Search

Blob detection and image denoising are fundamental, sometimes related tasks in computer vision. In this paper, we present a computational method to quantitatively measure blob characteristics using normalized unilateral second-order Gaussian kernels. This method suppresses non-blob structures while yielding a quantitative measurement of the position, prominence and scale of blobs, which can facilitate the tasks of blob reconstruction and blob reduction. Subsequently, we propose a denoising scheme to address high-ISO long-exposure noise, which sometimes spatially shows a blob appearance, employing a blob reduction procedure as a cheap preprocessing for conventional denoising methods. We apply the proposed denoising methods to real-world noisy images as well as standard images that are corrupted by real noise. The experimental results demonstrate the superiority of the proposed methods over state-of-the-art denoising methods. [ABSTRACT FROM AUTHOR]

People in crowd scenes always exhibit consistent behaviors and form collective motions. The analysis of collective motion has motivated a surge of interest in computer vision. Nevertheless, the effort is hampered by the complex nature of collective motions. Considering the fact that collective motions are formed by individuals, this paper proposes a new framework for both quantifying and detecting collective motion by investigating the spatio-temporal behavior of individuals. The main contributions of this work are threefold: 1) an intention-aware model is built to fully capture the intrinsic dynamics of individuals; 2) a structure-based collectiveness measurement is developed to accurately quantify the collective properties of crowds; 3) a multi-stage clustering strategy is formulated to detect both the local and global behavior consistency in crowd scenes. Experiments on real world data sets show that our method is able to handle crowds with various structures and time-varying dynamics. Especially, the proposed method shows nearly 10% improvement over the competitors in terms of NMI, Purity and RI. Its applicability is illustrated in the context of anomaly detection and semantic scene segmentation. [ABSTRACT FROM AUTHOR]

This paper presents an innovative method for motion segmentation in RGB-D dynamic videos with multiple moving objects. The focus is on finding static, small or slow moving objects (often overlooked by other methods) that their inclusion can improve the motion segmentation results. In our approach, semantic object based segmentation and motion cues are combined to estimate the number of moving objects, their motion parameters and perform segmentation. Selective object-based sampling and correspondence matching are used to estimate object specific motion parameters. The main issue with such an approach is the over segmentation of moving parts due to the fact that different objects can have the same motion (e.g. background objects). To resolve this issue, we propose to identify objects with similar motions by characterizing each motion by a distribution of a simple metric and using a statistical inference theory to assess their similarities. To demonstrate the significance of the proposed statistical inference, we present an ablation study, with and without static objects inclusion, on SLAM accuracy using the TUM-RGBD dataset. To test the effectiveness of the proposed method for finding small or slow moving objects, we applied the method to RGB-D MultiBody and SBM-RGBD motion segmentation datasets. The results showed that we can improve the accuracy of motion segmentation for small objects while remaining competitive on overall measures. [ABSTRACT FROM AUTHOR]

The task of single image super-resolution (SISR) is a highly ill-posed inverse problem since reconstructing the high-frequency details from a low-resolution image is challenging. Most previous CNN-based super-resolution (SR) methods tend to directly learn the mapping from the low-resolution image to the high-resolution image through some complex convolutional neural networks. However, the method of blindly increasing the depth of the network is not the best choice because the performance improvement of such methods is marginal but the computational cost is huge. A more efficient method is to integrate the image prior knowledge into the model to assist the image reconstruction. Indeed, the soft-edge has been widely applied in many computer vision tasks as the role of an important image feature. In this paper, we propose a Soft-edge assisted Network (SeaNet) to reconstruct the high-quality SR image with the help of image soft-edge. The proposed SeaNet consists of three sub-nets: a rough image reconstruction network (RIRN), a soft-edge reconstruction network (Edge-Net), and an image refinement network (IRN). The complete reconstruction process consists of two stages. In Stage-I, the rough SR feature maps and the SR soft-edge are reconstructed by the RIRN and Edge-Net, respectively. In Stage-II, the outputs of the previous stages are fused and then fed to the IRN for high-quality SR image reconstruction. Extensive experiments show that our SeaNet converges rapidly and achieves excellent performance under the assistance of image soft-edge. The code is available at https://gitlab.com/junchenglee/seanet-pytorch. [ABSTRACT FROM AUTHOR]

Image denoising technologies in a Euclidean domain have achieved good results and are becoming mature. However, in recent years, many real-world applications encountered in computer vision and geometric modeling involve image data defined in irregular domains modeled by huge graphs, which results in the problem on how to solve image denoising problems defined on graphs. In this paper, we propose a novel model for removing mixed or unknown noise in images on graphs. The objective is to minimize the sum of a weighted fidelity term and a sparse regularization term that additionally utilizes wavelet frame transform on graphs to retain feature details of images defined on graphs. Specifically, the weighted fidelity term with $\ell _{1}$ -norm and $\ell _{2}$ -norm is designed based on a analysis of the distribution of mixed noise. The augmented Lagrangian and accelerated proximal gradient methods are employed to achieve the optimal solution to the problem. Finally, some supporting numerical results and comparative analyses with other denoising algorithms are provided. It is noted that we investigate image denoising with unknown noise or a wide range of mixed noise, especially the mixture of Poisson, Gaussian, and impulse noise. Experimental results reported for synthetic and real images on graphs demonstrate that the proposed method is effective and efficient, and exhibits better performance for the removal of mixed or unknown noise in images on graphs than other denoising algorithms in the literature. The method can effectively remove mixed or unknown noise and retain feature details of images on graphs. It delivers a new avenue for denoising images in irregular domains. [ABSTRACT FROM AUTHOR]

Multi-view scene analysis has been widely explored in computer vision, including numerous practical applications. The texts in multi-view scenes are often detected by following the existing text detection method in a single image, which however ignores the multi-view corresponding constraint. The multi-view correspondences may contain structure, location information and assist difficulties induced by factors like occlusion and perspective distortion, which are deficient in the single image scene. In this paper, we address the corresponding text detection task and propose a novel text co-detection method to identify the co-occurring texts among multi-view scene images with compositions of detection and correspondence under large environmental variations. In our text co-detection method, the visual and geometrical correspondences are designed to explore texts holding high pairwise representation similarity and guide the exploitation of texts with geometrical correspondences, simultaneously. To guarantee the pairwise consistency among multiple images, we additionally incorporate the cycle consistency constraint, which guarantees alignments of text correspondences in the image set. Finally, text correspondence is represented by a permutation matrix and solved via positive semidefinite and low-rank constraints. Moreover, we also collect a new text co-detection dataset consisting of multi-view image groups obtained from the same scene with different photographing conditions. The experiments show that our text co-detection obtains satisfactory performance and outperforms the related state-of-the-art text detection methods. [ABSTRACT FROM AUTHOR]

