Search

Single-image super-resolution (SISR) has been an important topic due to the demand for high-quality virtual images in the field of visual artificial intelligence. Methods based on deep learning have achieved great success based on the excellent capability of grasping complicated features of deep convolutional networks. The performance can be improved slightly but not obviously by simply widening or deepening the network. In this paper, we propose a merged convolutional network for super-resolution, which extracts more adequate details to restore high-resolution images. We used dense blocks for feature extraction to concatenate deep features with shallow features in depth. We also designed two sub-nets with distinct convolution kernels as different branches of the network, which can widen the network and improve the performance of the system. Finally, we employed sub-pixel layers to avoid feature distortion for up-sampling at the very end. Our method was evaluated using several standard benchmark datasets. The results demonstrate superior performance and good robustness compared with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Recommender Systems (RS) are used to give customized recommendations about specific items to users in a variety of applications including social web sites applications, media recommendation and commerce sites etc. Collaborative Filtering (CF) along with the Content Based Filtering (CBF) are two widely used methods which are being efficiently applied in RS implementation. CF suffers with sparseness problem where user-to-item ratings are amply sparse. On the other hand, CBF performance rely on methods of feature extraction for efficient use of items' description. The sparseness of user-to-item ratings and features extraction impede the performance of RS. Quality of rating prediction and item recommendation further degrades due to the negative values present in users/items latent factors. This paper proposes a novel RS that is built upon the semantics based items' content embedding model, enriched with contextual features extracted through Convolutional Neural Network (CNN). Non-negative Matrix Factorization (NMF), supplied with improvised embedding is used as CF technique. Embedding model captures the item details, thus resolving the sparsity, whereas, NMF caters for information loss due to negative values in latent factors. The proposed RS with contextually enriched NMF (Contx-NMF) simultaneously overcomes both the issues of sparseness and loss due to negative values, thus enhancing the rating prediction accuracy. The proposed model is evaluated on three public datasets (MovieLens 1M, MovieLens 10M)and Amazon Instant Video (AIV). The results demonstrate significant improvement in performance of Contx-NMF over state of the art RS models for sparse user-to-item ratings. [ABSTRACT FROM AUTHOR]

Abstract The number of kernels in a convolutional neural network (CNN) can have a significant impact on the performance of the CNN in the aspects of accuracy and computation efficiency. However, existing approaches to determining the number of convolution kernels are mainly conducted through a manual process, which suffers from the problems of potential overfitting, instability and inefficiency. In response to these problems, this paper presents a corner radiation area adaptation (CRAA) based method to automatically determine the number of convolution kernels. CRAA is evaluated in comparison with three representative methods on multiple public data sets. Experimental results show that CRAA is robust to the number of convolution kernels which is well adapted to a specific data set and achieves a higher level of classification accuracy by 3% when spending the same period of time in classification. More importantly, CRAA reduces the computational time by 15% in comparison with the three representative approaches when reaching the same level of accuracy in classification. [ABSTRACT FROM AUTHOR]

Abstract Traffic sign detection systems constitute a key component in trending real-world applications, such as autonomous driving, and driver safety and assistance. This paper analyses the state-of-the-art of several object-detection systems (Faster R-CNN, R-FCN, SSD, and YOLO V2) combined with various feature extractors (Resnet V1 50, Resnet V1 101, Inception V2, Inception Resnet V2, Mobilenet V1, and Darknet-19) previously developed by their corresponding authors. We aim to explore the properties of these object-detection models which are modified and specifically adapted to the traffic sign detection problem domain by means of transfer learning. In particular, various publicly available object-detection models that were pre-trained on the Microsoft COCO dataset are fine-tuned on the German Traffic Sign Detection Benchmark dataset. The evaluation and comparison of these models include key metrics, such as the mean average precision (mAP), memory allocation, running time, number of floating point operations, number of parameters of the model, and the effect of traffic sign image sizes. Our findings show that Faster R-CNN Inception Resnet V2 obtains the best mAP, while R-FCN Resnet 101 strikes the best trade-off between accuracy and execution time. YOLO V2 and SSD Mobilenet merit a special mention, in that the former achieves competitive accuracy results and is the second fastest detector, while the latter, is the fastest and the lightest model in terms of memory consumption, making it an optimal choice for deployment in mobile and embedded devices. [ABSTRACT FROM AUTHOR]

