User complaint data are quite valuable because they can reflect deficiencies of companies. Analyzing these short texts can help companies discover what topics users are complaining about. It is critical to locate and respond to these complaints timely so that companies can improve users’ satisfaction and loyalty. As the data volume is large, topic model can help discover key complaint topics quickly. The complaint data are in the form of short texts and streams, traditional topic models like LDA and BTM are not suitable in this scenario, for the reason that LDA is designed for long texts and BTM can not handle streams. This paper firstly proposes an improved shorttext topic model called PMITI-BTM to generate topics from user complaint data statically, and then further extends this algorithm into a dynamic one to suit the streaming feature of data. To further analyze the topic evolution, we finally propose a clustering algorithm called TDWAP to acquire the evolution process of these topics in different time slices. For each algorithm, we do several experiments to prove its efficiency. Results show that our methods not only can improve the performance of short texts topic discovery, but also can discover the evolution of topics.

The strong abilities of deep learning models have been shown in the area of text detection in natural scene images. In this paper, we introduce a new method called deep metric learning for scene text detection. We use the triplet loss [1] to replace the traditional loss function (Softmax) and learn a mapping from image regions to a compact Euclidean space where distances correspond to a measure of text similarity. By combining the CNN model with metric learning, we can make reliable binary classification between text regions and non-text ones. We show that the proposed model achieves competitive results on the ICDAR 2003, ICDAR 2011, and ICDAR 2013 datasets, with the F-measure of 0.74, 0.80, and 0.79.

Existing hashing methods normally define certain specific forms of hash functions, after which an objective function can be formulated to optimize the loss on training set to learn the parameters. However, in this way, the hash function will be tightly coupled with the generated objective in most cases. Moreover, since the objectives are generally formulated with binary quantization, most of them are nonconvex, which makes the optimization difficult and consequently decreases the similarity preserving performance of hashing. To solve this problem, we propose a novel pairwise correlation preserving framework to learn compact binary codes for hashing. First, we project each data into a metric space and represent it as a vector encoding the underlying local and global structure by pairwise correlation learning. Afterwards, pairwise correlation reconstruction (PCR), is further proposed to preserve the correlations of data between the metric space and the hamming space to learn binary codes. The PCR model is convex. Moreover, no specific hash functions are needed to be predefined and the steps of correlation learning and reconstruction are independent. The above characteristics make the optimization of PCR easily and efficiently, and thus leads to better preservation of data similarity in hamming space.

Text detection is a difficult task due to the significant diversity of the texts appearing in natural scene images. In this paper, we propose a novel text descriptor, SPP-net, extracted by equipping the Convolutional Neural Network (CNN) with spatial pyramid pooling. We first compute the feature maps from the original text lines without any cropping or warping, and then generate the fixed-size representations for text discrimination. Experimental results on the latest ICDAR 2011 and 2013 datasets have proven that the proposed descriptor outperforms the state-of-the-art methods by a noticeable margin on F-measure with its merit of incorporating multi-scale text information and its flexibility of describing text regions with different sizes and shapes.

Part-based approaches, such as Deformable Part Model (DPM), have been actively studied for pedestrian detection in recent years. However, the overall pedestrian detection performance heavily depends on the detection accuracy of a single part detector, which is not so discriminative that usually easily affected by occlusions and deformations. To address this problem, in this paper, we propose a novel method enhancing the pedestrian detection performance by capturing the dependencies between different part detectors. Our attempt is to refine the overall detection accuracy by exploiting the joint state distribution of relevant part detectors. Firstly, we estimate the parameters for the joint state distribution, which expresses the dependencies between different part detectors, on the training set. Afterwards, a linear classifier is trained on the scores of the part detectors to assign them with different weights. At last, given a testing image, the joint state is inferred and the scores of part detectors are integrated to output the refined score. The experimental results carried out on the commonly used benchmark datasets show that the proposed method outperforms other state-of-the-art methods on pedestrian detection accuracy.

