Visual semantic information comprises two important parts: the meaning of each visual semantic unit and the coherent visual semantic relation conveyed by these visual semantic units. Essentially, the former one is a visual perception task while the latter one corresponds to visual context reasoning. Remarkable advances in visual perception have been achieved due to the success of deep learning. In contrast, visual semantic information pursuit, a visual scene semantic interpretation task combining visual perception and visual context reasoning, is still in its early stage. It is the core task of many different computer vision applications, such as object detection, visual semantic segmentation, visual relationship detection or scene graph generation. Since it helps to enhance the accuracy and the consistency of the resulting interpretation, visual context reasoning is often incorporated with visual perception in current deep end-to-end visual semantic information pursuit methods. However, a comprehensive review for this exciting area is still lacking. In this survey, we present a unified theoretical paradigm for all these methods, followed by an overview of the major developments and the future trends in each potential direction. The common benchmark datasets, the evaluation metrics and the comparisons of the corresponding methods are also introduced.
The kernel null-space technique and its regression-based formulation (called one-class kernel spectral regression, a.k.a. OC-KSR) is known to be an effective and computationally attractive one-class classification framework. Despite its outstanding performance, the applicability of kernel null-space method is limited due to its susceptibility to possible training data corruptions and inability to rank training observations according to their conformity with the model. This work addresses these shortcomings by studying the effect of regularising the solution of the null-space kernel Fisher methodology in the context of its regression-based formulation (OC-KSR). In this respect, first, the effect of a Tikhonov regularisation in the Hilbert space is analysed where the one-class learning problem in presence of contaminations in the training set is posed as a sensitivity analysis problem. Next, driven by the success of the sparse representation methodology, the effect of a sparsity regularisation on the solution is studied. For both alternative regularisation schemes, iterative algorithms are proposed which recursively update label confidences and rank training observations based on their fit with the model. Through extensive experiments conducted on different data sets, the proposed methodology is found to enhance robustness against contamination in the training set as compared with the baseline kernel null-space technique as well as other existing approaches in a one-class classification paradigm while providing the functionality to rank training samples effectively.
With the advantage of low storage cost and high retrieval efficiency, hashing techniques have recently been an emerging topic in cross-modal similarity search. As multiple modal data reflect similar semantic content, many researches aim at learning unified binary codes. However, discriminative hashing features learned by these methods are not adequate. This results in lower accuracy and robustness. We propose a novel hashing learning framework which jointly performs classifier learning, subspace learning and matrix factorization to preserve class-specific semantic content, termed Discriminative Supervised Hashing (DSH), to learn the discrimative unified binary codes for multi-modal data. Besides, reducing the loss of information and preserving the non-linear structure of data, DSH non-linearly projects different modalities into the common space in which the similarity among heterogeneous data points can be measured. Extensive experiments conducted on the three publicly available datasets demonstrate that the framework proposed in this paper outperforms several state-of -the-art methods.
3D face reconstruction is an important task in the field of computer vision. Although 3D face reconstruction has being developing rapidly in recent years, it is still a challenge for face reconstruction under large pose. That is because much of the information about a face in a large pose will be unknowable. In order to address this issue, this paper proposes a novel 3D face reconstruction algorithm (PIFR) based on 3D Morphable Model (3DMM). After input a single face image, it generates a frontal image by normalizing the image. Then we set weighted sum of the 3D parameters of the two images. Our method solves the problem of face reconstruction of a single image of a traditional method in a large pose, works on arbitrary Pose and Expressions, greatly improves the accuracy of reconstruction. Experiments on the challenging AFW, LFPW and AFLW database show that our algorithm significantly improves the accuracy of 3D face reconstruction even under extreme poses .
We present a new loss function, namely Wing loss, for robust facial landmark localisation with Convolutional Neural Networks (CNNs). We first compare and analyse different loss functions including L2, L1 and smooth L1. The analysis of these loss functions suggests that, for the training of a CNN-based localisation model, more attention should be paid to small and medium range errors. To this end, we design a piece-wise loss function. The new loss amplifies the impact of errors from the interval (-w, w) by switching from L1 loss to a modified logarithm function. To address the problem of under-representation of samples with large out-of-plane head rotations in the training set, we propose a simple but effective boosting strategy, referred to as pose-based data balancing. In particular, we deal with the data imbalance problem by duplicating the minority training samples and perturbing them by injecting random image rotation, bounding box translation and other data augmentation approaches. Last, the proposed approach is extended to create a two-stage framework for robust facial landmark localisation. The experimental results obtained on AFLW and 300W demonstrate the merits of the Wing loss function, and prove the superiority of the proposed method over the state-of-the-art approaches.
