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 effectively alleviate the impact of low quality input. A feature fusion module is proposed to strengthen the feature representation of the two branches, where the features from the Recognizer are Fused with image Restoration branch, referred to as RRF. Without changing the recognition network structure, extensive quantitative and qualitative experimental results show that the proposed method significantly outperforms the baseline methods in boosting the recognition accuracy of benchmark datasets and low resolution images in TextZoom dataset.
In recent years, synthetic speech generated by advanced text-to-speech (TTS) and voice conversion (VC) systems has caused great harms to automatic speaker verification (ASV) systems, urging us to design a synthetic speech detection system to protect ASV systems. In this paper, we propose a new speech anti-spoofing model named ResWavegram-Resnet (RW-Resnet). The model contains two parts, Conv1D Resblocks and backbone Resnet34. The Conv1D Resblock is based on the Conv1D block with a residual connection. For the first part, we use the raw waveform as input and feed it to the stacked Conv1D Resblocks to get the ResWavegram. Compared with traditional methods, ResWavegram keeps all the information from the audio signal and has a stronger ability in extracting features. For the second part, the extracted features are fed to the backbone Resnet34 for the spoofed or bonafide decision. The ASVspoof2019 logical access (LA) corpus is used to evaluate our proposed RW-Resnet. Experimental results show that the RW-Resnet achieves better performance than other state-of-the-art anti-spoofing models, which illustrates its effectiveness in detecting synthetic speech attacks.
Depth completion aims to generate a dense depth map from the sparse depth map and aligned RGB image. However, current depth completion methods use extremely expensive 64-line LiDAR(about $100,000) to obtain sparse depth maps, which will limit their application scenarios. Compared with the 64-line LiDAR, the single-line LiDAR is much less expensive and much more robust. Therefore, we propose a method to tackle the problem of single-line depth completion, in which we aim to generate a dense depth map from the single-line LiDAR info and the aligned RGB image. A single-line depth completion dataset is proposed based on the existing 64-line depth completion dataset(KITTI). A network called Semantic Guided Two-Branch Network(SGTBN) which contains global and local branches to extract and fuse global and local info is proposed for this task. A Semantic guided depth upsampling module is used in our network to make full use of the semantic info in RGB images. Except for the usual MSE loss, we add the virtual normal loss to increase the constraint of high-order 3D geometry in our network. Our network outperforms the state-of-the-art in the single-line depth completion task. Besides, compared with the monocular depth estimation, our method also has significant advantages in precision and model size.
With the rapid development of indoor location-based services (LBSs), the demand for accurate localization keeps growing as well. To meet this demand, we propose an indoor localization algorithm based on graph convolutional network (GCN). We first model access points (APs) and the relationships between them as a graph, and utilize received signal strength indication (RSSI) to make up fingerprints. Then the graph and the fingerprint will be put into GCN for feature extraction, and get classification by multilayer perceptron (MLP).In the end, experiments are performed under a 2D scenario and 3D scenario with floor prediction. In the 2D scenario, the mean distance error of GCN-based method is 11m, which improves by 7m and 13m compare with DNN-based and CNN-based schemes respectively. In the 3D scenario, the accuracy of predicting buildings and floors are up to 99.73% and 93.43% respectively. Moreover, in the case of predicting floors and buildings correctly, the mean distance error is 13m, which outperforms DNN-based and CNN-based schemes, whose mean distance errors are 34m and 26m respectively.