Due to the explosive growth of visual data and the raised urgent needs for more efficient nearest neighbor search methods, hashing methods have been widely studied in recent years. However, parameter optimization of the hash function in most available approaches is tightly coupled with the form of the function itself, which makes the optimization difficult and consequently affects the similarity preserving performance of hashing. To address this issue, we propose a novel pairwise correlation reconstruction framework for learning compact binary codes flexibly. Firstly, each data point is projected into a metric space and represented as a vector encoding the underlying local and global structure of the input space. The similarities of the data are then measured by the pairwise correlations of the learned vectors, which are represented as Euclidean distances. Afterwards, in order to preserve the similarities maximally, the optimal binary codes are learned by reconstructing the pairwise correlations. Experimental results are provided and analyzed on four commonly used benchmark datasets to demonstrate that the proposed method achieves the best nearest neighbor search performance comparing with the state-of-the-art methods.

In this work, we propose an integrated framework for image segmentation and annotation based on topic models. We first employ probabilistic latent semantic analysis (PLSA) to discover the topics of image regions and pixels, both utilized in our framework to segment images into different regions and to improve the annotation accuracy. Furthermore, we propose a supervised version of PLSA, SPLSA, as a new graphical model in order to accommodate the annotation results into the segmentation process to improve its performance. We compare the proposed SPLSA model with PLSA on their image segmentation performance, and also evaluate the image annotation performance of our methods on different datasets. The experimental results prove that the supervised information in SPLSA improves the segmentation results, and the image annotation accuracy is higher than the state-of-art methods including Conditional Random Fields.

Image annotation plays an important role in image retrieval and understanding. Various techniques have been proposed for assigning keywords to images. One of the most frequently used methods is to search annotated images with similar visual features, and keywords are transfered to new coming images. This leads to the problem of nearest neighbor search, which is a hot topic of pattern recognition, information retrieval, and data compression. In this paper we proposed a fast and effective method for retrieving similar images from large collections of annotated images. The proposed technique employs discrete cosine transform and regular lattice quantization to encode images and search similar images directly with the corresponding codes. This technique is evaluated on image annotation. Similar images are retrieved by utilizing our encoding strategy, and keywords are assigned by utilizing traditional label transfer mechanism. Experimental results show that our method provides competitive performance with traditional methods, and mean while provides one scalable framework for annotating large collections of image dataset.

Region-based Image Annotation has received increasing attention in recent years. Topic models such as probabilistic Latent Semantic Analysis (PLSA) and Latent Dirichlet Allocation (LDA) have shown great success in object recognition and localization. In this paper, we introduce a supervised topic model for region-based image annotation. Images are segmented into superpixels, and visual features are extracted from each superpixel region. Boosted classifiers are then trained for each class, and the output of boosted classifiers are quantized as boosted visual words. The proposed model builds a generative model on both visual words and corresponding class labels. We tested the model on the 21-class MSRC dataset. Experimental results show that our model improves the annotation performance comparing with boosted classifiers.

Mass detection in mammograms is a challenging problem. In this paper, we propose a cost-sensitive cascaded method for automatic mass detection, which employs machine learning techniques to detect region of interests (ROI). In detail, we divide the original mammograms into overlapped squared sub-images. For each sub-image, intensity features based on gray histogram, texture features based on spatial gray-level co-occurrence matrix (SGLDM) and texture features based on local binary patterns (LBP) are extracted and input to a cost-sensitive cascaded classifier. Simple threshold segmentation and neural network are used to further reduce false positives. Experimental results show that the proposed method is effective in mass detection.

The paper presents an efficient and low-cost method for automatically detecting and tracking the moving object from astronomical CCD image sequences, using a combination of active contours and shape feature similarities. An object detection algorithm is firstly implemented following some image preprocessing steps, in order to locate all the major objects in each image. Next, an object tracking method based on greedy snake algorithm is proposed so that all the detected objects are able to be correctly tracked. Finally, the moving object in the image sequence is identified by applying a shape feature similarity matching operation. Experimental results are also illustrated to demonstrate the capability of proposed method to perform correct tracking in different situations.