Face detection and recognition benchmarks have shifted toward more difficult environments. The challenge presented in this paper addresses the next step in the direction of automatic detection and identification of people from outdoor surveillance cameras. While face detection has shown remarkable success in images collected from the web, surveillance cameras include more diverse occlusions, poses, weather conditions and image blur. Although face verification or closed-set face identification have surpassed human capabilities on some datasets, open-set identification is much more complex as it needs to reject both unknown identities and false accepts from the face detector. We show that unconstrained face detection can approach high detection rates albeit with moderate false accept rates. By contrast, open-set face recognition is currently weak and requires much more attention.
The paper introduces a new efficient nonlinear one-class classifier formulated as the Rayleigh quotient criterion optimisation. The method, operating in a reproducing kernel Hilbert subspace, minimises the scatter of target distribution along an optimal projection direction while at the same time keeping projections of positive observations distant from the mean of the negative class. We provide a graph embedding view of the problem which can then be solved efficiently using the spectral regression approach. In this sense, unlike previous similar methods which often require costly eigen-computations of dense matrices, the proposed approach casts the problem under consideration into a regression framework which is computationally more efficient. In particular, it is shown that the dominant complexity of the proposed method is the complexity of computing the kernel matrix. Additional appealing characteristics of the proposed one-class classifier are: 1-the ability to be trained in an incremental fashion (allowing for application in streaming data scenarios while also reducing the computational complexity in a non-streaming operation mode); 2-being unsupervised, but providing the option for refining the solution using negative training examples, when available; Last but not least, 3-the use of the kernel trick which facilitates a nonlinear mapping of the data into a high-dimensional feature space to seek better solutions.
Human face is a 3D object with shape and surface texture. 3D Morphable Model (3DMM) is a powerful tool for reconstructing the 3D face from a single 2D face image. In the shape fitting process, 3DMM estimates the correspondence between 2D and 3D landmarks. Most traditional 3DMM fitting methods fail to reconstruct an accurate model because face shape fitting is a difficult non-linear optimization problem. In this paper we show that landmark weighting is instrumental to improve the accuracy of shape reconstruction and propose a novel 3D Morphable Model Fitting method. Different from previous works that treat all landmarks equally, we take into consideration the estimated errors for each pair of 2D and 3D corresponding landmarks. The landmark points are weighted in the optimization cost function based on these errors. Obviously, these landmarks have different semantics because they locate on different facial components. In the context of the solution of fitting is approximated, there are deviations in landmarks matching. However, these landmarks with different semantics have different effects on reconstructing 3D faces. Thus, it is necessary to consider each landmark individually. To our knowledge, we are the first to analyze each feature point for 3D face reconstruction by 3DMM. The weight is adaptive with the estimation residuals of landmarks. Experimental results show that the proposed method significantly reduces the reconstruction error and improves the authenticity of the 3D model expression.
Hashing techniques have been applied broadly in large-scale retrieval tasks due to their low storage requirements and high speed of processing. Many hashing methods have shown promising performance but as they fail to exploit all structural information in learning the hashing function, they leave a scope for improvement. The paper proposes a novel discrete hashing learning framework which jointly performs classifier learning and subspace learning for cross-modal retrieval. Concretely, the framework proposed in the paper includes two stages, namely a kernelization process and a quantization process. The aim of kernelization is to learn a common subspace where heterogeneous data can be fused. The quantization process is designed to learn discriminative unified hashing codes. Extensive experiments on three publicly available datasets clearly indicate the superiority of our method compared with the state-of-the-art methods.
With efficient appearance learning models, Discriminative Correlation Filter (DCF) has been proven to be very successful in recent video object tracking benchmarks and competitions. However, the existing DCF paradigm suffers from two major problems, \ie spatial boundary effect and temporal filter degeneration. To mitigate these challenges, we propose a new DCF-based tracking method. The key innovations of the proposed method include adaptive spatial feature selection and temporal consistent constraints, with which the new tracker enables joint spatio-temporal filter learning in a lower dimensional discriminative manifold. More specifically, we apply structured sparsity constraints to multi-channel filers. Consequently, the process of learning spatial filters can be approximated by the lasso regularisation. To encourage temporal consistency, the filter model is restricted to lie around its historical value and updated locally to preserve the global structure in the manifold. Last, a unified optimisation framework is proposed to jointly select temporal consistency preserving spatial features and learn discriminative filters with the augmented Lagrangian method. Qualitative and quantitative evaluations have been conducted on a number of well-known benchmarking datasets such as OTB2013, OTB50, OTB100, Temple-Colour and UAV123. The experimental results demonstrate the superiority of the proposed method over the state-of-the-art approaches.