Browse Proceedings

As multimodal data become increasingly popular on social media platforms, it is desirable to enhance text-based approaches with other important data sources (e.g. images) for the Sentiment Classification of social media posts. However, existing ...

Existing deep learning-based video deraining techniques have achieved remarkable processes. However, there exist some fundamental issues including plentiful engineering experiences for architecture design and slow hardware-insensitive inference ...

Recently, underwater image enhancement has attracted broad attention due to its potential in ocean exploitation. Unfortunately, limited to the hand-crafted subjective ground truth for matching low-quality underwater images, existing techniques are ...

The aim of medical image fusion is to integrate complementary information in multi-modality medical images into an informative fused image which is pivotal for assistance in clinical diagnosis. Since medical images in different modalities always ...

Recent image inpainting works have shown promising results thanks to great advances of generative adversarial networks (GANs). However, these methods would still generate distorted structures or blurry textures for the situation of large missing ...

Video recording suffers from noise, artifacts, low illumination, and weak contrast under low-light conditions. With such difficulties, it is challenging to recover a high-quality video from the corresponding low-light one. Previous works have ...$\mathrm{}{}^{\mathrm{}}$

Previous methods of highlight removal in image processing have exclusively addressed images taken in specific illumination environments. However, most of these methods have limitations in natural scenes and thus, introduce artifacts to nature ...

In order to solve the problems of degradation, uneven illumination, and shadows in the process of binarization of document images, two approaches were proposed. In this paper, many state of the art were deeply studied and an improved scheme were ...

Many light field image super-resolution networks are proposed to directly aggregate the features of different low-resolution sub-aperture images (SAIs) to reconstruct high-resolution sub-aperture images. However, most of them ignore aligning ...

Infrared small target detection is one of the key technologies in IR guidance systems. In order to obtain high detection performance and low false alarm rates against intricate backgrounds with heavy clutters and noises, an infrared small target ...

Many lightweight models have achieved great progress in single image super-resolution. However, their parameters are still too many to be applied in practical applications, and it still has space for parameter reduction. Meanwhile, multi-scale ...

In recent years, improving the visual quality of low-light images has attracted tremendous attention. Most of the existing deep learning approaches estimate the single illumination and then obtain the enhanced result according to the Retinex ...

Image captioning has attracted extensive research interests in recent years, which aims to generate a natural language description of an image. However, many approaches focus only on individual target object information without exploring the ...

In this paper, we propose a non-local network routing (NNR) approach for perceptual image super-resolution. Unlike conventional methods which generate visually-faked textures due to exiting hand-designed losses, our approach aims to globally ...

Multi-focus image fusion plays an important role in the field of image processing for its ability in solving the depth-of-focus limitation problem in optical lens imaging by fusing a series of partially focused images of the same scene. The ...

Learned image compression methods have represented the potential to outperform the traditional image compression methods in recent times. However, current learned image compression methods utilize the same spatial resolution for latent variables, ...

Capturing images in a low-light environment are usually bothered with problems such as serious noise, color degradation, and images underexposure. Most of the low-light image enhancement approaches cannot solve the problem of the loss of the ...

Low-light face images not only are difficult to be perceived by humans but also cause errors in automatic face recognition systems. Current methods of image illumination enhancement mainly focus on the improvement of the visual perception, but ...

Images captured in a dark environment may suffer from low visibility, which may degrade the visual aesthetics of images and the performance of vision-based systems. Extensive studies have focused on the low-light image enhancement (LIE) problem. ...

Hyperspectral image processing methods based on Tucker decomposition by utilizing low-rank and sparse priors are sensitive to the model order, and merely utilizing the global structural information. After statistical analysis on hyperspectral ...

To avoid any fallacious assumption on the degeneration procedure in preparing training data, some self-similarity based super-resolution (SR) algorithms have been proposed to exploit the internal recurrence of patches without relying on external ...

Image denoising which aims to remove noise in the given images is one of the most challenging tasks in the low level computer vision field. Especially for the real image noise, its complex distribution is difficult to be simulated by a single ...

In some scenarios such as autonomous diriving, we can get a sparse point cloud with a large field of view, but an RGB image with a limited FoV. This paper studies the problem of image expansion using depth information converted from sparse point ...

Deep convolutional neural networks (CNNs) have been extensively applied on single image super-resolution (SISR) due to the strong representation. However, since SISR is an ill-posed problem, many CNN-based methods rely heavily on excessive ...

As the carrier of information, digital video plays an important role in daily life. With the development of video editing tools, the authenticity of video is facing enormous challenges. As an inter-frame forgery, video speed manipulation may lead ...

The problem of skin lesion segmentation remains to be a challenging task due to the low contrast of lesions, occlusions and varied sizes of foreground. The existing methods are unable to perform well on complex scenarios. In this paper, an ...