Text detection/localization, as an important task in computer vision, has witnessed substantialadvancements in methodology and performance with convolutional neural networks. However, the vastmajority of popular methods use rectangles or quadrangles to describe text regions. These representationshave inherent drawbacks, especially relating to dense adjacent text and loose regional text boundaries,which usually cause difficulty detecting arbitrarily shaped text. In this paper, we propose a novel text regionrepresentation method, with a robust pipeline, which can precisely detect dense adjacent text instances witharbitrary shapes. We consider a text instance to be composed of an adaptive central text region mask anda corresponding expanding ratio between the central text region and the full text region. More specifically,our pipeline generates adaptive central text regions and corresponding expanding ratios with a proposedtraining strategy, followed by a new proposed post-processing algorithm which expands central text regionsto the complete text instance with the corresponding expanding ratios. We demonstrated that our new textregion representation is effective, and that the pipeline can precisely detect closely adjacent text instances ofarbitrary shapes. Experimental results on common datasets demonstrate superior performance o
Recently, video scene text detection has received increasing attention due to its comprehensive applications. However, the lack of annotated scene text video datasets has become one of the most important problems, which hinders the development of video scene text detection. The existing scene text video datasets are not large-scale due to the expensive cost caused by manual labeling. In addition, the text instances in these datasets are too clear to be a challenge. To address the above issues, we propose a tracking based semi-automatic labeling strategy for scene text videos in this paper. We get semi-automatic scene text annotation by labeling manually for the first frame and tracking automatically for the subsequent frames, which avoid the huge cost of manual labeling. Moreover, a paired low-quality scene text video dataset named Text-RBL is proposed, consisting of raw videos, blurry videos, and low-resolution videos, labeled by the proposed convenient semi-automatic labeling strategy. Through an averaging operation and bicubic down-sampling operation over the raw videos, we can efficiently obtain blurry videos and low-resolution videos paired with raw videos separately. To verify the effectiveness of Text-RBL, we propose a baseline model combined with the text detector and tracker for video scene text detection. Moreover, a failure detection scheme is designed to alleviate the baseline model drift issue caused by complex scenes. Extensive experiments demonstrate that Text-RBL with paired low-quality videos labeled by the semi-automatic method can significantly improve the performance of the text detector in low-quality scenes.
Face Anti-spoofing (FAS) is a challenging problem due to complex serving scenarios and diverse face presentation attack patterns. Especially when captured images are low-resolution, blurry, and coming from different domains, the performance of FAS will degrade significantly. The existing multi-modal FAS datasets rarely pay attention to the cross-domain problems under deployment scenarios, which is not conducive to the study of model performance. To solve these problems, we explore the fine-grained differences between multi-modal cameras and construct a cross-domain multi-modal FAS dataset under surveillance scenarios called GREAT-FASD-S. Besides, we propose an Attention based Face Anti-spoofing network with Feature Augment (AFA) to solve the FAS towards low-quality face images. It consists of the depthwise separable attention module (DAM) and the multi-modal based feature augment module (MFAM). Our model can achieve state-of-the-art performance on the CASIA-SURF dataset and our proposed GREAT-FASD-S dataset.
Precise indoor localization is one of the key requirements for fifth Generation (5G) and beyond, concerning various wireless communication systems, whose applications span different vertical sectors. Although many highly accurate methods based on signal fingerprints have been lately proposed for localization, their vast majority faces the problem of degrading performance when deployed in indoor systems, where the propagation environment changes rapidly. In order to address this issue, the crowdsourcing approach has been adopted, according to which the fingerprints are frequently updated in the respective database via user reporting. However, the late crowdsourcing techniques require precise indoor floor plans and fail to provide satisfactory accuracy. In this paper, we propose a low-complexity self-calibrating indoor crowdsourcing localization system that combines historical with frequently updated fingerprints for high precision user positioning. We present a multi-kernel transfer learning approach which exploits the inner relationship between the original and updated channel measurements. Our indoor laboratory experimental results with the proposed approach and using Nexus 5 smartphones at 2.4GHz with 20MHz bandwidth have shown the feasibility of about one meter level accuracy with a reasonable fingerprint update overhead.
Spatial Description Resolution, as a language-guided localization task, is proposed for target location in a panoramic street view, given corresponding language descriptions. Explicitly characterizing an object-level relationship while distilling spatial relationships are currently absent but crucial to this task. Mimicking humans, who sequentially traverse spatial relationship words and objects with a first-person view to locate their target, we propose a novel spatial relationship induced (SIRI) network. Specifically, visual features are firstly correlated at an implicit object-level in a projected latent space; then they are distilled by each spatial relationship word, resulting in each differently activated feature representing each spatial relationship. Further, we introduce global position priors to fix the absence of positional information, which may result in global positional reasoning ambiguities. Both the linguistic and visual features are concatenated to finalize the target localization. Experimental results on the Touchdown show that our method is around 24\% better than the state-of-the-art method in terms of accuracy, measured by an 80-pixel radius. Our method also generalizes well on our proposed extended dataset collected using the same settings as Touchdown.