Sorry, you need to enable JavaScript to visit this website.

High Dynamic Range (HDR) Wide Color Gamut (WCG) Ultra High Definition (4K/UHD) content has become increasingly popular recently. Due to the increased data rate, novel video compression methods have been developed to maintain the quality of the videos being delivered to consumers under bandwidth constraints. This has led to new challenges for the development of objective Video Quality Assessment (VQA) models, which are traditionally designed without sufficient calibration and validation based on subjective quality assessment of UHD-HDR-WCG videos.

Reliably predicting where people look in images and videos remains challenging and requires substantial eye-tracking data to be collected and analysed for various applications. In this paper, we present an eye-tracking study where twenty-eight participants viewed forty still scenes of video advertising. First, we analyse human attentional behaviour based on gaze data. Then, we evaluate to what extent a machine – saliency model – can predict human behaviour. Experimental results show that there is a significant gap between human and machine in visual saliency.

Our previous study has shown that image distortions cause saliency distraction, and that visual saliency of a distorted image differs from that of its distortion-free reference. Being able to measure such distortion-induced saliency variation (DSV) significantly benefits algorithms for automated image quality assessment. Methods of quantifying DSV, however, remain unexplored due to the lack of a benchmark. In this paper, we build a benchmark for the measurement of DSV through a subjective study.

Existing blind evaluators for screen content images (SCIs) are mainly learning-based and require a number of training images with co-registered human opinion scores. However, the size of existing databases is small, and it is labor-, timeconsuming and expensive to largely generate human opinion scores. In this study, we propose a novel blind quality evaluator without training.

Facial attractiveness prediction has drawn considerable attention from image processing community.
Despite the substantial progress achieved by existing works, various challenges remain.
One is the lack of accurate representation for facial composition, which is essential for attractiveness evaluation. In this paper, we propose to use pixel-wise labelling masks as the meta information of facial composition, and input them into a network for learning high-level semantic representations.

Action quality assessment is crucial in areas of sports, surgery and assembly line where action skills can be evaluated. In this paper, we propose the Segment-based P3D-fused network S3D built-upon ED-TCN and push the performance on the UNLV-Dive dataset by a significant margin. We verify that segment-aware training performs better than full-video training which turns out to focus on the water spray. We show that temporal segmentation can be embedded with few efforts.

Image aesthetic assessment is important for finding well taken and appealing photographs but is challenging due to the ambiguity and subjectivity of aesthetic criteria. We develop the pairwise aesthetic comparison network (PAC-Net), which consists of two parts: aesthetic feature extraction and pairwise feature comparison. To alleviate the ambiguity and subjectivity, we train PAC-Net to learn the relative aesthetic ranks of two images by employing a novel loss function, called aesthetic-adaptive cross entropy loss.

In this paper, we propose a novel virtual reality image quality assessment (VR IQA) with adversarial learning for omnidirectional images. To take into account the characteristics of the omnidirectional image, we devise deep networks including novel quality score predictor and human perception guider. The proposed quality score predictor automatically predicts the quality score of distorted image using the latent spatial and position feature.

In this paper, we propose variational fusion of time-of-flight (TOF) and stereo data using edge selective joint filtering (ESJF). We utilize ESJF to up-sample low-resolution (LR) depth captured by TOF camera and produce high-resolution (HR)depth maps with accurate edge information. First, we measure confidence of two sensor with different reliability to fuse them. Then, we up-sample TOF depth map using ESJF to generate discontinuity maps and protect edges in depth. Finally, we perform variational fusion of TOF and stereo depth data based on total variation (TV) guided by discontinuity maps.