Some neurons in the primary visual cortex (V1) of human visual system (HVS) conduct dynamic center-surround computation, which is thought to contribute to compress the high dynamic range (HDR) scene and preserve the details. We simulate this dynamic receptive field (RF) property of V1 neurons to solve the so-called tone mapping (TM) task in this paper. The novelties of our method are as follows. (1) Cortical processing mechanisms of HVS are modeled to build a local TM operation based on two Gaussian functions whose kernels and weights adapt according to the center-surround contrast, thus reducing halo artifacts and effectively enhancing the local details of bright and dark parts of image. (2) Our method uses an adaptive filter that follows the contrast levels of the image, which is computationally very efficient. (3) The local fusion between the center and surround responses returned by a cortical processing flow and the global signals returned by a sub-cortical processing flow according to the local contrast forms a dynamic mechanism that selectively enhances the details. Extensive experiments show that the proposed method can efficiently render the HDR scenes with good contrast, clear details, and high structural fidelity. In addition, the proposed method can also obtain promising performance when applied to enhance the low-light images. Furthermore, by modeling these biological solutions, our technique is simple and robust considering that our results were obtained using the same parameters for all the datasets (e.g., HDR images or low-light images), that is, mimicking how HVS operates. [ABSTRACT FROM AUTHOR]

Fast and accurate ellipse detection is critical in certain computer vision tasks. In this paper, we propose an arc adjacency matrix-based ellipse detection (AAMED) method to fulfill this requirement. At first, after segmenting the edges into elliptic arcs, the digraph-based arc adjacency matrix (AAM) is constructed to describe their triple sequential adjacency states. Curvature and region constraints are employed to make the AAM sparse. Secondly, through bidirectionally searching the AAM, we can get all arc combinations which are probably true ellipse candidates. The cumulative-factor (CF) based cumulative matrices (CM) are worked out simultaneously. CF is irrelative to the image context and can be pre-calculated. CM is related to the arcs or arc combinations and can be calculated by the addition or subtraction of CF. Then the ellipses are efficiently fitted from these candidates through twice eigendecomposition of CM using Jacobi method. Finally, a comprehensive validation score is proposed to eliminate false ellipses effectively. The score is mainly influenced by the constraints about adaptive shape, tangent similarity, distribution compensation. Experiments show that our method outperforms the 12 state-of-the-art methods on 9 datasets as a whole, with reference to recall, precision, F-measure, and time-consumption. [ABSTRACT FROM AUTHOR]

Light field technology has reached a certain level of maturity in recent years, and its applications in both computer vision research and industry are offering new perspectives for cinematography and virtual reality. Several methods of capture exist, each with its own advantages and drawbacks. One of these methods involves the use of handheld plenoptic cameras. While these cameras offer freedom and ease of use, they also suffer from various visual artefacts and inconsistencies. We propose in this paper an advanced pipeline that enhances their output. After extracting sub-aperture images from the RAW images with our demultiplexing method, we perform three correction steps. We first remove hot pixel artefacts, then correct colour inconsistencies between views using a colour transfer method, and finally we apply a state of the art light field denoising technique to ensure a high image quality. An in-depth analysis is provided for every step of the pipeline, as well as their interaction within the system. We compare our approach to existing state of the art sub-aperture image extracting algorithms, using a number of metrics as well as a subjective experiment. Finally, we showcase the positive impact of our system on a number of relevant light field applications. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have facilitated substantial progress on various problems in computer vision and image processing. However, applying them to image fusion has remained challenging due to the lack of the labelled data for supervised learning. This paper introduces a deep image fusion network (DIF-Net), an unsupervised deep learning framework for image fusion. The DIF-Net parameterizes the entire processes of image fusion, comprising of feature extraction, feature fusion, and image reconstruction, using a CNN. The purpose of DIF-Net is to generate an output image which has an identical contrast to high-dimensional input images. To realize this, we propose an unsupervised loss function using the structure tensor representation of the multi-channel image contrasts. Different from traditional fusion methods that involve time-consuming optimization or iterative procedures to obtain the results, our loss function is minimized by a stochastic deep learning solver with large-scale examples. Consequently, the proposed method can produce fused images that preserve source image details through a single forward network trained without reference ground-truth labels. The proposed method has broad applicability to various image fusion problems, including multi-spectral, multi-focus, and multi-exposure image fusions. Quantitative and qualitative evaluations show that the proposed technique outperforms existing state-of-the-art approaches for various applications. [ABSTRACT FROM AUTHOR]

Image denoising and high-level vision tasks are usually handled independently in the conventional practice of computer vision, and their connection is fragile. In this paper, we cope with the two jointly and explore the mutual influence between them with the focus on two questions, namely (1) how image denoising can help improving high-level vision tasks, and (2) how the semantic information from high-level vision tasks can be used to guide image denoising. First for image denoising we propose a convolutional neural network in which convolutions are conducted in various spatial resolutions via downsampling and upsampling operations in order to fuse and exploit contextual information on different scales. Second we propose a deep neural network solution that cascades two modules for image denoising and various high-level tasks, respectively, and use the joint loss for updating only the denoising network via back-propagation. We experimentally show that on one hand, the proposed denoiser has the generality to overcome the performance degradation of different high-level vision tasks. On the other hand, with the guidance of high-level vision information, the denoising network produces more visually appealing results. Extensive experiments demonstrate the benefit of exploiting image semantics simultaneously for image denoising and high-level vision tasks via deep learning. The code is available online: https://github.com/Ding-Liu/DeepDenoising [ABSTRACT FROM AUTHOR]

Image feature correspondence selection is pivotal to many computer vision tasks from object recognition to 3D reconstruction. Although many correspondence selection algorithms have been developed in the past decade, there still lacks an in-depth evaluation and comparison in the open literature, which makes it difficult to choose the appropriate algorithm for a specific application. This paper attempts to fill this gap by evaluating eight competing correspondence selection algorithms including both classical methods and current state-of-the-art ones. In addition to preselected correspondences, we have compared different combinations of detector and descriptor on four standard datasets. The diversity of those datasets cover a wide range of uncertainty factors including zoom, rotation, blur, viewpoint change, JPEG compression, light change, different rendering styles and multiple structures. We have measured the quality of competing correspondence selection algorithms in terms of four performance metrics - i.e., precision, recall, F-measure and efficiency. Moreover, we propose to combine the strengths of eight competing methods by combining their correspondence selection results. Extensive experimental results are reported to demonstrate the superiority of several fusion strategies to individual methods, which suggests the possibility of adaptively combining those methods for even better performance. [ABSTRACT FROM AUTHOR]

