The rapid growth of edge computing is accelerating data subscriptions between cloud platforms and mobile subscribers, but sensitive information in these data faces security and privacy concerns. Fortunately, matchmaking attribute-based encryption (MABE) as a new type of encrypted data filtering mechanism has been introduced in cloud edge, which not only enforces fine-grained access control over the encrypted data, but also allows subscribers to dynamically filter data of interest from authentic publishers through edge nodes. However, filtering entire ciphertext collection in linear time is not feasible for large-scale data storage, and edge nodes may return mismatched or incomplete results due to corruption or compromise. To this end, we propose VDFilter, an efficient and verifiable encrypted data filtering framework over large-scale storage in cloud edge. VDFilter first introduces a verifiable MABE as the underlying primitive, which achieves efficient data filtering in edge nodes with an inverted collection from the ciphertext collection, and verifies the soundness and completeness of filtered results with an accumulation tree. To accommodate the ciphertext collection from multiple publishers, VDFilter deploys the construction of the accumulation tree on the Intel SGX enclave within the cloud server, and utilizes authenticated data structures to guarantee secure and efficient filtered result verification. Finally, we provide formal security proofs for VDFilter and demonstrate its efficiency with extensive experiments. Compared with existing schemes, VDFilter is much more efficient in data storing and filtering even with verification operations, and its computational and communication overhead on the subscriber is also low.

Image deblurring aims to restore the latent sharp images from the corresponding blurred ones. In this paper, we present an unsupervised method for domain-specific, single-image deblurring based on disentangled representations. The disentanglement is achieved by splitting the content and blur features in a blurred image using content encoders and blur encoders. We enforce a KL divergence loss to regularize the distribution range of extracted blur attributes such that little content information is contained. Meanwhile, to handle the unpaired training data, a blurring branch and the cycle-consistency loss are added to guarantee that the content structures of the deblurred results match the original images. We also add an adversarial loss on deblurred results to generate visually realistic images and a perceptual loss to further mitigate the artifacts. We perform extensive experiments on the tasks of face and text deblurring using both synthetic datasets and real images, and achieve improved results compared to recent state-of-the-art deblurring methods.

Unconstrained video-based face recognition is a challenging problem due to significant within-video variations caused by pose, occlusion and blur. To tackle this problem, an effective idea is to propagate the identity from high-quality faces to low-quality ones through contextual connections, which are constructed based on context such as body appearance. However, previous methods have often propagated erroneous information due to lack of uncertainty modeling of the noisy contextual connections. In this paper, we propose the Uncertainty-Gated Graph (UGG), which conducts graph-based identity propagation between tracklets, which are represented by nodes in a graph. UGG explicitly models the uncertainty of the contextual connections by adaptively updating the weights of the edge gates according to the identity distributions of the nodes during inference. UGG is a generic graphical model that can be applied at only inference time or with end-to-end training. We demonstrate the effectiveness of UGG with state-of-the-art results in the recently released challenging Cast Search in Movies and IARPA Janus Surveillance Video Benchmark dataset.

In this paper, we propose a pose-robust metric learning framework for unconstrained face verification by jointly optimizing face and pose verification tasks. We learn a joint model for these two tasks and explicitly discourage the information sharing between pose and identity verification metrics so as to mitigate the information contained in the pose verification task leading to making the identity metrics for face verification more pose-robust. Specifically, we use the joint Bayesian metric learning framework to learn the metrics for both tasks and enforce an orthogonal regularization constraint on the learned projection matrices for the two tasks. The pose labels used for training the joint model are automatically estimated and do not require extra annotations. An efficient stochastic gradient descent (SGD) algorithm is used to solve the optimization problem. We conduct extensive experiments on three challenging unconstrained face datasets and show promising results compared to state-of-the-art methods.

In this work, we propose a metric adaptation method for set-based face verification and evaluate it on the newly released IARPA Janus Benchmark A (IJB-A) dataset and its extended version, the Janus Challenging Set 2 (CS2). A template-specific metric is trained to adaptively learn the discriminative information in test templates and the negative training set, which contains subjects that are mutually exclusive to subjects in test templates. The proposed regularized joint Bayesian metric learning framework not only alleviates the over-fitting problem but also provides a way to efficiently reduce the model size. We also analyze the selection of the compact and representative negative set to speed up the training time and to reduce storage space. Experiments on the IJB-A and CS2 datasets yield promising results.

Domain adaptation (DA) methods attempt to solve the domain mismatch problem between source and target data. In this paper, we propose an incremental dictionary learning method where some target data called supportive samples are selected to assist adaptation. Supportive samples are close to the source domain and have two properties: first, their predicted class labels are reliable and can be used for building more discriminative classification models; second, they act as a bridge to connect the two domains and reduce the domain mismatch. Theoretical analysis shows that both properties are important for adaptation, enabling the idea of adding supportive samples to the source domain. A stopping criterion is designed to guarantee that the domain mismatch decreases monotonically during adaptation. Experimental results on several widely used visual datasets show that the proposed approach performs better than many state-of-the-art methods.

Task-driven dictionary learning (TDDL) has shown great success in many classification applications. However, the performance of TDDL is limited by the challenging properties of hyperspectral images (HSI). Fortunately, previous research has made significant progress in HSI classification by enforcing various structured sparsity constraints (priors) on the TDDL-based model. In this paper, we extend some previous work by relaxing the structured sparsity priors and make the model become more flexible and powerful. Specifically, we add class label Laplacian sparsity constraints in two different places, either on the sparse code or on the classifier outputs. Experimental results on widely used datasets shown improvement in performance compared to current state-of-the-art approaches.