The increasing popularity of video (i.e., audio-visual) applications or services over both wired and wireless links has prompted recent growing interests in the investigations of quality of experience (QoE) in online video transmission. Conventional video quality metrics, such as peak-signal-to-noise-ratio and quality of service, only focus on the reception quality from the systematic perspective. As a result, they cannot represent the true visual experience of an individual user. Instead, the QoE introduces a user experience-driven strategy which puts special emphasis on the contextual and human factors in addition to the transmission system. This advantage has raised the popularity and widespread usage of QoE in video transmission. In this paper, we present an overview of selected issues pertaining to QoE and its recent applications in video transmission, with consideration of the compelling features of QoE (i.e., context and human factors). The selected issues include QoE modeling with influence factors in the end-to-end chain of video transmission, QoE assessment (including subjective test and objective QoE monitoring) and QoE management of video transmission over different types of networks. Through the literature review, we observe that the context and human factors in QoE-aware video transmission have attracted significant attentions since the past two to three years. A vast number of high quality works were published in this area, and will be highlighted in this survey. In addition to a thorough summary of recent progresses, we also present an outlook of future developments on QoE assessment and management in video transmission, especially focusing on the context and human factors that have not been addressed yet and the technical challenges that have not been completely solved so far. We believe that our overview and findings can provide a timely perspective on the related issues and the future research directions in QoE-oriented services over video communications.

Due to light scatter and absorption in waterbody, underwater imaging can be easily impaired with low contrast and visual distortion. The resulting images are often unable to meet the quality requirements of human perception and computer processing. Therefore, Underwater Image Enhancement (UIE) has been attracting extensive research efforts. Although deep learning has demonstrated its great success in many vision tasks, its huge amounts of parameters and computations are not conducive to UIE in resource-limited scenarios. In this paper, we address this issue by proposing a Lightweight Cascaded Network (LCNet) based on Laplacian image pyramids. At each pyramid level, we implement cascaded blocks upon a residual network. Specifically, high quality residuals can be progressively predicted with significantly reduced complexity in a coarse-to-fine fashion. Furthermore, these sub-networks are recursively nested to build our LCNet, thereby reducing the overall computational complexity with reused parameters. Extensive experiments demonstrate that the proposed method performs favorably against the state-of-the-arts in terms of visual quality, model parameters and complexity.

Due to complex and volatile lighting environment, underwater imaging can be readily impaired by light scattering, warping, and noises. To improve the visual quality, Underwater Image Enhancement (UIE) techniques have been widely studied. Recent efforts have also been contributed to evaluate and compare the UIE performances with subjective and objective methods. However, the subjective evaluation is time-consuming and uneconomic for all images, while existing objective methods have limited capabilities for the newly-developed UIE approaches based on deep learning. To fill this gap, we propose an Underwater Image Fidelity (UIF) metric for objective evaluation of enhanced underwater images. By exploiting the statistical features of these images in CIELab space, we present the naturalness, sharpness, and structure indexes. Among them, the naturalness and sharpness indexes represent the visual improvements of enhanced images; the structure index indicates the structural similarity between the underwater images before and after UIE. We combine all indexes with a saliency-based spatial pooling and thus obtain the final UIF metric. To evaluate the proposed metric, we also establish a first-of-its-kind large-scale UIE database with subjective scores, namely Underwater Image Enhancement Database (UIED). Experimental results confirm that the proposed UIF metric outperforms a variety of underwater and general-purpose image quality metrics. The database and source code are available at https://github.com/z21110008/UIF .

Classification remains challenging when confronted with the existence of multi-view data with limited labels. In this paper, we propose an embedding regularizer learning scheme for multi-view semi-supervised classification (ERL-MVSC). The proposed framework integrates diversity, sparsity and consensus to dexterously manipulate multi-view data with limited labels. To encourage diversity, ERL-MVSC recasts a linear regression model to derive view-specific embedding regularizers and automatically determines their weights. This is able to tactfully incorporate complementary information of different views. To ensure sparsity, ERL-MVSC imposes $\ell _{2,1}$ -norm on a fused embedding regularizer to exploit the sparse local structure of samples, thereby conveying valuable classification information and enhancing the robustness against noise/outliers. To enhance consensus, ERL-MVSC learns a shared predicted label matrix, which serves as the comment target of multi-view classification. With these techniques, we formulate ERL-MVSC as a joint optimization problem of an embedding regularizer and a predicted label matrix, which can be solved by a coordinate descent method. Extensive experimental results on real-world datasets demonstrate the effectiveness and superiority of the proposed algorithm.

Underwater imaging is usually degraded by low contrast or color cast due to light absorption and scattering. This fact limits the accuracy of object recognition in underwater and marine environments. In this article, to address this issue, we propose a CURE-Net that progressively improves degraded underwater images in a coarse-to-fine way. To be specific, our CURE-Net consists of three cascaded subnetworks. The first two subnetworks use attention and gate fusion to learn multiscale contextual information, whereas the third subnetwork preserves fine spatial details. A detail enhancement block and a supervised recovery block are deployed between subnetworks to further improve the recovery of colors and details. Our proposed CURE-Net is extensively evaluated on popular data sets and achieves state-of-the-art performance. Compared with its peers, our method is also more friendly to object recognition—underwater objects are more easily recognized after being processed by our method.

Images collected in low-light environments usually suffer from multiple, non-uniform distributed distortions, including local dark, dim light, backlit and so on. In this paper, we propose a Stage-Transformer-Guided Network (STGNet) that effectively handles region-specific distributions and enhance diverse low-light images. Specifically, our STGNet adopts a multi-stage way to progressively learn hierarchical features that benefit the robustness of our model. At each stage, we design an efficient transformer with horizontal and vertical attentions that jointly capture degradation distributions with different magnitudes and orientations. We also introduce learnable degradation queries to adaptively select task-specific features of degradations for enhancement. In addition, we design a histogram loss for enhancement and combine it with other loss functions, in order to exploit both global contrast and local details during network training. Benefiting from the above contributions, our STGNet achieves the state-of-the-art performances on both synthetic and real-world datasets.