Object detection has been a challenging task in computer vision. Although significant progress has been made in object detection with deep neural networks, the attention mechanism has yet to be fully developed. In this paper, we propose a hybrid attention mechanism for single-stage object detection. First, we present the modules of spatial attention, channel attention and aligned attention for single-stage object detection. In particular, dilated convolution layers with symmetrically fixed rates are stacked to learn spatial attention. A channel attention mechanism with the cross-level group normalization and squeeze-and-excitation operation is proposed. Aligned attention is constructed with organized deformable filters. Second, the three types of attention are unified to construct the hybrid attention mechanism. We then plug the hybrid attention into Retina-Net and propose the efficient single-stage HAR-Net for object detection. The attention modules and the proposed HAR-Net are evaluated on the COCO detection dataset. The experiments demonstrate that hybrid attention can significantly improve the detection accuracy and that the HAR-Net can achieve a state-of-the-art 45.8% mAP, thus outperforming existing single-stage object detectors. [ABSTRACT FROM AUTHOR]

Superpixel segmentation is a fundamental computer vision technique that finds application in a multitude of high level computer vision tasks. Most state-of-the-art superpixel segmentation methods are unsupervised in nature and thus cannot fully utilize frequently occurring texture patterns or incorporate multi-scale context. In this paper, we show that superpixel segmentation can be improved by leveraging the superior modeling power of deep convolutional autoencoders in a fully unsupervised manner. We pose the superpixel segmentation problem as one of manifold learning where pixels that belong to similar texture patterns are assigned near identical embedding vectors. The proposed deep network is able to learn image-wide and dataset-wide feature patterns and the relationships between them. This knowledge is used to segment and group pixels in a way that is consistent with a more global definition of pattern coherence. Experiments demonstrate that the superpixels obtained from the embeddings learned by the proposed method outperform the state-of-the-art superpixel segmentation methods for boundary precision and recall values. Additionally, we find that semantic edges obtained from the superpixel embeddings to be significantly better than the contemporary unsupervised approaches. [ABSTRACT FROM AUTHOR]

With the rapid development of deep learning technology and other powerful tools, 3D object detection has made great progress and become one of the fastest growing field in computer vision. Many automated applications such as robotic navigation, autonomous driving, and virtual or augmented reality system require estimation of accurate 3D object location and detection. Under this requirement, many methods have been proposed to improve the performance of 3D object localization and detection. Despite recent efforts, 3D object detection is still a very challenging task due to occlusion, viewpoint variations, scale changes, and limited information in 3D scenes. In this paper, we present a comprehensive review of recent state-of-the-art approaches in 3D object detection technology. We start with some basic concepts, then describe some of the available datasets that are designed to facilitate the performance evaluation of 3D object detection algorithms. Next, we will review the state-of-the-art technologies in this area, highlighting their contributions, importance, and limitations as a guide for future research. Finally, we provide a quantitative comparison of the results of the state-of-the-art methods on the popular public datasets. [ABSTRACT FROM AUTHOR]

Learning interpretable data representation has been an active research topic in deep learning and computer vision. While representation disentanglement is an effective technique for addressing this task, existing works cannot easily handle the problems in which manipulating and recognizing data across multiple domains are desirable. In this paper, we present a unified network architecture of Multi-domain and Multi-modal Representation Disentangler ($M^{2}RD$), with the goal of learning domain-invariant content representation with the associated domain-specific representation observed. By advancing adversarial learning and disentanglement techniques, the proposed model is able to perform continuous image manipulation across data domains with multiple modalities. More importantly, the resulting domain-invariant feature representation can be applied for unsupervised domain adaptation. Finally, our quantitative and qualitative results would confirm the effectiveness and robustness of the proposed model over state-of-the-art methods on the above tasks. [ABSTRACT FROM AUTHOR]

Accurate and efficient image alignment is the core problem in the research of panoramic stitching nowadays. This paper proposes a local-adaptive image alignment method based on triangular facet approximation, which directly manipulates the matching data in the camera coordinates, and therefore rises superior to the imaging model of cameras. A more robust planar transformation model is proposed and extended to be local-adaptive via combining it with two weighting strategies. By approximating the scene as a combination of adjacent triangular facets, the planar and spherical triangulation strategies are introduced to more efficiently align normal and fisheye images respectively. The efficiency of the proposed method are verified through the comparative experiments on several challenging cases both qualitatively and quantitatively. [ABSTRACT FROM AUTHOR]

Connected Components Labeling is an essential step of many Image Processing and Computer Vision tasks. Since the first proposal of a labeling algorithm, which dates back to the sixties, many approaches have optimized the computational load needed to label an image. In particular, the use of decision forests and state prediction have recently appeared as valuable strategies to improve performance. However, due to the overhead of the manual construction of prediction states and the size of the resulting machine code, the application of these strategies has been restricted to small masks, thus ignoring the benefit of using a block-based approach. In this paper, we combine a block-based mask with state prediction and code compression: the resulting algorithm is modeled as a Directed Rooted Acyclic Graph with multiple entry points, which is automatically generated without manual intervention. When tested on synthetic and real datasets, in comparison with optimized implementations of state-of-the-art algorithms, the proposed approach shows superior performance, surpassing the results obtained by all compared approaches in all settings. [ABSTRACT FROM AUTHOR]

Finding suitable image representations for the task at hand is critical in computer vision. Different approaches extending the original Restricted Boltzmann Machine (RBM) model have recently been proposed to offer rotation-invariant feature learning. In this paper, we present an extended novel RBM that learns rotation invariant features by explicitly factorizing for rotation nuisance in 2D image inputs within an unsupervised framework. While the goal is to learn invariant features, our model infers an orientation per input image during training, using information related to the reconstruction error. The training process is regularised by a Kullback-Leibler divergence, offering stability and consistency. We used the $\gamma $ -score, a measure that calculates the amount of invariance, to mathematically and experimentally demonstrate that our approach indeed learns rotation invariant features. We show that our method outperforms the current state-of-the-art RBM approaches for rotation invariant feature learning on three different benchmark datasets, by measuring the performance with the test accuracy of an SVM classifier. Our implementation is available at https://bitbucket.org/tuttoweb/rotinvrbm . [ABSTRACT FROM AUTHOR]

Saliency detection task has witnessed a booming interest for years, due to the growth of the computer vision community. In this paper, we introduce a new saliency model that performs active learning with kernelized subspace ranker (KSR) referred to as KSR-AL. This pool-based active learning algorithm ranks the informativeness of unlabeled data by considering both uncertainty sampling and information density, thereby minimizing the cost of labeling. The informative images are selected to train the KSR iteratively and incrementally. The learning model of this algorithm is designed on object-level proposals and region-based convolutional neural network (R-CNN) features, by jointly learning a Rank-SVM classifier and a subspace projection. When the active learning process meets its stopping criteria, the saliency map of each image is generated by a weight fusion of its top-ranked proposals, whose ranking scores are graded by the learned ranker. We show that the KSR-AL achieves a reduction in annotation, as well as improvement in performance, compared with the supervised learning scheme. Besides, the proposed algorithm also outperforms the state-of-the-art methods. These improvements are demonstrated by extensive experiments on six publicly available benchmark datasets. [ABSTRACT FROM AUTHOR]

