Scene text spotting is a challenging task, especially for inverse-like scene text, which has complex layouts, e.g., mirrored, symmetrical, or retro-flexed. In this paper, we propose a unified end-to-end trainable inverse-like antagonistic text spotting framework dubbed IATS, which can effectively spot inverse-like scene texts without sacrificing general ones. Specifically, we propose an innovative reading-order estimation module (REM) that extracts reading-order information from the initial text boundary generated by an initial boundary module (IBM). To optimize and train REM, we propose a joint reading-order estimation loss consisting of a classification loss, an orthogonality loss, and a distribution loss. With the help of IBM, we can divide the initial text boundary into two symmetric control points and iteratively refine the new text boundary using a lightweight boundary refinement module (BRM) for adapting to various shapes and scales. To alleviate the incompatibility between text detection and recognition, we propose a dynamic sampling module (DSM) with a thin-plate spline that can dynamically sample appropriate features for recognition in the detected text region. Without extra supervision, the DSM can proactively learn to sample appropriate features for text recognition through the gradient returned by the recognition module. Extensive experiments on both challenging scene text and inverse-like scene text datasets demonstrate that our method achieves superior performance both on irregular and inverse-like text spotting.
Attention-based encoder-decoder (AED) models have shown impressive performance in ASR. However, most existing AED methods neglect to simultaneously leverage both acoustic and semantic features in decoder, which is crucial for generating more accurate and informative semantic states. In this paper, we propose an Acoustic and Semantic Cooperative Decoder (ASCD) for ASR. In particular, unlike vanilla decoders that process acoustic and semantic features in two separate stages, ASCD integrates them cooperatively. To prevent information leakage during training, we design a Causal Multimodal Mask. Moreover, a variant Semi-ASCD is proposed to balance accuracy and computational cost. Our proposal is evaluated on the publicly available AISHELL-1 and aidatatang_200zh datasets using Transformer, Conformer, and Branchformer as encoders, respectively. The experimental results show that ASCD significantly improves the performance by leveraging both the acoustic and semantic information cooperatively.
With the prosperity of the video surveillance, multiple visual sensors have been applied for an accurate localization of pedestrians in a specific area, which facilitate various applications like intelligent safety or new retailing. However, previous methods rely on the supervision from the human annotated pedestrian positions in every video frame and camera view, which is a heavy burden in addition to the necessary camera calibration and synchronization. Therefore, we propose in this paper an Unsupervised Multi-view Pedestrian Detection approach (UMPD) to eliminate the need of annotations to learn a multi-view pedestrian detector. 1) Firstly, Semantic-aware Iterative Segmentation (SIS) is proposed to extract discriminative visual representations of the input images from different camera views via an unsupervised pretrained model, then convert them into 2D segments of pedestrians, based on our proposed iterative Principal Component Analysis and the zero-shot semantic classes from the vision-language pretrained models. 2) Secondly, we propose Vertical-aware Differential Rendering (VDR) to not only learn the densities and colors of 3D voxels by the masks of SIS, images and camera poses, but also constraint the voxels to be vertical towards the ground plane, following the physical characteristics of pedestrians. 3) Thirdly, the densities of 3D voxels learned by VDR are projected onto Bird-Eyes-View as the final detection results. Extensive experiments on popular multi-view pedestrian detection benchmarks, i.e., Wildtrack and MultiviewX, show that our proposed UMPD approach, as the first unsupervised method to our best knowledge, performs competitively with the previous state-of-the-art supervised techniques. Code will be available.
Detecting pedestrians accurately in urban scenes is significant for realistic applications like autonomous driving or video surveillance. However, confusing human-like objects often lead to wrong detections, and small scale or heavily occluded pedestrians are easily missed due to their unusual appearances. To address these challenges, only object regions are inadequate, thus how to fully utilize more explicit and semantic contexts becomes a key problem. Meanwhile, previous context-aware pedestrian detectors either only learn latent contexts with visual clues, or need laborious annotations to obtain explicit and semantic contexts. Therefore, we propose in this paper a novel approach via Vision-Language semantic self-supervision for context-aware Pedestrian Detection (VLPD) to model explicitly semantic contexts without any extra annotations. Firstly, we propose a self-supervised Vision-Language Semantic (VLS) segmentation method, which learns both fully-supervised pedestrian detection and contextual segmentation via self-generated explicit labels of semantic classes by vision-language models. Furthermore, a self-supervised Prototypical Semantic Contrastive (PSC) learning method is proposed to better discriminate pedestrians and other classes, based on more explicit and semantic contexts obtained from VLS. Extensive experiments on popular benchmarks show that our proposed VLPD achieves superior performances over the previous state-of-the-arts, particularly under challenging circumstances like small scale and heavy occlusion. Code is available at https://github.com/lmy98129/VLPD.
Arbitrary shape text detection is a challenging task due to the significantly varied sizes and aspect ratios, arbitrary orientations or shapes, inaccurate annotations, etc. Due to the scalability of pixel-level prediction, segmentation-based methods can adapt to various shape texts and hence attracted considerable attention recently. However, accurate pixel-level annotations of texts are formidable, and the existing datasets for scene text detection only provide coarse-grained boundary annotations. Consequently, numerous misclassified text pixels or background pixels inside annotations always exist, degrading the performance of segmentation-based text detection methods. Generally speaking, whether a pixel belongs to text or not is highly related to the distance with the adjacent annotation boundary. With this observation, in this paper, we propose an innovative and robust segmentation-based detection method via probability maps for accurately detecting text instances. To be concrete, we adopt a Sigmoid Alpha Function (SAF) to transfer the distances between boundaries and their inside pixels to a probability map. However, one probability map can not cover complex probability distributions well because of the uncertainty of coarse-grained text boundary annotations. Therefore, we adopt a group of probability maps computed by a series of Sigmoid Alpha Functions to describe the possible probability distributions. In addition, we propose an iterative model to learn to predict and assimilate probability maps for providing enough information to reconstruct text instances. Finally, simple region growth algorithms are adopted to aggregate probability maps to complete text instances. Experimental results demonstrate that our method achieves state-of-the-art performance in terms of detection accuracy on several benchmarks.