Abstract The extensive deployment of surveillance cameras in public places, such as subway stations and shopping malls, necessitates automated visual-data processing approaches to match pedestrians across non-overlapping multiple cameras. However, due to the insufficient number of labeled training samples in real surveillance scene, it is difficult to train an effective deep neural network for cross-camera pedestrian recognition. Moreover, the cross-camera variation in viewpoint, illumination, and background makes the task even more challenging. To address these issues, in this paper we propose to transfer the parameters of a pre-trained network to our target network and then update the parameters adaptively using training samples from the target domain. More importantly, we develop new network structures that are specially tailored for cross-camera pedestrian recognition task, and implement a simple yet effective multi-level feature fusion method that yield more discriminative and robust features for pedestrian recognition. Specifically, rather than conventionally perform classification on the single-level feature of the last feature layer, we instead utilize multi-level feature by associating feature visualization with multi-level feature fusion. As another contribution, we have published our codes and extracted features to facilitate further research. Extensive experiments are conducted on WARD, PRID and MARS datasets, we show that the proposed method consistently outperforms state-of-the-arts. [ABSTRACT FROM AUTHOR]

Convolutional neural networks have been significantly improving common object detection performances for a long time. However, targets across frames are independently detected in an image sequence, and object detection methods in multiple frames are generally divided into two main stages: object detection in every single frame and feature map association across frames. In this paper, a multi-frame detection framework is proposed to directly detect small impurities in opaque glass bottles with liquor. Specifically, a convolutional neural network trained with correlational examples simultaneously detects and correlates proposals, and then links them selectively to obtain robust detection results under challenging illuminations. Besides, memory costs of patch pairs become extremely large compared with those of patches, thus a sequential training procedure is introduced to relax hardware requirements. Extensive experiments on impurity datasets demonstrate superior performances of multi-frame detection frameworks with convolutional neural networks than traditional single-frame models. [ABSTRACT FROM AUTHOR]

In this work, we address the problem of face verification, namely determining whether a pair of face images belongs to the same or different subjects. Previous works often consider solving the problem of face verification in two steps: feature extraction and face recognition, resulting in a fragmented procedure. We argue that these techniques, although working well, fail to explicitly exploit a full end-to-end framework for face verification, which has received much attention and achieved significant improvements recently. In this paper, we propose a novel Joint Bayesian guided metric learning technique for dealing with the face verification task, which well integrates the above two steps of face verification into an end-to-end convolutional neural network (CNN) architecture. In the training stage, an initial neural network, which has the similar architecture with GoogLeNet CNN model, is firstly pre-trained by optimizing classification-based objective functions on the publicly available CASIA WebFace database. Based on constructed face pairs dataset from CASIA WebFace and LFW datasets, we then fine-tune the whole network parameters under the guide of the learned knowledge, which is obtained from the highly successful Joint Bayesian model. This guided learning procedure, which can also be seen as a metric learning technique, can further update network parameters for discriminating face pairs. In the testing process, the outputs by this unified network are discriminated with a threshold value to produce the ultimate prediction for the face verification task. Comprehensive evaluations over the LFW dataset well demonstrate the encouraging face verification performance of our proposed framework. [ABSTRACT FROM AUTHOR]

In this paper, a novel image operator is proposed to detect and locate text in scene images. To achieve a high recall of character detection, extremal regions are detected as character candidates. Two classifiers are trained to identify characters, and a recursive local search algorithm is proposed to extract characters that are wrongly identified by the classifiers. An efficient pruning method, which combines component trees and recognition results, is proposed to prune repeating components. A cascaded method combines text line entropy with a Convolutional Neural Network model. It is used to verify text candidates, which reduces the number of non-text regions. The proposed technique is test on three public datasets, i.e. ICDAR2011 dataset, ICDAR2013 dataset and ICDAR2015 dataset. The experimental results show that our approach achieves state-of-the-art performance. [ABSTRACT FROM AUTHOR]