In recent years, the satellite videos have been captured by moving satellite platforms. In contrast to consumers, movies, and common surveillance videos, satellite videos can record the snapshots of city-scale scenes. In a broad field-of-view of satellite videos, each moving target would be very tiny and usually composed of several pixels in frames. Even worse, the noise signals also exist in the video frames, and the background of the video frames subpixel-level and uneven moving thanks to the motion of satellites. We argue that it is a novel type of computer vision task since previous technologies are unable to detect such tiny moving vehicles efficiently. This paper proposes a novel framework that can identify small moving vehicles in satellite videos. In particular, we offer a novel detecting algorithm based on the local noise modeling. We differentiate the potential vehicle targets from noise patterns by an exponential probability distribution. Subsequently, a multi-morphological-cue based discrimination strategy is designed to distinguish correct vehicle targets from the existing noises further. Another significant contribution is to introduce a series of evaluation protocols to measure the performance of tiny moving vehicle detection systematically. We annotate satellite videos manually to test our algorithms under different evaluation criterions. The proposed algorithm is also compared with the state-of-the-art baselines, which demonstrates the advantages of our framework over the benchmarks. Besides, the dataset would be downloaded from http://first.authour.github.com. [ABSTRACT FROM AUTHOR]

The guided filter and its subsequent derivatives have been widely employed in many image processing and computer vision applications primarily brought about by their low complexity and good edge-preservation properties. Despite this success, the different variants of the guided filter are unable to handle more aggressive filtering strengths leading to the manifestation of “detail halos”. At the same time, these existing filters perform poorly when the input and guide images have structural inconsistencies. In this paper, we demonstrate that these limitations are due to the guided filter operating as a variable-strength locally-isotropic filter that, in effect, acts as a weak anisotropic filter on the image. Our analysis shows that this behaviour stems from the use of unweighted averaging in the final steps of guided filter variants including the adaptive guided filter (AGF), weighted guided image filter (WGIF), and gradient-domain guided image filter (GGIF). We propose a novel filter, the Anisotropic Guided Filter (AnisGF), that utilises weighted averaging to achieve maximum diffusion while preserving strong edges in the image. The proposed weights are optimised based on the local neighbourhood variances to achieve strong anisotropic filtering while preserving the low computational cost of the original guided filter. Synthetic tests show that the proposed method addresses the presence of detail halos and the handling of inconsistent structures found in previous variants of the guided filter. Furthermore, experiments in scale-aware filtering, detail enhancement, texture removal, and chroma upsampling demonstrate the improvements brought about by the technique. [ABSTRACT FROM AUTHOR]

Convolutional Neural Networks have achieved significant success across multiple computer vision tasks. However, they are vulnerable to carefully crafted, human-imperceptible adversarial noise patterns which constrain their deployment in critical security-sensitive systems. This paper proposes a computationally efficient image enhancement approach that provides a strong defense mechanism to effectively mitigate the effect of such adversarial perturbations. We show that deep image restoration networks learn mapping functions that can bring off-the-manifold adversarial samples onto the natural image manifold, thus restoring classification towards correct classes. A distinguishing feature of our approach is that, in addition to providing robustness against attacks, it simultaneously enhances image quality and retains models performance on clean images. Furthermore, the proposed method does not modify the classifier or requires a separate mechanism to detect adversarial images. The effectiveness of the scheme has been demonstrated through extensive experiments, where it has proven a strong defense in gray-box settings. The proposed scheme is simple and has the following advantages: 1) it does not require any model training or parameter optimization, 2) it complements other existing defense mechanisms, 3) it is agnostic to the attacked model and attack type, and 4) it provides superior performance across all popular attack algorithms. Our codes are publicly available at https://github.com/aamir-mustafa/super-resolution-adversarial-defense. [ABSTRACT FROM AUTHOR]

Small object tracking becomes an increasingly important task, which however has been largely unexplored in computer vision. The great challenges stem from the facts that: 1) small objects show extreme vague and variable appearances, and 2) they tend to be lost easier as compared to normal-sized ones due to the shaking of lens. In this paper, we propose a novel aggregation signature suitable for small object tracking, especially aiming for the challenge of sudden and large drift. We make three-fold contributions in this work. First, technically, we propose a new descriptor, named aggregation signature, based on saliency, able to represent highly distinctive features for small objects. Second, theoretically, we prove that the proposed signature matches the foreground object more accurately with a high probability. Third, experimentally, the aggregation signature achieves a high performance on multiple datasets, outperforming the state-of-the-art methods by large margins. Moreover, we contribute with two newly collected benchmark datasets, i.e., small90 and small112, for visually small object tracking. The datasets will be available in https://github.com/bczhangbczhang/. [ABSTRACT FROM AUTHOR]

Instance segmentation is a challenging computer vision problem which lies at the intersection of object detection and semantic segmentation. Motivated by plant image analysis in the context of plant phenotyping, a recently emerging application field of computer vision, this paper presents the exemplar-based recursive instance segmentation (ERIS) framework. A three-layer probabilistic model is first introduced to jointly represent hypotheses, voting elements, instance labels, and their connections. Afterward, a recursive optimization algorithm is developed to infer the maximum a posteriori (MAP) solution, which handles one instance at a time by alternating among the three steps of detection, segmentation, and update. The proposed ERIS framework departs from previous works mainly in two respects. First, it is exemplar-based and model-free, which can achieve instance-level segmentation of a specific object class given only a handful of (typically less than 10) annotated exemplars. Such a merit enables its use in case that no massive manually-labeled data is available for training strong classification models, as required by most existing methods. Second, instead of attempting to infer the solution in a single shot, which suffers from extremely high computational complexity, our recursive optimization strategy allows for reasonably efficient MAP-inference in full hypothesis space. The ERIS framework is substantialized for the specific application of plant leaf segmentation in this work. Experiments are conducted on public benchmarks to demonstrate the superiority of our method in both effectiveness and efficiency in comparison with the state-of-the-art. [ABSTRACT FROM AUTHOR]

