Search

Currently, video text spotting tasks usually fall into the four-staged pipeline: detecting text regions in individual images, recognizing localized text regions frame-wisely, tracking text streams and post-processing to generate final results. However, they may suffer from the huge computational cost as well as sub-optimal results due to the interferences of low-quality text and the none-trainable pipeline strategy. In this article, we propose a fast and robust end-to-end video text spotting framework named FREE by only recognizing the localized text stream one-time instead of frame-wise recognition. Specifically, FREE first employs a well-designed spatial-temporal detector that learns text locations among video frames. Then a novel text recommender is developed to select the highest-quality text from text streams for recognizing. Here, the recommender is implemented by assembling text tracking, quality scoring and recognition into a trainable module. It not only avoids the interferences from the low-quality text but also dramatically speeds up the video text spotting. FREE unites the detector and recommender into a whole framework, and helps achieve global optimization. Besides, we collect a large scale video text dataset for promoting the video text spotting community, containing 100 videos from 21 real-life scenarios. Extensive experiments on public benchmarks show our method greatly speeds up the text spotting process, and also achieves the remarkable state-of-the-art.

This paper proposes a segregated temporal assembly recurrent (STAR) network for weakly-supervised multiple action detection. The model learns from untrimmed videos with only supervision of video-level labels and makes prediction of intervals of multiple actions. Specifically, we first assemble video clips according to class labels by an attention mechanism that learns class-variable attention weights and thus helps the noise relieving from background or other actions. Secondly, we build temporal relationship between actions by feeding the assembled features into an enhanced recurrent neural network. Finally, we transform the output of recurrent neural network into the corresponding action distribution. In order to generate more precise temporal proposals, we design a score term called segregated temporal gradient-weighted class activation mapping (ST-GradCAM) fused with attention weights. Experiments on THUMOS'14 and ActivityNet1.3 datasets show that our approach outperforms the state-of-the-art weakly-supervised method, and performs at par with the fully-supervised counterparts., Comment: Accepted to Proc. AAAI Conference on Artificial Intelligence 2019

Since real-world ubiquitous documents (e.g., invoices, tickets, resumes and leaflets) contain rich information, automatic document image understanding has become a hot topic. Most existing works decouple the problem into two separate tasks, (1) text reading for detecting and recognizing texts in images and (2) information extraction for analyzing and extracting key elements from previously extracted plain text. However, they mainly focus on improving information extraction task, while neglecting the fact that text reading and information extraction are mutually correlated. In this paper, we propose a unified end-to-end text reading and information extraction network, where the two tasks can reinforce each other. Specifically, the multimodal visual and textual features of text reading are fused for information extraction and in turn, the semantics in information extraction contribute to the optimization of text reading. On three real-world datasets with diverse document images (from fixed layout to variable layout, from structured text to semi-structured text), our proposed method significantly outperforms the state-of-the-art methods in both efficiency and accuracy., Accepted to ACM MM2020. Code is available at https://davar-lab.github.io/publication.html or https://github.com/hikopensource/DAVAR-Lab-OCR

The task of matching observations of the same person in disjoint views captured by non-overlapping cameras is known as the person re-identification problem. It is challenging owing to low-quality images, inter-object occlusions, and variations in illumination, viewpoints and poses. Unlike previous approaches that learn Mahalanobis-like distance metrics, we propose a novel approach based on dictionary learning that takes the advances of sparse coding of discriminatingly and cross-view invariantly encoding features representing different people. Firstly, we propose a robust and discriminative feature extraction method of different feature levels. The feature representations are projected to a lower computation common subspace. Secondly, we learn a single cross-view invariant dictionary for each feature level for different camera views and a fusion strategy is utilized to generate the final matching results. Experimental statistics show the superior performance of our approach by comparing with state-of-the-art methods on two publicly available benchmark datasets VIPeR and PRID 2011.

