Search

Abstract The convolutional network-based tracking (CNT) algorithm provides a training network with warped target regions in the first frame instead of large auxiliary datasets, which solves the problem of convolutional neural network (CNN)-based tracking requiring very long training time and a large number of auxiliary training samples. However, the two-layer CNT uses only gray feature that causes sensitivity to appearance variations. Besides, some samples with useless information should be removed to avoid drifting problems. For these reasons, a multi-layer convolutional network-based visual tracking algorithm via important region selection (IRST) is proposed in this paper. The proposed important region selection model is built via high entropy selection and background discrimination, which enables the training samples to be informative in order to provide enough stable information and also be discriminative so as to resist distractors. The feature maps are also obtained by weighting the template filters with cluster weights. Instead of simple gray features, IRST adds the Gabor layer to explore the texture feature of the target that is effective on coping with illumination and rotation variations. Extensive experiments show that the proposed algorithm achieves superior performances in many challenging visual tracking tasks. [ABSTRACT FROM AUTHOR]

Retinal vessel analysis of fundus images is an indispensable method for the screening and diagnosis of related diseases. In this paper, we propose a novel retinal vessel segmentation method of the fundus images based on convolutional neural network (CNN) and fully connected conditional random fields (CRFs). The segmentation process is mainly divided into two steps. Firstly, a multiscale CNN architecture with an improved cross-entropy loss function is proposed to produce the probability map from image to image. We construct the multiscale network by combining the feature map of each middle layer to learn more detail information of the retinal vessels. Meanwhile, our proposed cross-entropy loss function ignores the slightest loss of relatively easy samples in order to take more attention to learn the hard examples. Secondly, CRFs is applied to get the final binary segmentation result which makes use of more spatial context information by taking into account the interactions among all of the pixels in the fundus images. The effectiveness of the proposed method has been evaluated on two public datasets, i.g., DRIVE and STARE with comparisons against eleven state-of-the-art approaches including five deep learning based methods. Results show that our method allows for detection of more tiny blood vessels and more precise locating of the edges. [ABSTRACT FROM AUTHOR]

This paper investigates how to integrate the complementary information from RGB and thermal (RGB-T) sources for object tracking. We propose a novel Convolutional Neural Network (ConvNet) architecture, including a two-stream ConvNet and a FusionNet, to achieve adaptive fusion of different source data for robust RGB-T tracking. Both RGB and thermal streams extract generic semantic information of the target object. In particular, the thermal stream is pre-trained on the ImageNet dataset to encode rich semantic information, and then fine-tuned using thermal images to capture the specific properties of thermal information. For adaptive fusion of different modalities while avoiding redundant noises, the FusionNet is employed to select most discriminative feature maps from the outputs of the two-stream ConvNet, and updated online to adapt to appearance variations of the target object. Finally, the object locations are efficiently predicted by applying the multi-channel correlation filter on the fused feature maps. Extensive experiments on the recently public benchmark GTOT verify the effectiveness of the proposed approach against other state-of-the-art RGB-T trackers. [ABSTRACT FROM AUTHOR]

Facial landmark localization is important to many facial recognition and analysis tasks, such as face attributes analysis, head pose estimation, 3D face modeling, and facial expression analysis. In this paper, we propose a new approach to localizing landmarks in facial image by deep convolutional neural network (DCNN). We make two enhancements on the CNN to adapt it to the feature localization task as follows. First, we replace the commonly used max pooling by depth-wise convolution to obtain better localization performance. Second, we define a response map for each facial points as a 2D probability map indicating the presence likelihood, and train our model with a KL divergence loss. To obtain robust localization results, our approach first takes the expectations of the response maps of enhanced CNN and then applies auto-encoder model to the global shape vector, which is effective to rectify the outlier points by the prior global landmark configurations. The proposed ECNN method achieves 5.32% mean error on the experiments on the 300-W dataset, which is comparable to the state-of-the-art performance on this standard benchmark, showing the effectiveness of our methods. [ABSTRACT FROM AUTHOR]