Collective activity recognition, which tells what activity a group of people is performing, is a cutting-edge research topic in computer vision. Different from action performed by individuals, collective activity needs to consider the complex interactions among different people. However, most previous works require exhaustive annotations such as accurate label information of individual actions, pairwise interactions, and poses, which could not be easily available in practice. Moreover, most of them treat human detection as a decoupled task before collective activity recognition and leverage all detected persons. This not only ignores the mutual relation between the two tasks, which makes it hard for filtering out irrelevant people, but also probably increases the computation burden when reasoning the collective activities. In this paper, we propose a fast weakly supervised deep learning architecture for collective activity recognition. For fast inference, we propose to make the actor detection and weakly supervised collective activity reasoning collaborate in an end-to-end framework by sharing convolutional layers between them. The joint learning makes the two tasks united and reinforced each other, so that it is more effective to filter out the outliers who are not involved in the activity. For the weakly supervised learning, we propose a latent embedding scheme for mining person-group interactive relationship to get rid of the use of any pairwise relation between people and the individual action labels as well. The experimental results show that the proposed framework achieves comparable or even better performance as compared to the state-of-the-art on three datasets. Our joint modelling reasons collective activities at the speed of 22.65 fps, which is the fastest ever known and substantially makes collective activity recognition more towards real-time applications. [ABSTRACT FROM AUTHOR]

This paper presents a new, simple, and efficient segmentation approach, based on a fusion procedure which aims at combining several segmentation maps associated to simpler partition models in order to finally get a more reliable and accurate segmentation result. The different label fields to be fused in our application are given by the same and simple (K-means based) clustering technique on an input image expressed in different color spaces. Our fusion strategy aims at combining these segmentation maps with a final clustering procedure using as input features, the local histogram of the class labels, previously estimated and associated to each site and for all these initial partitions. This fusion framework remains simple to implement, fast, general enough to be applied to various computer vision applications (e.g., motion detection and segmentation), and has been successfully applied on the Berkeley image database. The experiments herein reported in this paper illustrate the potential of this approach compared to the state-of-the-art segmentation methods recently proposed in the literature. [ABSTRACT FROM AUTHOR]

In this paper, we analyze the computational challenges in implementing particle filtering, especially to video sequences. Particle filtering is a technique used for filtering nonlinear dynamical systems driven by non-Gaussian noise processes. It has found widespread applications in detection, navigation, and tracking problems. Although, in general, particle filtering methods yield improved results, it is difficult to achieve real time performance. In this paper, we analyze the computational drawbacks of traditional particle filtering algorithms, and present a method for implementing the particle filter using the Independent Metropolis Hastings sampler, that is highly amenable to pipelined implementations and parallelization. We analyze the implementations of the proposed algorithm, and, in particular, concentrate on implementations that have minimum processing times. It is shown that the design parameters for the fastest implementation can be chosen by solving a set of convex programs. The proposed computational methodology was verified using a cluster of PCs for the application of visual tracking. We demonstrate a linear speedup of the algorithm using the methodology proposed in the paper. [ABSTRACT FROM AUTHOR]

Structured light vision systems have been successfully used for accurate measurement of 3-D surfaces in computer vision. However, their applications are mainly limited to scanning stationary objects so far since tens of images have to be captured for recovering one 3-D scene. This paper presents an idea for real-time acquisition of 3-D surface data by a specially coded vision system. To achieve 3-D measurement for a dynamic scene, the data acquisition must be performed with only a single image. A principle of uniquely color-encoded pattern projection is proposed to design a color matrix for improving the reconstruction efficiency. The matrix is produced by a special code sequence and a number of state transitions. A color projector is controlled by a computer to generate the desired color patterns in the scene. The unique indexing of the light codes is crucial here for color projection since it is essential that each light grid be uniquely identified by incorporating local neighborhoods so that 3-D reconstruction can be performed with only local analysis of a single image. A scheme is presented to describe such a vision processing method for fast 3-D data acquisition. Practical experimental performance is provided to analyze the efficiency of the proposed methods. [ABSTRACT FROM AUTHOR]

In recent years, the widespread use of deep neural networks (DNNs) has facilitated great improvements in performance for computer vision tasks like image classification and object recognition. In most realistic computer vision applications, an input image undergoes some form of image distortion such as blur and additive noise during image acquisition or transmission. Deep networks trained on pristine images perform poorly when tested on such distortions. In this paper, we evaluate the effect of image distortions like Gaussian blur and additive noise on the activations of pre-trained convolutional filters. We propose a metric to identify the most noise susceptible convolutional filters and rank them in order of the highest gain in classification accuracy upon correction. In our proposed approach called DeepCorrect, we apply small stacks of convolutional layers with residual connections at the output of these ranked filters and train them to correct the worst distortion affected filter activations, while leaving the rest of the pre-trained filter outputs in the network unchanged. Performance results show that applying DeepCorrect models for common vision tasks like image classification (ImageNet), object recognition (Caltech-101, Caltech-256), and scene classification (SUN-397), significantly improves the robustness of DNNs against distorted images and outperforms other alternative approaches. [ABSTRACT FROM AUTHOR]

Image representation methods based on deep convolutional neural networks (CNNs) have achieved the state-of-the-art performance in various computer vision tasks, such as image retrieval and person re-identification. We recognize that more discriminative feature embeddings can be learned with supervised deep metric learning and handcrafted features for image retrieval and similar applications. In this paper, we propose a new supervised deep feature embedding with a handcrafted feature model. To fuse handcrafted feature information into CNNs and realize feature embeddings, a general fusion unit is proposed (called Fusion-Net). We also define a network loss function with image label information to realize supervised deep metric learning. Our extensive experimental results on the Stanford online products’ data set and the in-shop clothes retrieval data set demonstrate that our proposed methods outperform the existing state-of-the-art methods of image retrieval by a large margin. Moreover, we also explore the applications of the proposed methods in person re-identification and vehicle re-identification; the experimental results demonstrate both the effectiveness and efficiency of the proposed methods. [ABSTRACT FROM AUTHOR]

This is Part II of the paper, "Gray-Level Grouping (GLG): an Automatic Method for Optimized Image Contrast Enhancement". Part I of this paper introduced a new automatic contrast enhancement technique: gray-level grouping (GLG). GLG is a general and powerful technique, which can be conveniently applied to a broad variety of low-contrast images and outperforms conventional contrast enhancement techniques. However, the basic GLG method still has limitations and cannot enhance certain classes of low-contrast images well, e.g., images with a noisy background. The basic GLG also cannot fulfill certain special application purposes, e.g., enhancing only part of an image which corresponds to a certain segment of the image histogram. In order to break through these limitations, this paper introduces an extension of the basic GLG algorithm, selective gray-level grouping (SGLG), which groups the histogram components in different segments of the grayscale using different criteria and, hence, is able to enhance different parts of the histogram to various extents. This paper also introduces two new preprocessing methods to eliminate background noise in noisy low-contrast images so that such images can be properly enhanced by the (S)GLG technique. The extension of (S)GLG to color images is also discussed in this paper. SGLG and its variations extend the capability of the basic GLG to a larger variety of low-contrast images, and can fulfill special application requirements. SGLG and its variations not only produce results superior to conventional contrast enhancement techniques, but are also fully automatic under most circumstances, and are applicable to a broad variety of images. [ABSTRACT FROM AUTHOR]

