. In this paper, we propose a weakly supervised scene text detection method (WeText) that trains robust and accurate scene text detection models by learning from unannotated or weakly annotated data. With a "light" supervised model trained on a small fully annotated dataset, we explore semi-supervised and weakly supervised learning on a large unannotated dataset and a large weakly annotated dataset, respectively. For the unsupervised learning, the light supervised model is applied to the unannotated dataset to search for more character training samples, which are further combined with the small annotated dataset to retrain a superior character detection model. For the weakly supervised learning, the character searching is guided by high-level annotations of words/text lines that are widely available and also much easier to prepare. In addition, we design an unified scene character detector by adapting regression based deep networks, which greatly relieves the error accumulation issue that widely exists in most traditional approaches. Extensive experiments across different unannotated and weakly annotated datasets show that the scene text detection performance can be clearly boosted under both scenarios, where the weakly supervised learning can achieve the state-of-the-art performance by using only 229 fully annotated scene text images.

The prevalent scene text detection approach follows four sequential steps comprising character candidate detection, false character candidate removal, text line extraction, and text line verification. However, errors occur and accumulate throughout each of these sequential steps which often lead to low detection performance. To address these issues, we propose a unified scene text detection system, namely Text Flow, by utilizing the minimum cost (min-cost) flow network model. With character candidates detected by cascade boosting, the min-cost flow network model integrates the last three sequential steps into a single process which solves the error accumulation problem at both character level and text line level effectively. The proposed technique has been tested on three public datasets, i.e, ICDAR2011 dataset, ICDAR2013 dataset and a multilingual dataset and it outperforms the state-of-the-art methods on all three datasets with much higher recall and F-score. The good performance on the multilingual dataset shows that the proposed technique can be used for the detection of texts in different languages.

Text segmentation provides important clues for the accurate identification of character locations and the analysis of character properties such as shape estimation and texture synthesis. In this paper, we propose a robust text segmentation method that employs Markov Random Field (MRF) and use graph cut algorithms to solve the energy minimization problem. To effectively select accurate seeds to boost the text segmentation performance, stroke feature transform is adopted to robustly identify text seeds and text edges. Background seeds are obtained near the text edges in order to well preserve the text boundaries. The energy functions are defined as an MRF consisting of data energy and smoothness energy which can be efficiently solved by graph cut algorithms. One distinctive property of the proposed technique is that it can identify more distinctive seeds so that only one cut is needed to well separate the text regions from the background, hence much faster than the existing iterative graph cut approach. Experiments on ICDAR 2003 and ICDAR 2011 datasets show that the proposed technique obtains superior performance on both pixel level and atom level segmentation.

Because of the unconstrained environment of scene text, traditional Optical Character Recognition (OCR) engines fail to achieve satisfactory results. In this paper, we propose a new technique which employs first order Histogram of Oriented Gradient (HOG) through a spatial pyramid. The spatial pyramid can encode the relative spatial layout of the character parts while HOG can only include the local image shape without spatial relation. A feature descriptor combining these two can extracts more useful information from the image for text recognition. Chi-square kernel based Support Vector Machine is employed for classification based on the proposed feature descriptors. The method is tested on three public datasets, namely ICDAR2003 robust reading dataset, Street View Text (SVT) dataset and IIIT 5K-word dataset. The results on these dataset are comparable with the state-of-the-art methods.

Recognition of characters in natural images is a challenging task due to the complex background, variations of text size and perspective distortion, etc. Traditional optical character recognition (OCR) engine cannot perform well on those unconstrained text images. A novel technique is proposed in this paper that makes use of convolutional cooccurrence histogram of oriented gradient (ConvCoHOG), which is more robust and discriminative than both the histogram of oriented gradient (HOG) and the co-occurrence histogram of oriented gradients (CoHOG). In the proposed technique, a more informative feature is constructed by exhaustively extracting features from every possible image patches within character images. Experiments on two public datasets including the ICDAr 2003 Robust Reading character dataset and the Street View Text (SVT) dataset, show that our proposed character recognition technique obtains superior performance compared with state-of-the-art techniques.

