Search

This paper studies the composition in portrait paintings and develops an algorithm to improve the composition of portrait photographs based on example portrait paintings. A study of portrait paintings shows that the placement of the face and the figure is pose-related. Based on this observation, this paper develops an algorithm to improve the composition of a portrait photograph by learning the placement of the face and the figure from an example portrait painting. This example portrait painting is selected based on the similarity of its figure pose to that of the input photograph. This similarity measure is modeled as a graph matching problem. Finally, space cropping is performed using an optimization function to assign a similar location for each body part of the figure in the photograph with that of the figure in the example portrait painting. The experimental results demonstrate the effectiveness of the proposed method. A user study shows that the proposed pose-based composition improvement is preferred more than rule-based methods and learning-based methods. [ABSTRACT FROM AUTHOR]

Flexible block partition and newly adopted intra coding tools bring significant performance improvement for next generation video coding, and meanwhile introduce non-negligible encoding complexity increment. This paper presents a scalable intra coding optimization (SICO) scheme for the third generation of audio video coding standard (AVS3). The complexity distribution and inheriting relationship among different partitioning, as well as intra prediction modes, are systematically analyzed. Subsequently, low-complexity algorithms are proposed, which could early exclude unlikely coding modes safely. In particular, a data-driven binary classifier is elegantly trained for the determination of coding unit partitioning. Moreover, the preliminary coding information can be exhaustively utilized for the mode decision in a low-cost manner. The proposed method provides scalable intra coding optimizing solutions, which is eligible to cater to various application scenarios. Experimental results show that the proposed method could achieve a wide range of encoding complexity reduction from 18% to 76% with moderate compression performance loss. One implementation of the proposed method has been adopted to the AVS3 reference software. [ABSTRACT FROM AUTHOR]

Recently, crowdsourcing-based content delivery networks (CDN) emerge as a promising technology that can distribute massive video content to a vast number of Internet users by crawling bandwidth and storage resources from Internet end devices. Any ordinary Internet users with excessive resources can be recruited into such systems as mini-servers. Different from edge servers equipped with dedicated resources in traditional CDNs, the resource of a single mini-server is scarce and volatile that can vary severely with time, since its bandwidth is shared by many different applications. How to build a robust high performance crowdsourcing-based CDN system has attracted contributions from both academia and industry, but how to solve the drawback caused by unstable uploading bandwidth is still a challenging problem. So far, a prevalent methodology is to migrate the strategies implemented by traditional CDNs into crowdsourcing-based CDN systems based on the fact that these two kinds of systems share many similarities. In this paper, our argument is that the content delivery time can be reduced by replicating coded content on mini-servers (which is almost useless for edge servers in traditional CDNs) to enable downloading users to automatically adapt their downloading progress with oscillating bandwidth capacity from different mini-servers. Theoretical model is created to derive the performance improvement (evaluated in term of average file downloading time) achieved by our strategy, which is further validated via simulation. This paper not only provides system designers a more efficient content replication solution, but also can push forward the development of the crowdsourcing-based CDNs. [ABSTRACT FROM AUTHOR]

Reversible data hiding hides data in an image such that the original image is recoverable. This paper presents a novel embedding framework with reduced distortion called skewed histogram shifting using a pair of extreme predictions. Unlike traditional prediction error histogram shifting schemes, where only one good prediction is used to generate a prediction error histogram, the proposed scheme uses a pair of extreme predictions to generate two skewed histograms. By exploiting the structure of the skewed histogram, only the pixels from the peak and the short tail are used for embedding, which decreases the distortion from the lesser number of pixels being shifted. Detailed experiments and analysis are provided using several image databases. [ABSTRACT FROM AUTHOR]

In this paper, an adaptive block coding order for intra prediction is proposed. Modern video coding standards, including the most recent High Efficiency Video Coding (HEVC), utilize fixed scan orders in processing blocks during intra coding. However, the fixed scan orders typically result in residual blocks with noticeable edge patterns. That means the fixed scan orders cannot fully exploit the content-adaptive spatial correlations between adjacent blocks, thus the bitrate after compression tends to be large. To reduce the bitrate induced by inaccurate intra prediction, the proposed approach adaptively chooses both the block and subblock coding orders by minimizing the coding cost. Specifically, determining the block coding order is formulated as a traveling salesman problem that is solved using dynamic programming. Besides the block coding order, we also design the subblock coding order in each block with an adaptive manner. The experimental results demonstrate a Bjøntegaard-Delta-rate reduction of up to 4.4% compared with HEVC anchor. [ABSTRACT FROM AUTHOR]

Pairwise prediction-error expansion (pairwise PEE) is a recent technique for the high-dimensional reversible data hiding. However, in the absence of adaptive embedding, its potential has not been fully exploited. In this paper, we propose the adaptive pixel pairing (APP) and the adaptive mapping selection for the enhancement of pairwise PEE. Our motivation is twofold: building a sharper 2D histogram and designing the effective 2D mapping for it. In APP, we consider to increase the similarity between pixels in a pair, by excluding the rough pixels from pairing and only putting the smooth pixels into pairs. In this way, the pixels in a pair have a larger possibility of being equal, and thus the resulted 2D prediction-error histogram (PEH) has lower entropy. Next, the adaptive mapping selection mechanism is introduced to properly determine the optimal modification, based on “whether it fits for the resulted PEH” rather than heuristic experience. The experimental results show that the proposed method has a significant improvement over the pairwise PEE. [ABSTRACT FROM AUTHOR]

Different from conventional haze removal methods based on a single image, near-infrared imaging can provide two types of multimodal images: one is the near-infrared image and the other is the visible color image. These two images have different characteristics regarding color and visibility. The captured near-infrared image is haze-free, but it is grayscale, whereas the visible color image has colors, but it contains haze. There are serious discrepancies in terms of brightness and image structures between the near-infrared image and the visible color image. Due to this discrepancy, the direct use of the near-infrared image for haze removal causes a color distortion problem during near-infrared fusion. The key objective for the near-infrared fusion is therefore to remove the color distortion as well as the haze. To achieve this objective, this paper presents a new near-infrared fusion model that combines the proposed new color and depth regularizations with the conventional haze degradation model. The proposed color regularization sets the color range of the unknown haze-free image based on the combination of the two colors of the colorized near-infrared image and the captured visible color image. That is, the proposed color regularization can provide color information for the unknown haze-free color image. The new depth regularization enables the consecutively estimated depth maps not to be largely deviated, thereby transferring natural-looking colors and high visibility of the colorized near-infrared image into the preliminary dehazed version of the captured visible color image with color distortion and edge artifacts. Experimental results show that the proposed color and depth regularizations can help remove the color distortion and the haze simultaneously. The effectiveness of the proposed color regularization for the near-infrared fusion is verified by comparing it with other conventional regularizations. [ABSTRACT FROM AUTHOR]