This paper presents a new approach to represent an image by "verge points," which are defined as high-curvature points on the image surface. This representation offers a compact and reversible way to preserve the essence of the original image. Various applications, such as compression, edge detection, image enhancement, and image editing, can be achieved based on this representation. In this paper, the whole procedure for verge point representation is presented. Based on these verge points, image reconstruction can be easily achieved via iterative linear interpolation. These extracted verge points with compatible properties are further linked into verge curves to offer more compact representation. Progressive representation is also developed based on a multiscale extraction scheme. Some potential applications are then presented to demonstrate the versatility of this representation. [ABSTRACT FROM AUTHOR]

In this paper, the Cramér-Rao Lower Bound (CRLB) of image registration error using an isotropic fiducial mark is derived. The derived CRLB is a functional of the intensity profile of the fiducial mark. Following the development of the CRLB, a new method for designing an isotropic fiducial mark, suitable for digital image registration is presented. A parameterization method of the fiducial intensity profile is introduced which guarantees no aliasing effect when the fiducial mark is digitized with proper sampling rate. A method for computing the fiducial intensity profile, based on minimization of the CRLB registration error, and subject to certain practical constraints is developed. For imaging systems with significant low-pass effect, it is proposed in this paper to pre-emphasize the high frequency components of the fiducial mark by converting the designed gray-scale fiducial marks into binary fiducial marks. Experimental results show that the designed fiducial mark can provide very accurate registration results and that the registration accuracy is independent of its location. [ABSTRACT FROM AUTHOR]

Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision. In this paper, we discover that a high-quality visual saliency model can be learned from multiscale features extracted using deep convolutional neural networks (CNNs), which have had many successes in visual recognition tasks. For learning such saliency models, we introduce a neural network architecture, which has fully connected layers on top of CNNs responsible for feature extraction at three different scales. The penultimate layer of our neural network has been confirmed to be a discriminative high-level feature vector for saliency detection, which we call deep contrast feature. To generate a more robust feature, we integrate handcrafted low-level features with our deep contrast feature. To promote further research and evaluation of visual saliency models, we also construct a new large database of 4447 challenging images and their pixelwise saliency annotations. Experimental results demonstrate that our proposed method is capable of achieving the state-of-the-art performance on all public benchmarks, improving the F-measure by 6.12% and 10%, respectively, on the DUT-OMRON data set and our new data set (HKU-IS), and lowering the mean absolute error by 9% and 35.3%, respectively, on these two data sets. [ABSTRACT FROM PUBLISHER]

Accurate prediction of the visual attributes is significant in various recognition tasks. For many visual attributes, while it is very difficult to describe the exact degrees of their presences, by comparing the pairs of samples, the relative ordering of presences may be easily figured out. Based on this observation, instead of considering such attribute as binary attribute, the relative attribute method learns a ranking function for each attribute to provide more accurate and informative prediction results. In this paper, we also explore pairwise ranking for visual attribute prediction and propose to improve the relative attribute method in two aspects. First, we propose a relative tree method, which can achieve more accurate ranking in case of nonlinearly distributed visual data. Second, by resorting to randomization and ensemble learning, the relative tree method is extended to the relative forest method to further boost the accuracy and simultaneously reduce the computational cost. To validate the effectiveness of the proposed methods, we conduct extensive experiments on four databases: PubFig, OSR, FGNET, and WebFace. The results show that the proposed relative forest method not only outperforms the original relative attribute method, but also achieve the state-of-the-art accuracy for ordinal visual attribute prediction. [ABSTRACT FROM PUBLISHER]

Texture is an important characteristic for different computer vision tasks and applications. Local binary pattern (LBP) is considered one of the most efficient texture descriptors yet. However, LBP has some notable limitations, in particular its sensitivity to noise. In this paper, we address these criteria by introducing a novel texture descriptor, robust adaptive median binary pattern (RAMBP). RAMBP is based on a process involving classification of noisy pixels, adaptive analysis window, scale analysis, and a comparison of image medians. The proposed method handles images with highly noisy textures and increases the discriminative properties by capturing microstructure and macrostructure texture information. The method was evaluated on popular texture datasets for classification and retrieval tasks and under different high noise conditions. Without any training or prior knowledge of the noise type, RAMBP achieved the best classification compared to state-of-the-art techniques. It scored more than 90% under 50% impulse noise densities, more than 95% under Gaussian noised textures with a standard deviation $\sigma = 5$ , more than 99% under Gaussian blurred textures with a standard deviation $\sigma = 1.25$ , and more than 90% for mixed noise. The proposed method yielded competitive results and proved to be one of the best descriptors in noise-free texture classification. Furthermore, RAMBP showed high performance for the problem of noisy texture retrieval providing high scores of recall and precision measures for textures with high noise levels. Finally, compared with the state-of-the-art methods, RAMBP achieves a good running time with low feature dimensionality. [ABSTRACT FROM AUTHOR]

Image corner detection is very important in the fields of image analysis and computer vision. Curvature calculation techniques are used in many contour-based corner detectors. We identify that existing calculation of curvature is sensitive to local variation and noise in the discrete domain and does not perform well when corners are closely located. In this paper, discrete curvature representations of single and double corner models are investigated and obtained. A number of model properties have been discovered, which help us detect corners on contours. It is shown that the proposed method has a high corner resolution (the ability to accurately detect neighboring corners), and a corresponding corner resolution constant is also derived. Meanwhile, this method is less sensitive to any local variations and noise on the contour; and false corner detection is less likely to occur. The proposed detector is compared with seven state-of-the-art detectors. Three test images with ground truths are used to assess the detection capability and localization accuracy of these methods in cases with noise-free and different noise levels; 24 images with various scenes without ground truths are used to evaluate their repeatability under affine transformation, JPEG compression, and noise degradations. The experimental results show that our proposed detector attains a better overall performance. [ABSTRACT FROM AUTHOR]