Recent studies have shown that image representations built upon deep convolutional layers in Convolutional Neural Networks (CNNs) have strong discriminative characteristics. In this paper, we present a novel and effective method to create compact binary codes (deep binary codes) based on deep convolutional features for image retrieval. Deep binary codes are generated by comparing the response from each feature map and the average response across all the feature maps on the deep convolutional layers. Additionally, a spatial cross-summing strategy is proposed to directly generate bit-scalable binary codes. As the deep binary codes on different deep layers can be obtained by passing the image through the CNN and each of them makes a different contribution to the search accuracy, we then present a dynamic, on-the-fly late fusion approach where the top N high quality search scores from deep binary codes are automatically determined online and fused to further enhance the retrieval precision. Two strengths of the proposed methods are that the generation of deep binary codes is based on a generic model, which does not require additional training for new image domains, and that the dynamic late fusion scheme is query adaptive. Extensive experimental results on well known benchmarks show that the performance of deep binary codes are competitive with state-of-the-art approaches for large scale image retrieval. Moreover, it is shown that the dynamic late fusion scheme significantly enhances the search accuracy. [ABSTRACT FROM AUTHOR]

In this paper, we tackle the problem of depth estimation from a single image, which is essential for understanding 3D scene structure and can promote the development of visual applications. Markov Random Field (MRF) related depth estimation methods have attracted extensive attentions due to their ability of building structural relationships on outputs. Almost all of them employed engineered low-level absolute and relative features for constructing MRF. However, the engineered features are not capable of producing accurate depths for various scenes. In this paper, we propose Convolutional Conditional Random Field Network (CCRFN) consisting of feature learning and depth tuning components. In feature learning component, we build two Convolutional Neural Network (CNN) architectures to learn absolute and relative features from raw images. In depth tuning component, the learned features are fed into Conditional Random Field (CRF) to generate the depths of all pixels in an image by optimizing a well-defined energy function. CCRFN has two advantages that (1) it does not need hand-crafted features and (2) it models the depths at individual points as well as the relationship between them in the deep model. Experiments on widely used Make3D dataset show that CCRFN outperforms state-of-the-art methods on three evaluation criteria and generates more accurate depth maps with sharper object boundaries. [ABSTRACT FROM AUTHOR]

Action recognition (AR) is one of the most important tasks in video analysis and computer vision. Recently a large number of related methods have been proposed. While most of these methods are investigated on AR datasets collected from the visible spectrum, the AR problem under infrared scenarios still has not attracted much attention. There is even few public infrared datasets available for supporting the fundamental evaluation requirements of this research. To this issue, this work aims to emphasize the importance of the infrared AR problem in applications and arouse researchers' attention on this task. Specifically, we construct a new Inf rared A ction R ecognition ( InfAR ) dataset captured at different times, including in summer and winter, and explore how discriminable actions in our InfAR dataset are with the state-of-the-art pipelines based on low-level features and deep convolutional neural network (CNN), respectively. Our results reveal: (1) In all, dense trajectory feature can achieve the best performance while the appearance features, e.g., HOG, have relatively poorer performance; (2) the encoding method of vector of locally aggregated descriptors is evidently better than that of the widely-used Fisher Vector; (3) the late fusion facilitates a better performance than early fusion; (4) action videos captured in winter is more discriminable than in summer; (5) compared to appearance information, the motion information is more essential for infrared action recognition and utilizing this information through deep CNN can improve greatly the performance. The best performance achieved on our dataset is 76.66% (Average Precision), leaving a reasonable space for further exploring the insights underlying such type of infrared AR problem and accordingly designing proper techniques to further promote the performance on this specifically constructed InfAR dataset. [ABSTRACT FROM AUTHOR]

Face representation is a crucial step of face detection system. In this paper, we present a fast face detection algorithm based on representation learnt using convolutional neural network (CNN) so as to explicitly capture various latent facial features. Firstly, in order to improve the speed of detection in the system, we train an Adaboost background filter which can remove the background most quickly. Secondly, we use the CNN to extract more distinctive features for those face and non-face patterns that have not been filtered by Adaboost. CNN can automatically learn and synthesize a problem-specific feature extractor from a training set, without making any assumptions or using any hand-made design concerning the features to extract or the areas of the face pattern to analyze. Finally, support vector machines (SVM) are used to detect instead of using the classification function of CNN itself. Extensive experiments demonstrate the robustness and efficiency of our system by comparing it with several popular face detection algorithms on the widely used CMU+MIT frontal face dataset and FDDB dataset. [ABSTRACT FROM AUTHOR]