Video question generation is a challenging task in visual information retrieval, which generates questions given a sequence of video frames. The existing methods mainly tackle the problem of single-turn video question generation, but single-turn conversation usually can’t meet the needs of video information acquisition. In this paper, we propose a new framework for single-turn VQG, which introduces attention mechanism to process inference of dialog history. And we introduce selection mechanism to choose from the candidate questions generated by each round of dialog history. In the framework, we leverage a recent video question answering model to predict the answer to the generated question and adopt the answer quality as rewards to fine-tune our model based on a reinforced learning mechanism. We also introduce a new task of multi-turn video question generation (M-VQG), which is generating multiple questions based on dialog history and video information to build conversation step by step. Our method achieves the state-of-the-art performance of the single-turn VQG task on two large-scale datasets, YouTube-Clips and TACoS-MultiLevel, and provides a baseline approach for M-VQG task. [ABSTRACT FROM AUTHOR]

Recently, Li et al. proposed an effective non-additive distortion model for JPEG steganography by preserving Block Boundary Continuity (BBC) in the spatial domain. However, the method based on BBC only explored how the modifications of DCT coefficient pairs at the same mode in adjacent blocks will impact on BBC. In this paper, we propose a method to enhance the BBC, called BBC++, by considering the mutual impact on the BBC from all DCT coefficients in adjacent blocks. To do that, we design updating strategies for both covers and costs in multi-round embedding processions. During the embedding, the cover is updated to repair the BBC after embedding and the corresponding costs are updated to keep the BBC from being destroyed in the next embedding. Experimental results show that the BBC++ can better maintain BBC and outperform previous non-additive distortion steganography when resisting modern JPEG steganalyzers. [ABSTRACT FROM AUTHOR]

The structures of feature vectors-based semisupervised/supervised learning have gained considerable interest in recent years due to their effectiveness for better object modeling and classification. In many machine learning and computer vision tasks, a critical issue is the similarity between two feature vectors. In this paper, we present a novel technique to measure similarities among feature vectors by decomposing each feature vector as an \ell 1 sparse linear combination of the rest of the feature vectors. The main idea is that the coefficients in such sparse decomposition reflect the features’ neighborhood structure, thus providing better similarity measures among the decomposed feature vector and the rest of the feature vectors. The proposed approach is applied to label propagation and action recognition, and is evaluated on several commonly used datasets. The experimental results show that the proposed sparsity-induced similarity measure significantly improves the performance of both label propagation and action recognition. [ABSTRACT FROM PUBLISHER]

Subspace data representation has recently become a common practice in many computer vision tasks. Low-rank representation (LRR) is one of the most successful models for clustering vectorial data according to their subspace structures. This paper explores the possibility of extending LRR for subspace data on Grassmann manifold. Rather than directly embedding the Grassmann manifold into the symmetric matrix space, an extrinsic view is taken to build the self-representation in the local area of the tangent space at each Grassmannian point, resulting in a localized LRR method on Grassmann manifold. A novel algorithm for solving the proposed model is investigated and implemented. The performance of the new clustering algorithm is assessed through experiments on several real-world data sets including MNIST handwritten digits, ballet video clips, SKIG action clips, and DynTex++ data set and highway traffic video clips. The experimental results show that the new method outperforms a number of state-of-the-art clustering methods. [ABSTRACT FROM AUTHOR]

In this paper, we propose a nonlinear structural hashing approach to learn compact binary codes for scalable video search. Unlike most existing video hashing methods which consider image frames within a video separately for binary code learning, we develop a multi-layer neural network to learn compact and discriminative binary codes by exploiting both the structural information between different frames within a video and the nonlinear relationship between video samples. To be specific, we learn these binary codes under two different constraints at the output of our network: 1) the distance between the learned binary codes for frames within the same scene is minimized and 2) the distance between the learned binary matrices for a video pair with the same label is less than a threshold and that for a video pair with different labels is larger than a threshold. To better measure the structural information of the scenes from videos, we employ a subspace clustering method to cluster frames into different scenes. Moreover, we design multiple hierarchical nonlinear transformations to preserve the nonlinear relationship between videos. Experimental results on three video data sets show that our method outperforms state-of-the-art hashing approaches on the scalable video search task. [ABSTRACT FROM AUTHOR]

This paper aims for the task of text-to-video retrieval, where given a query in the form of a natural-language sentence, it is asked to retrieve videos which are semantically relevant to the given query, from a great number of unlabeled videos. The success of this task depends on cross-modal representation learning that projects both videos and sentences into common spaces for semantic similarity computation. In this work, we concentrate on video representation learning, an essential component for text-to-video retrieval. Inspired by the reading strategy of humans, we propose a Reading-strategy Inspired Visual Representation Learning (RIVRL) to represent videos, which consists of two branches: a previewing branch and an intensive-reading branch. The previewing branch is designed to briefly capture the overview information of videos, while the intensive-reading branch is designed to obtain more in-depth information. Moreover, the intensive-reading branch is aware of the video overview captured by the previewing branch. Such holistic information is found to be useful for the intensive-reading branch to extract more fine-grained features. Extensive experiments on three datasets are conducted, where our model RIVRL achieves a new state-of-the-art on TGIF and VATEX. Moreover, on MSR-VTT, our model using two video features shows comparable performance to the state-of-the-art using seven video features and even outperforms models pre-trained on the large-scale HowTo100M dataset. Code is available at https://github.com/LiJiaBei-7/rivrl. [ABSTRACT FROM AUTHOR]