Hashing has attracted increasing research attention in recent years due to its high efficiency of computation and storage in image retrieval. Recent works have demonstrated the superiority of simultaneous feature representations and hash functions learning with deep neural networks. However, most existing deep hashing methods directly learn the hash functions by encoding the global semantic information, while ignoring the local spatial information of images. The loss of local spatial structure makes the performance bottleneck of hash functions, therefore limiting its application for accurate similarity retrieval. In this paper, we propose a novel deep ordinal hashing (DOH) method, which learns ordinal representations to generate ranking-based hash codes by leveraging the ranking structure of feature space from both local and global views. In particular, to effectively build the ranking structure, we propose to learn the rank correlation space by exploiting the local spatial information from fully convolutional network and the global semantic information from the convolutional neural network simultaneously. More specifically, an effective spatial attention model is designed to capture the local spatial information by selectively learning well-specified locations closely related to target objects. In such hashing framework, the local spatial and global semantic nature of images is captured in an end-to-end ranking-to-hashing manner. Experimental results conducted on three widely used datasets demonstrate that the proposed DOH method significantly outperforms the state-of-the-art hashing methods. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (CNNs) have revolutionized the computer vision research and have seen unprecedented adoption for multiple tasks, such as classification, detection, and caption generation. However, they offer little transparency into their inner workings and are often treated as black boxes that deliver excellent performance. In this paper, we aim at alleviating this opaqueness of CNNs by providing visual explanations for the network’s predictions. Our approach can analyze a variety of CNN-based models trained for computer vision applications, such as object recognition and caption generation. Unlike the existing methods, we achieve this via unraveling the forward pass operation. The proposed method exploits feature dependencies across the layer hierarchy and uncovers the discriminative image locations that guide the network’s predictions. We name these locations CNN fixations, loosely analogous to human eye fixations. Our approach is a generic method that requires no architectural changes, additional training, or gradient computation, and computes the important image locations (CNN fixations). We demonstrate through a variety of applications that our approach is able to localize the discriminative image locations across different network architectures, diverse vision tasks, and data modalities. [ABSTRACT FROM AUTHOR]

Recent advances in object detection have led to the development of segmentation by detection approaches that integrate top-down geometric priors for multiclass object segmentation. A key yet under-addressed issue in utilizing top-down cues for the problem of multiclass object segmentation by detection is efficiently generating robust and accurate geometric priors. In this paper, we propose a random geometric prior forest scheme to obtain object-adaptive geometric priors efficiently and robustly. In the scheme, a testing object first searches for training neighbors with similar geometries using the random geometric prior forest, and then the geometry of the testing object is reconstructed by linearly combining the geometries of its neighbors. Our scheme enjoys several favorable properties when compared with conventional methods. First, it is robust and very fast because its inference does not suffer from bad initializations, poor local minimums or complex optimization. Second, the figure/ground geometries of training samples are utilized in a multitask manner. Third, our scheme is object-adaptive but does not require the labeling of parts or poselets, and thus, it is quite easy to implement. To demonstrate the effectiveness of the proposed scheme, we integrate the obtained top-down geometric priors with conventional bottom-up color cues in the frame of graph cut. The proposed random geometric prior forest achieves the best segmentation results of all of the methods tested on VOC2010/2012 and is 90 times faster than the current state-of-the-art method. [ABSTRACT FROM PUBLISHER]

Quality assessment of 3D images encounters more challenges than its 2D counterparts. Directly applying 2D image quality metrics is not the solution. In this paper, we propose a new full-reference quality assessment for stereoscopic images by learning binocular receptive field properties to be more in line with human visual perception. To be more specific, in the training phase, we learn a multiscale dictionary from the training database, so that the latent structure of images can be represented as a set of basis vectors. In the quality estimation phase, we compute sparse feature similarity index based on the estimated sparse coefficient vectors by considering their phase difference and amplitude difference, and compute global luminance similarity index by considering luminance changes. The final quality score is obtained by incorporating binocular combination based on sparse energy and sparse complexity. Experimental results on five public 3D image quality assessment databases demonstrate that in comparison with the most related existing methods, the devised algorithm achieves high consistency with subjective assessment. [ABSTRACT FROM PUBLISHER]

Facial expression recognition is one of the open problems in computer vision. Robust neutral face recognition in real time is a major challenge for various supervised learning-based facial expression recognition methods. This is due to the fact that supervised methods cannot accommodate all appearance variability across the faces with respect to race, pose, lighting, facial biases, and so on, in the limited amount of training data. Moreover, processing each and every frame to classify emotions is not required, as user stays neutral for majority of the time in usual applications like video chat or photo album/web browsing. Detecting neutral state at an early stage, thereby bypassing those frames from emotion classification would save the computational power. In this paper, we propose a light-weight neutral versus emotion classification engine, which acts as a pre-processer to the traditional supervised emotion classification approaches. It dynamically learns neutral appearance at key emotion (KE) points using a statistical texture model, constructed by a set of reference neutral frames for each user. The proposed method is made robust to various types of user head motions by accounting for affine distortions based on a statistical texture model. Robustness to dynamic shift of KE points is achieved by evaluating the similarities on a subset of neighborhood patches around each KE point using the prior information regarding the directionality of specific facial action units acting on the respective KE point. The proposed method, as a result, improves emotion recognition (ER) accuracy and simultaneously reduces computational complexity of the ER system, as validated on multiple databases. [ABSTRACT FROM AUTHOR]

Face recognition methods, which usually represent face images using holistic or local facial features, rely heavily on alignment. Their performances also suffer a severe degradation under variations in expressions or poses, especially when there is one gallery per subject only. With the easy access to high-resolution (HR) face images nowadays, some HR face databases have recently been developed. However, few studies have tackled the use of HR information for face recognition or verification. In this paper, we propose a pose-invariant face-verification method, which is robust to alignment errors, using the HR information based on pore-scale facial features. A new keypoint descriptor, namely, pore-Principal Component Analysis (PCA)-Scale Invariant Feature Transform (PPCASIFT)—adapted from PCA-SIFT—is devised for the extraction of a compact set of distinctive pore-scale facial features. Having matched the pore-scale features of two-face regions, an effective robust-fitting scheme is proposed for the face-verification task. Experiments show that, with one frontal-view gallery only per subject, our proposed method outperforms a number of standard verification methods, and can achieve excellent accuracy even the faces are under large variations in expression and pose. [ABSTRACT FROM AUTHOR]

Studies in neuroscience and biological vision have shown that the human retina has strong computational power, and its information representation supports vision tasks on both ventral and dorsal pathways. In this paper, a new local image descriptor, termed distinctive efficient robust features (DERF), is derived by modeling the response and distribution properties of the parvocellular-projecting ganglion cells in the primate retina. DERF features exponential scale distribution, exponential grid structure, and circularly symmetric function difference of Gaussian (DoG) used as a convolution kernel, all of which are consistent with the characteristics of the ganglion cell array found in neurophysiology, anatomy, and biophysics. In addition, a new explanation for local descriptor design is presented from the perspective of wavelet tight frames. DoG is naturally a wavelet, and the structure of the grid points array in our descriptor is closely related to the spatial sampling of wavelets. The DoG wavelet itself forms a frame, and when we modulate the parameters of our descriptor to make the frame tighter, the performance of the DERF descriptor improves accordingly. This is verified by designing a tight frame DoG, which leads to much better performance. Extensive experiments conducted in the image matching task on the multiview stereo correspondence data set demonstrate that DERF outperforms state of the art methods for both hand-crafted and learned descriptors, while remaining robust and being much faster to compute. [ABSTRACT FROM AUTHOR]