The segmentation of scene text from the image background has shown great importance in scene text recognition. In this paper, we propose a multi-level MSER technology that identifies the best-quality text candidates from a set of stable regions that are extracted from different color channel images. In order to identify the best-quality text candidates, a segmentation score is defined which exploits four measures to evaluate the text probability of each stable region including: 1) Stroke width that measures the small stroke width variation of the text, 2) Boundary curvature that measures the smoothness of the stable region boundary, 3) Character confidence that measures the likelihood of a stable region being text based on a pre-trained support vector classifier, 4) Color constancy that measures the global color consistency of each selected text candidate. Finally, the MSERs with the best segmentation score from each channel are combined to form the final segmentation. The proposed method is evaluated on the ICDAR2003 and SVT datasets and experiments show that it outperforms both popular document image binarization methods and state of the art scene text segmentation methods.

This paper presents an approach to text recognition in natural scene images. Unlike most existing works which assume that texts are horizontal and frontal parallel to the image plane, our method is able to recognize perspective texts of arbitrary orientations. For individual character recognition, we adopt a bag-of-key points approach, in which Scale Invariant Feature Transform (SIFT) descriptors are extracted densely and quantized using a pre-trained vocabulary. Following [1, 2], the context information is utilized through lexicons. We formulate word recognition as finding the optimal alignment between the set of characters and the list of lexicon words. Furthermore, we introduce a new dataset called StreetViewText-Perspective, which contains texts in street images with a great variety of viewpoints. Experimental results on public datasets and the proposed dataset show that our method significantly outperforms the state-of-the-art on perspective texts of arbitrary orientations.

Document Image Binarization is a technique to segment text out from the background region of a document image, which is a challenging task due to high intensity variations of the document foreground and background. Recently, a series of document image binarization contests (DIBCOs) had been held that have drawn great research interest in this area. Several document binarization techniques have been proposed and achieve great performance on the contest datasets. However, those proposed techniques may not perform well on all kinds of degraded document images because it is difficult to design a classification method that correctly models the non-uniform degraded document background and text foreground simultaneously. In this paper, we propose a self learning classification framework that combines binary outputs of different binarization methods. The proposed framework makes used of the sparse representation to re-classify the document pixels and produces a better binary results. The experimental results on the recent DIBCO contests show the great performance and robustness of our proposed framework on different kinds of degraded document images.

Scene text recognition is a fundamental step in End-to-End applications where traditional optical character recognition (OCR) systems often fail to produce satisfactory results. This paper proposes a technique that uses co-occurrence histogram of oriented gradients (Co-HOG) to recognize the text in scenes. Compared with histogram of oriented gradients (HOG), Co-HOG is a more powerful tool that captures spatial distribution of neighboring orientation pairs instead of just a single gradient orientation. At the same time, it is more efficient compared with HOG and therefore more suitable for real-time applications. The proposed scene text recognition technique is evaluated on ICDAR2003 character dataset and Street View Text (SVT) dataset. Experiments show that the Co-HOG based technique clearly outperforms state-of-the-art techniques that use HOG, Scale Invariant Feature Transform (SIFT), and Maximally Stable Extremal Regions (MSER).

Character shape reconstruction for the scene character is challenging and interesting because scene character usually suffers from uneven illumination, complex background, perspective distortion. To address such ill conditions, we propose to utilize Histogram Gradient Division (HGD) and Reverse Gradient Orientation (RGO) to select Candidate Text Pixels (CTPs) for a given input character. Ring Radius Transform is applied on each pixel in a CTP image to obtain radius map where each pixel is assigned a value which is the radius to the nearest CTP. Candidate medial axis pixels are those having maximum radius values in their neighborhoods. We find such pixels on horizontal, vertical, principal diagonal and secondary diagonal directions to determine the respective medial axis pixels. The union of all medial axis pixels at each pixel location is considered as a candidate medial axis pixel of the character. Then color difference and k-means clustering are employed to eliminate false candidate medial axis. The potential medial axis values are used to reconstruct the shape of the character. The method is tested on 1025 characters of complex foreground and background from ICDAR 2003 dataset in terms of shape reconstruction and recognition rate. Experimental results demonstrate the effectiveness of our proposed method for complex foreground and background characters in terms of character recognition rate and reconstruction error.