The explosive growth in high-dimensional visual data requires effective regularization techniques to utilize the underlying low-dimensional structure. We consider low-rank matrix recovery, and many existing approaches are based on the nuclear norm regularization. Recently, truncated nuclear norm (TNNR) has been proposed to achieve a better approximation to the rank function than that of the traditional nuclear norm. TNNR was defined by the nuclear norm by subtracting the sum of the largest $r$ singular values. However, the estimation of $r$ is not trivial. In addition, the original algorithm based on TNNR only considers the matrix completion cases and requires double loops, which is not quite computationally efficient. Correspondingly, in this paper, we propose the adaptive bisection method to adaptively estimate $r$ , which can efficiently reduce the cost of computation. Moreover, to further accelerate computing, we apply iteratively reweighted nuclear norm to solve the nonconvex TNNR directly, and the convergence can also be guaranteed. Finally, we extend the applications of TNNR from the matrix completion problems to the general low-rank matrix recovery. Extensive experiments validate the superiority of the proposed algorithm over the state-of the-art methods. [ABSTRACT FROM AUTHOR]

Pedestrian tracking in video has been a popular research topic with many practical applications. In order to improve tracking performance, many ideas have been proposed, among which the use of geometric information is one of the most popular directions in recent research. In this paper, we propose a novel multicamera pedestrian tracking framework, which incorporates the structural information of pedestrian groups in the crowd. In this framework, first, a new cross-camera model is proposed, which enables the fusion of the confidence information from all camera views. Second, the group structures on the ground plane provide extra constraints between pedestrians. Third, the structured support vector machine is adopted to update the cross-camera model for each pedestrian according to the most recent tracked location. The experiments and detailed analysis are conducted on challenging data. The results demonstrate that the improvement in tracking performance is significant when a group structure is integrated. [ABSTRACT FROM PUBLISHER]

An online approach to learn elementary groups containing only two targets, i.e., pedestrians, for inferring high-level context is introduced to improve multiperson tracking. In most existing data association-based tracking approaches, only low-level information (e.g., time, appearance, and motion) is used to build the affinity model, and each target is considered as an independent agent. Unlike those previous methods, in this paper, an online learned social grouping behavior model is used to provide more robust tracklet affinities. A disjoint grouping graph is used to encode social grouping behavior of pairwise targets, where each node represents an elementary group of two targets, and two nodes are connected if they share a common target. Probabilities of the uncertain target in two connected nodes being the same person are inferred from each edge of the grouping graph. Relationships between elementary groups are discovered by group tracking, and a nonlinear motion map is used for explaining nonlinear motion pattern between elementary groups. The proposed method is efficient, able to handle group split and merge, and can be easily integrated into any basic affinity model. The approach is evaluated on four data sets, and it shows significant improvements compared with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Automatically identifying characters in movies has attracted researchers’ interest and led to several significant and interesting applications. However, due to the vast variation in character appearance as well as the weakness and ambiguity of available annotation, it is still a challenging problem. In this paper, we investigate this problem with the supervision of actor-character name correspondence provided by the movie cast. Our proposed framework, namely, Cast2Face, is featured by: 1) we restrict the assigned names within the set of character names in the cast; 2) for each character, by using the corresponding actor and movie name as keywords, we retrieve from the Google image search and get a group of face images to form the gallery set; 3) the probe face tracks in the movie are then identified as one of the actors by a robust kernel multitask joint sparse representation and classification method; and 4) the conditional random field model with consideration of the constraints between face tracks is introduced to enhance the final labeling. Finally, the assigned actor name of a face track is then mapped to the character name based on the cast again. Besides face naming, we further apply the proposed method to spotlight the summarization of a particular actor in his/her movies. We conduct extensive experiments and empirical evaluations on several feature-length movies to demonstrate the satisfying performance of our method. [ABSTRACT FROM AUTHOR]

We present a versatile model, FaceAnime, for various video generation tasks from still images. Video generation from a single face image is an interesting problem and usually tackled by utilizing Generative Adversarial Networks (GANs) to integrate information from the input face image and a sequence of sparse facial landmarks. However, the generated face images usually suffer from quality loss, image distortion, identity change, and expression mismatching due to the weak representation capacity of the facial landmarks. In this paper, we propose to “imagine” a face video from a single face image according to the reconstructed 3D face dynamics, aiming to generate a realistic and identity-preserving face video, with precisely predicted pose and facial expression. The 3D dynamics reveal changes of the facial expression and motion, and can serve as a strong prior knowledge for guiding highly realistic face video generation. In particular, we explore face video prediction and exploit a well-designed 3D dynamic prediction network to predict a 3D dynamic sequence for a single face image. The 3D dynamics are then further rendered by the sparse texture mapping algorithm to recover structural details and sparse textures for generating face frames. Our model is versatile for various AR/VR and entertainment applications, such as face video retargeting and face video prediction. Superior experimental results have well demonstrated its effectiveness in generating high-fidelity, identity-preserving, and visually pleasant face video clips from a single source face image. [ABSTRACT FROM AUTHOR]

This paper proposes a new metric to measure judder artifacts of video sequences. The judder artifacts appear as non-smooth motions in hold-type displays when the frame rate is low and object motion is fast. To analyze the judder artifacts in video sequences, the proposed judder metric is defined by analyzing the effects and cross-relations of judder features in the video sequences. The judder features include spatial features of image gradients and temporal features of motion vectors and the frame rate. In addition, sensitivity of the human visual system (HVS) is considered to determine the perceptual judder artifacts because it has special characteristics of sensitivity to image brightness and contrast. Therefore, a sensitivity map of the HVS is used to mask the judder artifacts. Then, the degree of perceptual judder artifacts is estimated using the judder features and a regression model. The experimental results demonstrate that the proposed judder metric is highly correlated with the subjective assessment results. [ABSTRACT FROM AUTHOR]

As increasing attention is paid to human action recognition from skeleton data, this paper focuses on such tasks by proposing a hierarchical model to discover the structure information of body-parts involved in actions for better analysis of human actions in the skeleton data. Considering human actions as simultaneous motions of body-parts of the human skeleton, we propose a hierarchical model to simultaneously apply discriminative body-parts selection at a same scale and group coupling of bundles of body-parts at different scales, while we decompose the human skeleton into a hierarchy of body-parts of varying scales. To represent such hierarchy of body-parts, we accordingly build a hierarchical rotation and relative velocity (HRRV) descriptor. The hierarchical representations encoded by Fisher vectors of the HRRV descriptors are properly formulated into the hierarchical model via the proposed mixed norm, to apply the sparse selection of body-parts and regularize the structure of such hierarchy of body-parts. The extensive evaluations on three challenging datasets demonstrate the effectiveness of our proposed approach, which achieves superior performance compared to the state-of-the-art algorithms on datasets with various sizes, showing it is more widely applicable than existing approaches. [ABSTRACT FROM AUTHOR]