Depth image compression is important for compact representation of 3D visual data in texture-plus-depth format, where texture and depth maps from one or more viewpoints are encoded and transmitted. A decoder can then synthesize a freely chosen virtual view via depth-image-based rendering using nearby coded texture and depth maps as reference. Further, depth information can be used in other image processing applications beyond view synthesis, such as object identification, segmentation, and so on. In this paper, we leverage on the observation that neighboring pixels of similar depth have similar motion to efficiently encode depth video. Specifically, we divide a depth block containing two zones of distinct values (e.g., foreground and background) into two arbitrarily shaped regions (sub-blocks) along the dividing boundary before performing separate motion prediction (MP). While such arbitrarily shaped sub-block MP can lead to very small prediction residuals (resulting in few bits required for residual coding), it incurs an overhead to transmit the dividing boundaries for sub-block identification at decoder. To minimize this overhead, we first devise a scheme called arithmetic edge coding (AEC) to efficiently code boundaries that divide blocks into sub-blocks. Specifically, we propose to incorporate the boundary geometrical correlation in an adaptive arithmetic coder in the form of a statistical model. Then, we propose two optimization procedures to further improve the edge coding performance of AEC for a given depth image. The first procedure operates within a code block, and allows lossy compression of the detected block boundary to lower the cost of AEC, with an option to augment boundary depth pixel values matching the new boundary, given the augmented pixels do not adversely affect synthesized view distortion. The second procedure operates across code blocks, and systematically identifies blocks along an object contour that should be coded using sub-block MP via a rate-distortion optimized trellis. Experimental results show an average overall bitrate reduction of up to 33% over classical H.264/AVC. [ABSTRACT FROM AUTHOR]

Fast and accurate motion estimation takes an important place in many fields of computer vision and image processing. Using Radon transform to compute projections of the images along specified directions is an effective way to show the relationship between the 2D image object and its projections and estimate motions between the images. All existing projection-based motion estimation methods without the use of iteration have a severe defect that only five of the six affine parameters can be estimated. There are some other methods that can estimate the six parameters, but most of them are usually based on a certain iterative framework, which is computationally intensive and sensitively dependent on the initial values. In this paper, a novel method based on Radon transform is proposed to estimate all the six affine parameters directly. The relationship in the projection domain between a pair of images connected by an affine motion is studied and a linear model is established, by which all the six affine parameters can be directively found. The employment of a hierarchical framework can produce more accurate results. The experimental results reveal that the proposed method has a much better performance than the state-of-the-art methods in this field. [ABSTRACT FROM AUTHOR]

Nonnegative matrix factorization (NMF) has received considerable attention in image processing, computer vision, and patter recognition. An important variant of NMF is nonnegative graph embedding (NGE), which encodes the statistical or geometric information of data in the process of matrix factorization. The NGE offers a general framework for unsupervised/supervised settings. However, NGE-like algorithms often suffer from noisy data, unreliable graphs, and noisy labels, which are commonly encountered in real-world applications. To address these issues, in this paper, we first propose a robust nonnegative graph embedding (RNGE) framework, where the joint sparsity in both graph embedding and data reconstruction endues robustness to undesirable noises. Next, we present a robust seminonnegative graph embedding (RsNGE) framework, which only constrains the coefficient matrix to be nonnegative while places no constraint on the base matrix. This extends the applicable range of RNGE to data which are not nonnegative and endows more discriminative power of the learnt base matrix. The RNGE/RsNGE provides a general formulation such that all the algorithms unified within the graph embedding framework can be easily extended to obtain their robust nonnegative/seminonnegative solutions. Further, we develop elegant multiplicative updating solutions that can solve RNGE/RsNGE efficiently and offer a rigorous convergence analysis. We conduct extensive experiments on four real-world data sets and compare the proposed RNGE/RsNGE to other representative NMF variants and data factorization methods. The experimental results demonstrate the robustness and effectiveness of the proposed approaches. [ABSTRACT FROM AUTHOR]

Recently, skeleton-based action recognition becomes popular owing to the development of cost-effective depth sensors and fast pose estimation algorithms. Traditional methods based on pose descriptors often fail on large-scale datasets due to the limited representation of engineered features. Recent recurrent neural networks (RNN) based approaches mostly focus on the temporal evolution of body joints and neglect the geometric relations. In this paper, we aim to leverage the geometric relations among joints for action recognition. We introduce three primitive geometries: joints, edges, and surfaces. Accordingly, a generic end-to-end RNN based network is designed to accommodate the three inputs. For action recognition, a novel viewpoint transformation layer and temporal dropout layers are utilized in the RNN based network to learn robust representations. And for action detection, we first perform frame-wise action classification, then exploit a novel multi-scale sliding window algorithm. Experiments on the large-scale 3D action recognition benchmark datasets show that joints, edges, and surfaces are effective and complementary for different actions. Our approaches dramatically outperform the existing state-of-the-art methods for both tasks of action recognition and action detection. [ABSTRACT FROM AUTHOR]

Vehicle re-identification (re-ID) is an area that has received far less attention in the computer vision community than the prevalent person re-ID. Possible reasons for this slow progress are the lack of appropriate research data and the special 3D structure of a vehicle. Previous works have generally focused on some specific views (e.g., front); but, these methods are less effective in realistic scenarios, where vehicles usually appear in arbitrary views to cameras. In this paper, we focus on the uncertainty of vehicle viewpoint in re-ID, proposing two end-to-end deep architectures: the Spatially Concatenated ConvNet and convolutional neural network (CNN)-LSTM bi-directional loop. Our models exploit the great advantages of the CNN and long short-term memory (LSTM) to learn transformations across different viewpoints of vehicles. Thus, a multi-view vehicle representation containing all viewpoints’ information can be inferred from the only one input view, and then used for learning to measure distance. To verify our models, we also introduce a Toy Car RE-ID data set with images from multiple viewpoints of 200 vehicles. We evaluate our proposed methods on the Toy Car RE-ID data set and the public Multi-View Car, VehicleID, and VeRi data sets. Experimental results illustrate that our models achieve consistent improvements over the state-of-the-art vehicle re-ID approaches. [ABSTRACT FROM AUTHOR]