Saliency prediction models are constrained by the limited diversity and quantity of labeled data. Standard data augmentation techniques such as rotating and cropping alter scene composition, affecting saliency. We propose a novel data augmentation ...

In recent years, excellent RGB-D salient object detection performance has been achieved. However, existing detection methods generally require a large number of model parameters in pursuit of high accuracy. To alleviate this problem, we propose a ...

Volumetric video, a technique used in augmented reality (AR) and virtual reality (VR) applications, presents unique challenges in rendering and compression. To enable efficient compression, video-based point cloud compression (V-PCC) techniques have been ...

We present a study of an artificial neural architecture that predict human ocular scanpaths while they are free-viewing different images types. This analysis is made by comparing different metrics that encompass scanpath patterns, these metrics ...

Next-generation multimedia networks are expected to provide systems and applications with top Quality of Experience (QoE) to users. To this end, robust quality evaluation metrics are critical. Unfortunately, most current research focuses only on ...

• A new architecture based on a suite of deep-learning models is introduced. The proposed architecture exploits relevant visual information, such as spatial color attributes and visual attention mechanisms, to accurately rank contrast-...

Video captioning algorithms aim at expressing the information and activities contained in a video clip in the form of lingual sentences. Most existing video captioning approaches have used only one sentence to describe the semantic content of a ...

Deep learning approaches have allowed for a great leap in the performances of visual saliency models. However, the lack of annotated data remains the main challenge for visual saliency prediction. In this paper, we leverage image inpainting methods to ...

Scene graph aims to faithfully reveal humans’ perception of image content. When humans look at a scene, they usually focus on their interested parts in a special priority. This innate habit indicates a hierarchical preference about human ...

• An efficient method to compute the Dahu pseudo-distance on multivariate images.

Interactive image segmentation is an important application in computer vision for selecting objects of interest in images. Several interactive segmentation methods are based on distance transform algorithms. However, the most known ...

Loop closure detection (LCD) is essential in the field of visual Simultaneous Localization and Mapping (vSLAM). In the LCD system, geometrical verification based on image matching plays a crucial role in avoiding erroneous detections. ...

• Create a novel LCD-oriented saliency prediction dataset (Saliency-LCD).
• Design ...

• Three limitations between the superpixel-based and VS-based FR-IQA models are found.
• We found that the two approaches have a complementary principle.
• Base on this principle, a FR-IQA model for synergizing superpixel and VS is ...

Superpixel and saliency-based evaluation methods play important roles in full reference image quality assessment (FR IQA). However, we find that these methods have one complementary principle and three limitations: (1) the weighted maps of ...

The intelligent video surveillance system (IVSS) can automatically analyze the content of the surveillance image (SI) and reduce the burden of the manual labour. However, the SIs may suffer quality degradations in the procedure of acquisition, ...

Objective quality assessment of retargeted images aims to find the best retargeting method for showing an image on different display terminals. This paper uses a Radial Basis Function (RBF) neural network to assess the quality of retargeted ...

No-referenceimage quality assessment (NR-IQA) techniques try to assess the quality of images without anyinformation regarding the pristine version of the image. NR-IQA becomes more challenging for images affected by multiple distortions and images ...

This paper introduces a geometric approach for assessing color harmony of a signboard, and color coherence of a signboard with the environment. We propose to incorporate visual saliency as an inherent color characteristic residing in ...

Display Omitted

• A public dataset with 5.2 K valid subjective ratings on 375 real-world signboards.

Saliency is the ability of being important, noticeable or attention worthy. Finding salient regions in images has important applications in automatic image cropping, image compression and advertisements. The salient regions for an individual in an ...

We propose a no-reference image quality assessment (NR-IQA) approach to predict the perceptual quality score of a given image without using any reference image. Our model consists of two steps and trains two similar convolutional neural networks (...

• A new connectivity-based CNN (BiconNet) for salient object detection is proposed.

Salient object detection (SOD) is viewed as a pixel-wise saliency modeling task by traditional deep learning-based methods. A limitation of current SOD models is insufficient utilization of inter-pixel information, which usually ...

In order to improve the brightness and contrast of low illumination color images and avoid over enhancement, an adaptive image enhancement algorithm based on visual saliency is proposed. Firstly, the original low illumination image is transformed ...

Face recognition systems are widely used for target recognition and identity authentication, such as automated teller machines, mobile phones, and entrance guard systems. However, face recognition systems are vulnerable to presentation ...