In this paper, we present novel sharp attention networks by adaptively sampling feature maps from convolutional neural networks for person re-identification (re-ID) problems. Due to the introduction of sampling-based attention models, the proposed approach can adaptively generate sharper attention-aware feature masks. This greatly differs from the gating-based attention mechanism that relies on soft gating functions to select the relevant features for person re-ID. In contrast, the proposed sampling-based attention mechanism allows us to effectively trim irrelevant features by enforcing the resultant feature masks to focus on the most discriminative features. It can produce sharper attentions that is more assertive in localizing subtle features relevant to re-identifying people across cameras. For this purpose, a differentiable Gumbel-Softmax sampler is employed to approximate the Bernoulli sampling to train the sharp attention networks. Extensive experimental evaluations demonstrate the superiority of this new sharp attention model for person re-ID over other related existing, published state-of-the-art works on three challenging benchmarks, including CUHK03, Market-1501, and DukeMTMC-reID. [ABSTRACT FROM AUTHOR]

Preserving projection-based methods are good for finding the manifold structure embedded in data. As they use the Euclidean distance as a metric, which is sensitive to noise and outliers in data, nuclear norm-based 2D locality preserving projection (NN-2DLPP) is thus proposed to improve the robustness of 2DLPP. However, NN-2DLPP does not consider the discriminant ability of data. In order to improve the discriminant ability of preserving projection methods, in this paper, we use preserving projection learning with structurally incoherence of data and propose structurally incoherent low-rank 2DLPP (SILR-2DLPP) for image classification. This approach provides a discriminative representation of preserving projection learning by recovering the distinct different classes of the data. SILR-2DLPP searches the optimal subspace and low-rank representation simultaneously. We further extend SILR-2DLPP to a kernel case and propose kernel SILR-2DLPP (KSILR-2DLPP) to obtain a nonlinear representation. The theoretical analysis including the convergence and computational complexity of SILR-2DLPP are presented. To verify the performance of SILR-2DLPP and KSILR-2DLPP, six well-known image databases were used in the experiments. The experimental results show that the proposed methods are superior to the previous preserving projection methods for image classification. [ABSTRACT FROM AUTHOR]

In this paper, we propose a deep convolutional neural network (DCNN) architecture that addresses the problem of video/image concept annotation by exploiting concept relations at two different levels. At the first level, we build on ideas from multi-task learning, and propose an approach to learn concept-specific representations that are sparse, linear combinations of representations of latent concepts. By enforcing the sharing of the latent concept representations, we exploit the implicit relations between the target concepts. At a second level, we build on ideas from structured output learning and propose the introduction, at training time, of a new cost term that explicitly models the correlations between the concepts. By doing so, we explicitly model the structure in the output space (i.e., the concept labels). Both of the above are implemented using standard convolutional layers and are incorporated in a single DCNN architecture that can then be trained end-to-end with standard back-propagation. Experiments on four large-scale video and image data sets show that the proposed DCNN improves concept annotation accuracy and outperforms the related state-of-the-art methods. [ABSTRACT FROM AUTHOR]

During 3-D video communication, transmission errors, such as packet loss, could happen to the texture and depth sequences. View synthesis distortion will be generated when these sequences are used to synthesize virtual views according to the depth-image-based rendering method. A depth-value-based graphical model (DVGM) has been employed to achieve the accurate packet-loss-caused view synthesis distortion estimation (VSDE). However, the DVGM models the complicated view synthesis processes at depth-value level, which costs too much computation and is difficult to be applied in practice. In this paper, a depth-bin-based graphical model (DBGM) is developed, in which the complicated view synthesis processes are modeled at depth-bin level so that it can be used for the fast VSDE with 1-D parallel camera configuration. To this end, several depth values are fused into one depth bin, and a depth-bin-oriented rule is developed to handle the warping competition process. Then, the properties of the depth bin are analyzed and utilized to form the DBGM. Finally, a conversion algorithm is developed to convert the per-pixel input depth value probability distribution into the depth-bin format. Experimental results verify that our proposed method is 8– $32\times $ faster and requires 17%–60% less memory than the DVGM, with exactly the same accuracy. [ABSTRACT FROM AUTHOR]

Rate control is a key technique for video communication systems. The aim of rate control is to transmit the best possible quality video sequences under various restrictions, such as channel bandwidth, buffer capacity, maximum time delay allowed for a given service, and so on. The $\lambda $ domain rate control technique ($\lambda $ -RC) has been integrated into the latest High Efficiency Video Coding standard (H.265/HEVC) test model, due to its accurate bit estimation and high rate-distortion performance. However, it is found that the $\lambda $ -RC is not the optimal choice under the random-access configuration. When the random-access configuration is used, pictures are organized into temporal layers, where pictures in different layers are of different importance in terms of prediction. In this paper, a picture level lambda domain rate control technique for the random-access configuration in H.265/HEVC is proposed. The influence of temporal layers is effectively considered in the proposed algorithm referred to as TL- $\lambda $ -PRC. Experimental results verify that the proposed TL- $\lambda $ -PRC is efficient in coding performance and accurate in bit estimation. Compared with the $\lambda $ -RC with the fixed ration bit allocation which has been implemented in the test model of H.265/HEVC (HM 14.0), TL- $\lambda $ -PRC achieves an average reduction of 4.10% and 3.49% for slow motion and fast motion sequences, respectively, in BD-rate (Bjøntegaard-Delta bitrate) with more accurate bit estimation. The performance of different algorithms in terms of algorithm complexity and quality fluctuation are also carefully analyzed in this contribution. [ABSTRACT FROM AUTHOR]