Arbitrary shape text detection is a challenging task due to its complexity and variety, e.g, various scales, random rotations, and curve shapes. In this paper, we propose an arbitrary shape text detector with a boundary transformer, which can accurately and directly locate text boundaries without any post-processing. Our method mainly consists of a boundary proposal module and an iteratively optimized boundary transformer module. The boundary proposal module consisting of multi-layer dilated convolutions will compute important prior information (including classification map, distance field, and direction field) for generating coarse boundary proposals meanwhile guiding the optimization of boundary transformer. The boundary transformer module adopts an encoder-decoder structure, in which the encoder is constructed by multi-layer transformer blocks with residual connection while the decoder is a simple multi-layer perceptron network (MLP). Under the guidance of prior information, the boundary transformer module will gradually refine the coarse boundary proposals via boundary deformation in an iterative manner. Furthermore, we propose a novel boundary energy loss (BEL) which introduces an energy minimization constraint and an energy monotonically decreasing constraint for every boundary optimization step. Extensive experiments on publicly available and challenging datasets demonstrate the state-of-the-art performance and promising efficiency of our method.
In object detection, non-maximum suppression (NMS) methods are extensively adopted to remove horizontal duplicates of detected dense boxes for generating final object instances. However, due to the degraded quality of dense detection boxes and not explicit exploration of the context information, existing NMS methods via simple intersection-over-union (IoU) metrics tend to underperform on multi-oriented and long-size objects detection. Distinguishing with general NMS methods via duplicate removal, we propose a novel graph fusion network, named GFNet, for multi-oriented object detection. Our GFNet is extensible and adaptively fuse dense detection boxes to detect more accurate and holistic multi-oriented object instances. Specifically, we first adopt a locality-aware clustering algorithm to group dense detection boxes into different clusters. We will construct an instance sub-graph for the detection boxes belonging to one cluster. Then, we propose a graph-based fusion network via Graph Convolutional Network (GCN) to learn to reason and fuse the detection boxes for generating final instance boxes. Extensive experiments both on public available multi-oriented text datasets (including MSRA-TD500, ICDAR2015, ICDAR2017-MLT) and multi-oriented object datasets (DOTA) verify the effectiveness and robustness of our method against general NMS methods in multi-oriented object detection.
The open-set text recognition task is an emerging challenge that requires an extra capability to cognize novel characters during evaluation. We argue that a major cause of the limited performance for current methods is the confounding effect of contextual information over the visual information of individual characters. Under open-set scenarios, the intractable bias in contextual information can be passed down to visual information, consequently impairing the classification performance. In this paper, a Character-Context Decoupling framework is proposed to alleviate this problem by separating contextual information and character-visual information. Contextual information can be decomposed into temporal information and linguistic information. Here, temporal information that models character order and word length is isolated with a detached temporal attention module. Linguistic information that models n-gram and other linguistic statistics is separated with a decoupled context anchor mechanism. A variety of quantitative and qualitative experiments show that our method achieves promising performance on open-set, zero-shot, and close-set text recognition datasets.
Scene text recognition is a popular topic and extensively used in the industry. Although many methods have achieved satisfactory performance for the close-set text recognition challenges, these methods lose feasibility in open-set scenarios, where collecting data or retraining models for novel characters is too expensive. E.g., annotating samples for foreign languages can be expensive, whereas retraining the model each time a "novel" character is discovered from historical documents also costs time and resources. In this paper, we introduce and formulate a new task, i.e., the open-set text recognition task, which demands the capability to spot and cognize novel characters without retraining. Here, we propose a label-to-prototype learning framework that fulfills the new requirements in the proposed task. Specifically, novel characters are mapped to their corresponding prototypes with a Label-to-Prototype Learning module. The module is trained on seen labels and holds generalization capability for generating class centers for novel characters without retraining. The framework also implements rejection capability over out-of-set characters, which allows spotting unknown characters during the evaluation process. Extensive experiments show that our method achieves promising performance on a variety of zero-shot, close-set, and open-set text recognition datasets.
Segmentation-based methods have achieved great success for arbitrary shape text detection. However, separating neighboring text instances is still one of the most challenging problems due to the complexity of texts in scene images. In this paper, we propose an innovative Kernel Proposal Network (dubbed KPN) for arbitrary shape text detection. The proposed KPN can separate neighboring text instances by classifying different texts into instance-independent feature maps, meanwhile avoiding the complex aggregation process existing in segmentation-based arbitrary shape text detection methods. To be concrete, our KPN will predict a Gaussian center map for each text image, which will be used to extract a series of candidate kernel proposals (i.e., dynamic convolution kernel) from the embedding feature maps according to their corresponding keypoint positions. To enforce the independence between kernel proposals, we propose a novel orthogonal learning loss (OLL) via orthogonal constraints. Specifically, our kernel proposals contain important self-information learned by network and location information by position embedding. Finally, kernel proposals will individually convolve all embedding feature maps for generating individual embedded maps of text instances. In this way, our KPN can effectively separate neighboring text instances and improve the robustness against unclear boundaries. To our knowledge, our work is the first to introduce the dynamic convolution kernel strategy to efficiently and effectively tackle the adhesion problem of neighboring text instances in text detection. Experimental results on challenging datasets verify the impressive performance and efficiency of our method. The code and model are available at https://github.com/GXYM/KPN.