Many approaches have recently been proposed to detect irregular scene text and achieved promising results. However, their localization results may not well satisfy the following text recognition part mainly because of two reasons: 1) recognizing arbitrary shaped text is still a challenging task, and 2) prevalent non-trainable pipeline strategies between text detection and text recognition will lead to suboptimal performances. To handle this incompatibility problem, in this paper we propose an end-to-end trainable text spotting approach named Text Perceptron. Concretely, Text Perceptron first employs an efficient segmentation-based text detector that learns the latent text reading order and boundary information. Then a novel Shape Transform Module (abbr. STM) is designed to transform the detected feature regions into regular morphologies without extra parameters. It unites text detection and the following recognition part into a whole framework, and helps the whole network achieve global optimization. Experiments show that our method achieves competitive performance on two standard text benchmarks, i.e., ICDAR 2013 and ICDAR 2015, and also obviously outperforms existing methods on irregular text benchmarks SCUT-CTW1500 and Total-Text., Accepted by AAAI2020. Code is available at https://davar-lab.github.io/publication.html or https://github.com/hikopensource/DAVAR-Lab-OCR

Temporal action localization is an important yet challenging research topic due to its various applications. Since the frame-level or segment-level annotations of untrimmed videos require amounts of labor expenditure, studies on the weakly-supervised action detection have been springing up. However, most of existing frameworks rely on Class Activation Sequence (CAS) to localize actions by minimizing the video-level classification loss, which exploits the most discriminative parts of actions but ignores the minor regions. In this paper, we propose a novel weakly-supervised framework by adversarial learning of two modules for eliminating such demerits. Specifically, the first module is designed as a well-designed Seeded Sequence Growing (SSG) Network for progressively extending seed regions (namely the highly reliable regions initialized by a CAS-based framework) to their expected boundaries. The second module is a specific classifier for mining trivial or incomplete action regions, which is trained on the shared features after erasing the seeded regions activated by SSG. In this way, a whole network composed of these two modules can be trained in an adversarial manner. The goal of the adversary is to mine features that are difficult for the action classifier. That is, erasion from SSG will force the classifier to discover minor or even new action regions on the input feature sequence, and the classifier will drive the seeds to grow, alternately. At last, we could obtain the action locations and categories from the well-trained SSG and the classifier. Extensive experiments on two public benchmarks THUMOS'14 and ActivityNet1.3 demonstrate the impressive performance of our proposed method compared with the state-of-the-arts., To be appeared in ACM MM2019

Scene text recognition has been a hot research topic in computer vision due to its various applications. The state of the art is the attention-based encoder-decoder framework that learns the mapping between input images and output sequences in a purely data-driven way. However, we observe that existing attention-based methods perform poorly on complicated and/or low-quality images. One major reason is that existing methods cannot get accurate alignments between feature areas and targets for such images. We call this phenomenon "attention drift". To tackle this problem, in this paper we propose the FAN (the abbreviation of Focusing Attention Network) method that employs a focusing attention mechanism to automatically draw back the drifted attention. FAN consists of two major components: an attention network (AN) that is responsible for recognizing character targets as in the existing methods, and a focusing network (FN) that is responsible for adjusting attention by evaluating whether AN pays attention properly on the target areas in the images. Furthermore, different from the existing methods, we adopt a ResNet-based network to enrich deep representations of scene text images. Extensive experiments on various benchmarks, including the IIIT5k, SVT and ICDAR datasets, show that the FAN method substantially outperforms the existing methods., Comment: Revise the description of IC15 datasets (1811 samples)

Person re-identification is known as matching an individual captured in one or more cameras using a gallery of provided candidates from a different camera view. It is a hard task owing to variations in illumination, viewpoints, poses and small number of annotated training individuals. For obtaining the proper distance metrics, we propose a novel approach based on dictionary learning. Our method decomposes the dictionary into a view-invariant dictionary and a view-specific one in order to overcome the limited performance resulting from the balance between the discrimination and cross-view invariant ability. We present this multi-task joint dictionary learning method and show the competitive performance by comparing our results with state-of-the-art methods on two publicly available datasets.