This paper explores the problem of multi-view spectral clustering (MVSC) based on tensor low-rank modeling. Unlike the existing methods that all adopt an off-the-shelf tensor low-rank norm without considering the special characteristics of the tensor in MVSC, we design a novel structured tensor low-rank norm tailored to MVSC. Specifically, we explicitly impose a symmetric low-rank constraint and a structured sparse low-rank constraint on the frontal and horizontal slices of the tensor to characterize the intra-view and inter-view relationships, respectively. Moreover, the two constraints could be jointly optimized to achieve mutual refinement. On basis of the novel tensor low-rank norm, we formulate MVSC as a convex low-rank tensor recovery problem, which is then efficiently solved with an augmented Lagrange multiplier-based method iteratively. Extensive experimental results on seven commonly used benchmark datasets show that the proposed method outperforms state-of-the-art methods to a significant extent. Impressively, our method is able to produce perfect clustering. In addition, the parameters of our method can be easily tuned, and the proposed model is robust to different datasets, demonstrating its potential in practice. The code is available at https://github.com/jyh-learning/MVSC-TLRR. [ABSTRACT FROM AUTHOR]

In stereo matching, it is a challengeable task to effectively deal with occlusions between objects, which often cause disparity errors along object boundaries. In this paper, we propose discontinuity-preserving stereo matching based on reliability. We first estimate an initial disparity map by segmentation-based adaptive weights. Then, we obtain reliability for each pixel in an image, which indicates the correctness of the estimated disparity based on the matching cost. Finally, we minimize disparity errors caused by occlusions between objects using reliability and produce discontinuity-preserving disparity maps. Experiments on the Middlebury data set show that the proposed method successfully preserves disparity discontinuities along object boundaries and outperforms the state-of-the-art stereo matching methods. [ABSTRACT FROM AUTHOR]

This paper presents a novel multidirectional weighted interpolation algorithm for color filter array interpolation. Our proposed method has two contributions to demosaicking. First, different from conventional interpolation methods based on two directions or four directions, the proposed method exploits to greater degree correlations among neighboring pixels along eight directions to improve the interpolation performance. Second, we propose an efficient postprocessing method to reduce interpolation artifacts based on the color difference planes. Compared with conventional state-of-the-art demosaicking algorithms, our experimental results show the proposed algorithm provides superior performance in both objective and subjective image quality. Furthermore, this implementation has moderate computational complexity. [ABSTRACT FROM PUBLISHER]

Metric and similarity learning are important approaches to classification and retrieval. To efficiently learn a distance metric or a similarity function, online learning algorithms have been widely applied. In general, however, existing online metric and similarity learning algorithms have limited performance in real-world classification and retrieval applications. In this paper, we introduce a convergent online metric learning model named scalable large margin online metric learning (SLMOML). SLMOML belongs to the passive-aggressive learning family. At each step, it adopts the LogDet divergence to maintain the closeness between two successively learned Mahalanobis matrices, and utilizes the hinge loss to enforce a large margin between relatively dissimilar samples. More importantly, the Mahalanobis matrix can be updated by closed-form solution at each step. Furthermore, if the initial matrix is positive semi-definite (PSD), the learned matrices in the following steps are always PSD. Based on the Karush–Kuhn–Tucker conditions and the built equivalence between the passive-aggressive learning family and the Bregman projections, we have proved the global convergence of SLMOML. Extensive experiments on classification and retrieval tasks demonstrate the effectiveness and efficiency of SLMOML. [ABSTRACT FROM AUTHOR]

In order to improve the interpretation of principal components, many sparse principal component analysis (PCA) methods have been proposed by in the form of self-contained regression-type. In this paper, we generalize the steps needed to move from PCA-like methods to its self-contained regression-type, and propose a joint sparse pixel weighted PCA method. More specifically, we generalize a self-contained regression-type framework of graph embedding. Unlike the regression-type of graph embedding relying on the regular low-dimensional data, the self-contained regression-type framework does not rely on the regular low-dimensional data of graph embedding. The learned low-dimensional data in the form of self-contained regression theoretically approximates to the regular low-dimensional data. Under this self-contained regression-type, sparse regularization term can be arbitrarily added, and hence, the learned sparse regression coefficients can interpret the low-dimensional data. By using the joint sparse $\ell _{2,1}$ -norm regularizer, a sparse self-contained regression-type of pixel weighted PCA can be produced. Experiments on six data sets demonstrate that the proposed method is both feasible and effective. [ABSTRACT FROM AUTHOR]

Aiming at improving the performance of visual classification in a cost-effective manner, this paper proposes an incremental semi-supervised learning paradigm called deep co-space (DCS). Unlike many conventional semi-supervised learning methods usually performed within a fixed feature space, our DCS gradually propagates information from labeled samples to unlabeled ones along with deep feature learning. We regard deep feature learning as a series of steps pursuing feature transformation, i.e., projecting the samples from a previous space into a new one, which tends to select the reliable unlabeled samples with respect to this setting. Specifically, for each unlabeled image instance, we measure its reliability by calculating the category variations of feature transformation from two different neighborhood variation perspectives and merged them into a unified sample mining criterion deriving from Hellinger distance. Then, those samples keeping stable correlation to their neighboring samples (i.e., having small category variation in distribution) across the successive feature space transformation are automatically received labels and incorporated into the model for incrementally training in terms of classification. Our extensive experiments on standard image classification benchmarks (e.g., Caltech-256 and SUN-397) demonstrate that the proposed framework is capable of effectively mining from large-scale unlabeled images, which boosts image classification performance and achieves promising results compared with other semi-supervised learning methods. [ABSTRACT FROM AUTHOR]

The human visual system is not very sensitive to the absolute luminance of an image, but rather responds to local luminance changes, i.e., the gradient of an image. In this paper, we propose a constrained optimization approach for image gradient enhancement. The gradient strength of the enhanced image can be controlled directly using a target gradient strength parameter in the cost function. To suppress artifacts and ensure that contrast improves, a novel constraint is included in the optimization. Due to the number of variables in optimization-based image enhancement techniques being equal to the number of gray scales, we quantize the image using a $k$ -means clustering-based histogram mergence (KCHM) method before enhancement. KCHM can significantly reduce the number of image gray scales while effectively preserving the subjective quality. This is useful considering the reduction of variables is good for solving optimization and reducing computation cost. Experimental results demonstrate that the proposed method can significantly improve the subjective image quality by enhancing both the contrast and the image gradient. [ABSTRACT FROM AUTHOR]

Background subtraction is a key step in a wide spectrum of video applications, such as object tracking and human behavior analysis. Compressive sensing-based methods, which make little specific assumptions about the background, have recently attracted wide attention in background subtraction. Within the framework of compressive sensing, background subtraction is solved as a decomposition and optimization problem, where the foreground is typically modeled as pixel-wised sparse outliers. However, in real videos, foreground pixels are often not randomly distributed, but instead, group clustered. Moreover, due to costly computational expenses, most compressive sensing-based methods are unable to process frames online. In this paper, we take into account the group properties of foreground signals in both spatial and temporal domains, and propose a greedy pursuit-based method called spatio-temporal group sparsity recovery, which prunes data residues in an iterative process, according to both sparsity and group clustering priors, rather than merely sparsity. Furthermore, a random strategy for background dictionary learning is used to handle complex background variations, while foreground-free training is not required. Finally, we propose a two-pass framework to achieve online processing. The proposed method is validated on multiple challenging video sequences. Experiments demonstrate that our approach effectively works on a wide range of complex scenarios and achieves a state-of-the-art performance with far fewer computations. [ABSTRACT FROM AUTHOR]

Estimating the disparity and normal direction of one pixel simultaneously, instead of only disparity, also known as 3D label methods, can achieve much higher subpixel accuracy in the stereo matching problem. However, it is extremely difficult to assign an appropriate 3D label to each pixel from the continuous label space \mathbb R^3 while maintaining global consistency because of the infinite parameter space. In this paper, we propose a novel algorithm called PatchMatch-based superpixel cut to assign 3D labels of an image more accurately. In order to achieve robust and precise stereo matching between local windows, we develop a bilayer matching cost, where a bottom–up scheme is exploited to design the two layers. The bottom layer is employed to measure the similarity between small square patches locally by exploiting a pretrained convolutional neural network, and then, the top layer is developed to assemble the local matching costs in large irregular windows induced by the tangent planes of object surfaces. To optimize the spatial smoothness of local assignments, we propose a novel strategy to update 3D labels. In the procedure of optimization, both segmentation information and random refinement of PatchMatch are exploited to update candidate 3D label set for each pixel with high probability of achieving lower loss. Since pairwise energy of general candidate label sets violates the submodular property of graph cut, we propose a novel multilayer superpixel structure to group candidate label sets into candidate assignments, which thereby can be efficiently fused by $\alpha $ -expansion graph cut. Extensive experiments demonstrate that our method can achieve higher subpixel accuracy in different data sets, and currently ranks first on the new challenging Middlebury 3.0 benchmark among all the existing methods. [ABSTRACT FROM PUBLISHER]

Multiview video plus depth format has been adopted as the emerging 3D video representation recently. It includes a limited number of textures and depth maps to synthesize additional virtual views. Since the quality of depth maps influences the view synthesis process, their sharp edges should be well preserved to avoid mixing foreground with background. To address this issue, 3D-High Efficiency Video Coding (HEVC) introduces new coding tools, a partition-based intra mode [depth modeling mode (DMM)], a residual description technique [segmentwise depth coding (SDC)], and a more complex rate-distortion (RD) evaluation with view synthesis optimization (VSO), to provide more accurate predictions and achieve higher compression rate. However, these new techniques introduce a lot of possible candidates, and each of them requires complicated RD calculation in the process of intra-mode decision. They lead to unacceptable computational burden in a 3D-HEVC encoder. Therefore, in this paper, we raise two efficient techniques for depth intra-mode decision. First, by investigating the statistical characteristics of variance distributions in the two partitions of DMM, a simple but efficient criterion based on the squared Euclidean distance of variances (SEDV) is suggested to evaluate RD costs of the DMM candidates instead of the time-consuming VSO process. Second, a probability-based early depth intra-mode decision is proposed to select only the most promising mode and make the early determination of using SDC based on the low-complexity RD cost in rough mode decision. Experimental results show that the proposed algorithm with these two new techniques provides 33%–48% time reduction with little drop in the coding performance compared with the state-of-the-art algorithms. [ABSTRACT FROM PUBLISHER]

Positive label is often used as the supervisory information in the learning scenario, which refers to the category that a sample is assigned to. However, another side information lying in the labels, which describes the categories that a sample is exclusive of, have been largely ignored. In this paper, we propose a nonnegative matrix factorization (NMF) based classification method leveraging both positive and negative label information, which is termed as positive and negative label-driven NMF (PNLD-NMF). The proposed scheme concurrently accomplishes data representation and classification in a joint manner. Owing to the complementary characteristics between positive and negative labels, we further design a new regularization framework to take advantage of these two label types. Extensive experiments on six image classification benchmark datasets show that the proposed scheme is able to consistently deliver better classification accuracy. [ABSTRACT FROM AUTHOR]

Because of the importance of digital images and their extensive application to digital watermarking, block chain, access control, identity authentication, distributive storage in the cloud and so on, image secret sharing (ISS) is attracting ever-increasing attention. Share authentication is an important issue in its practical application. However, most ISS schemes with share authentication ability require a dealer to participate in the authentication (namely, dealer participatory authentication). In this paper, we design an ISS for a $(k,n)$ -threshold with separate share authentication abilities of both dealer participatory authentication and dealer nonparticipatory authentication. The advantages of polynomial-based ISS and visual secret sharing (VSS) are skillfully fused to achieve these two authentication abilities without sending a share by using a screening operation. In addition, the designed scheme has the characteristics of low decryption (authentication) complexity, lossless decryption and no pixel expansion. Experiments and theoretical analyses are performed to show the effectiveness of the designed scheme. [ABSTRACT FROM AUTHOR]

The drastic visual improvements introduced by High Dynamic Range (HDR) technologies open new markets for a wide range of industries. Among them, a significant opportunity is offered to owners of legacy Standard Dynamic Range (SDR) content that can be converted to the new standard to take advantage of the enhanced capabilities of the HDR displays. Similarly, since SDR broadcasting infrastructure will continue to be around for the time being, such conversion process is becoming an obvious necessity. To this end, different approaches have tried to efficiently convert SDR images and videos to HDR format, a procedure well known as inverse Tone Mapping. In this paper, we propose a novel high visual quality video inverse Tone Mapping Operator (iTMO) that addresses the inadequacies of the state-of-the-art methods, resulting in high visual quality HDR videos that match the capabilities of the HDR technology. Our approach is based on human visual perception and employs a segmentation method according to the Human Visual System (HVS) sensitivity to brightness changes in different regions of the frame and constructs the mapping curve using the brightness distribution information of these regions. Our iTMO uses a hybrid approach to achieve an optimal balance between the overall contrast and brightness of the output HDR frame by maximizing a weighted sum of contrast and brightness difference between input SDR and generated HDR frame. The proposed iTMO works equally well for all levels of brightness, eliminating any visual artifacts by dynamically maintaining changes at non-perceivable levels. Subjective and objective evaluations validated the superior visual performance of our proposed iTMO over state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Many representation methods were built for gray image textures. However, they are not effective for color textures in general. To alleviate this problem, in this paper we propose a novel Compact Interchannel Sampling Difference Descriptor (CISDD) for color texture classification. In particular, considering sampling-based method can capture more directional information, we first use a heavy-tailed distribution, t-distribution to generate sample points in the image patch to calculate the micro-block difference. Then we model the interchannel relationship of color texture image by using dense micro-block differences. Furthermore, we utilize principal component analysis (PCA) to reduce the dimensions of the features encoded by the Fisher vector, and construct a Compact Interchannel Sampling Difference Descriptor (CISDD) for representing color texture image. Finally, experimental results on five published standard texture datasets (KTH-TIPS, VisTex, CUReT, USPTex and Colored Brodatz) reveal that CISDD is effective and outperforms thirteen representative color texture classification methods. [ABSTRACT FROM AUTHOR]

In this paper, a new network-transmission-based (NTB) algorithm is proposed for human activity recognition in videos. The proposed NTB algorithm models the entire scene as an error-free network. In this network, each node corresponds to a patch of the scene and each edge represents the activity correlation between the corresponding patches. Based on this network, we further model people in the scene as packages, while human activities can be modeled as the process of package transmission in the network. By analyzing these specific package transmission processes, various activities can be effectively detected. The implementation of our NTB algorithm into abnormal activity detection and group activity recognition are described in detail in this paper. Experimental results demonstrate the effectiveness of our proposed algorithm. [ABSTRACT FROM PUBLISHER]

In this paper, we propose a novel method for 4D light-field (LF) depth estimation exploiting the special linear structure of an epipolar plane image (EPI) and locally linear embedding (LLE). Without high computational complexity, depth maps are locally estimated by locating the optimal slope of each line segmentation on the EPIs, which are projected by the corresponding scene points. For each pixel to be processed, we build and then minimize the matching cost that aggregates the intensity pixel value, gradient pixel value, spatial consistency, as well as reliability measure to select the optimal slope from a predefined set of directions. Next, a subangle estimation method is proposed to further refine the obtained optimal slope of each pixel. Furthermore, based on a local reliability measure, all the pixels are classified into reliable and unreliable pixels. For the unreliable pixels, LLE is employed to propagate the missing pixels by the reliable pixels based on the assumption of manifold preserving property maintained by natural images. We demonstrate the effectiveness of our approach on a number of synthetic LF examples and real-world LF data sets, and show that our experimental results can achieve higher performance than the typical and recent state-of-the-art LF stereo matching methods. [ABSTRACT FROM PUBLISHER]

This paper addresses automatic video summarization. We propose a novel approach that relies on constraint satisfaction programming (CSP). An expert defines the general rules for summary generation. These rules are written as constraints. The (final) user can define additional constraints or enter high-level parameters of predefined constraints. This has many advantages. It clearly separates summary generation rules from the summary generation algorithm (the CSP solver here). The summary can hence be modified without reviewing the whole generation process. It also allows users to adapt the summary to the target application and to their preferences. The proposed approach is mainly dedicated to edited professional video (like TV programs). It has been extensively evaluated not only using objective measures but also through a large-scale user evaluation. This evaluation involved more than 60 people. Experiments have been performed within the challenging application of tennis match automatic summarization, using about 28.5 h of videos. [ABSTRACT FROM PUBLISHER]

Summarization is desirable for efficient comprehension of an increasingly vast amount of data. A summary of multiple documents is a concise description of the main topic. Generally speaking, a topic delivers various aspects. For example, the natural disaster topic is likely to imply the aspects of casualties and rescue. Therefore, a good summary is expected to cover all the informative aspects of a topic in order to enhance both diversity and coverage of the topic. However, for the real-world data, the profile of aspects in a given topic (e.g., the number of the aspects as well as their appropriate describing sentences or images) is hardly specified in advance. To address this problem, this paper proposes an approach to learn the hidden aspects in the topics via a nonparametric Bayesian model for multimedia summarization, namely, aspect learning for multimedia summarization via nonparametric Bayesian (ALSNB). More specifically, we introduce the priors of beta-Bernoulli process and Dirichlet process into the traditional dictionary learning. As a result, the proposed approach is able to adaptively identify the particular aspects of an individual topic. The experimental results on several datasets for text summarization and image summarization show the superiority of the proposed ALSNB over other methods. [ABSTRACT FROM AUTHOR]

The Range Extensions (RExt) of the High Efficiency Video Coding (HEVC) standard have recently been approved by both ITU-T and ISO/IEC. This set of extensions targets video coding applications in areas including content acquisition, postproduction, contribution, distribution, archiving, medical imaging, still imaging, and screen content. In addition to the functionality of HEVC Version 1, RExt provide support for monochrome, 4:2:2, and 4:4:4 chroma sampling formats as well as increased sample bit depths beyond 10 bits per sample. This extended functionality includes new coding tools with a view to provide additional coding efficiency, greater flexibility, and throughput at high bit depths/rates. Improved lossless, near-lossless, and very high bit-rate coding is also a part of the RExt scope. This paper presents the technical aspects of HEVC RExt, including a discussion of RExt profiles, tools, applications, and provides experimental results for a performance comparison with previous relevant coding technology. When compared with the High 4:4:4 Predictive Profile of H.264/Advanced Video Coding (AVC), the corresponding HEVC 4:4:4 RExt profile provides up to $\sim 25$ %, $\sim 32$ %, and $\sim 36$ % average bit-rate reduction at the same PSNR quality level for intra, random access, and low delay configurations, respectively. [ABSTRACT FROM PUBLISHER]

Object proposal algorithms have been demonstrated to be very successful in accelerating object detection process. High object localization quality and detection recall can be obtained using thousands of proposals. However, the performance with a small number of proposals is still unsatisfactory. This paper demonstrates that the performance of a few proposals can be significantly improved with the minimal human interaction—a single touch point. To this end, we first generate hierarchical superpixels using an efficient tree-organized structure as our initial object proposals, and then select only a few proposals from them by learning an effective Convolutional neural network for objectness ranking. We explore and design an architecture to integrate human interaction with the global information of the whole image for objectness scoring, which is able to significantly improve the performance with a minimum number of object proposals. Extensive experiments show the proposed method outperforms all the state-of-the-art methods for locating the meaningful object with the touch point constraint. Furthermore, the proposed method is extended for video. By combining with the novel interactive motion segmentation cue for generating hierarchical superpixels, the performance on a single proposal is satisfactory and can be used in the interactive vision systems, such as selecting the input of a real-time tracking system. [ABSTRACT FROM AUTHOR]

Local histogram specification (LHS) is a useful technique for image processing. However, LHS faces a critical computational challenge when it is applied to high-resolution high-precision images. The calculation of the values in the cumulative distribution function (CDF) and the mapped value for the central pixel in each sliding window is time consuming with the computational complexity $O(s+L)$ of the state-of-the-art techniques, where s$ is the side length of the square window and L$ is the number of gray levels. In this paper, we propose a fast algorithm for LHS, called fast local histogram specification (FLHS). FLHS reduces the complexity of calculating the CDF value for the central pixel in each sliding window to , and the time complexity for the mapping procedure in each window to O(\log L)$ . This results in the overall time complexity of LHS reduced from O(s+L)$ to in each sliding window. Theoretical analysis shows that the newly developed algorithm is efficient. Experimental results on the 8-bit and high-resolution high-precision (16-bit) images demonstrate the efficiency of our proposed algorithm. [ABSTRACT FROM PUBLISHER]

High Efficiency Video Coding (HEVC) adopts the quadtree structured coding unit (CU), which allows recursive splitting into four equally sized blocks. At each depth level, it enables SKIP mode, merge mode, inter 2N \(\times 2\) N, inter 2N \(\times \) N, inter N \(\times 2\) N, inter 2N \(\times \) nU, inter 2N \(\times \) nD, inter nL \(\times 2\) N, inter nR \(\times 2\) N, inter N \(\times \) N (only available for the smallest CU), intra 2N \(\times 2\) N, and intra N \(\times \) N (only available for the smallest CU) in inter-frames. Similar to H.264/AVC, the mode decision process in HEVC is performed using all the possible depth levels (or CU sizes) and prediction modes to find the one with the least rate distortion (RD) cost using Lagrange multiplier. This achieves the highest coding efficiency, but leads to a very high computational complexity. Since the optimal prediction mode is highly content dependent, it is not efficient to use all the modes. In this paper, we propose a fast inter-mode decision algorithm for HEVC by jointly using the inter-level correlation of quadtree structure and the spatiotemporal correlation. There exist strong correlations of the prediction mode, the motion vector and RD cost between different depth levels and between spatially temporally adjacent CUs. We statistically analyze the prediction mode distribution at each depth level and the coding information correlation among the adjacent CUs. Based on the analysis results, three adaptive inter-mode decision strategies are proposed including early SKIP mode decision, prediction size correlation-based mode decision and RD cost correlation-based mode decision. Experimental results show that the proposed overall algorithm can save 49%–52% computational complexity on average with negligible loss of coding efficiency, exhibiting applicability to various types of video sequences. [ABSTRACT FROM AUTHOR]

As digital video databases grow, so grows the problem of effectively navigating through them. In this paper we propose a novel content-based video retrieval approach to searching such video databases, specifically those involving human actions, incorporating spatio-temporal localization. We outline a novel, highly efficient localization model that first performs temporal localization based on histograms of evenly spaced time-slices, then spatial localization based on histograms of a 2-D spatial grid. We further argue that our retrieval model, based on the aforementioned localization, followed by relevance ranking, results in a highly discriminative system, while remaining an order of magnitude faster than the current state-of-the-art method. We also show how relevance feedback can be applied to our localization and ranking algorithms. As a result, the presented system is more directly applicable to real-world problems than any prior content-based video retrieval system. [ABSTRACT FROM PUBLISHER]

Spectral regression discriminant analysis (SRDA) has recently been proposed as an efficient solution to large-scale subspace learning problems. There is a tunable regularization parameter in SRDA, which is critical to algorithm performance. However, how to automatically set this parameter has not been well solved until now. So this regularization parameter was only set to be a constant in SRDA, which is obviously suboptimal. This paper proposes to automatically estimate the optimal regularization parameter of SRDA based on the perturbation linear discriminant analysis (PLDA). In addition, two parameter estimation methods for the kernel version of SRDA are also developed. One is derived from the method of optimal regularization parameter estimation for SRDA. The other is to utilize the kernel version of PLDA. Experiments on a number of publicly available databases demonstrate the effectiveness of the proposed methods for face recognition, spoken letter recognition, handwritten digit recognition, and text categorization. [ABSTRACT FROM PUBLISHER]

Person re-identification aims to identify the same pedestrians across different camera views at different locations. This important yet difficult intelligent video analysis problem remains a vigorous area of research due to demands for performance improvements. Person re-identification involves two main steps: feature representation and metric learning. Handcrafted features, such as color and texture histograms, are frequently used for person re-identification, but most handcrafted features are limited by not being directly applicable to practical problems. Deep learning methods have obtained the state-of-the-art performance in a wide variety of applications, including image annotation, face recognition, and speech recognition. However, deep learning features are heavily dependent on large-scale labeling of samples. In this paper, by utilizing the Cross-view Quadratic Discriminant Analysis (XQDA) metric learning, we propose a novel scheme called deep multi-view feature learning (DMVFL), which exploits the collaboration between handcrafted and deep learning features in a simple but effective way. Furthermore, we prove that the XQDA is a robust algorithm. Extensive experiments on two challenging person re-identification data sets (VIPeR and GRID) demonstrate that DMVFL improves on current state-of-the-art methods. [ABSTRACT FROM AUTHOR]