Related papers: Effective Image Differencing with ConvNets for Rea…

In computer vision, superpixels have been widely used as an effective way to reduce the number of image primitives for subsequent processing. But only a few attempts have been made to incorporate them into deep neural networks. One main…

Very deep convolutional neural networks (CNNs) have been firmly established as the primary methods for many computer vision tasks. However, most state-of-the-art CNNs are large, which results in high inference latency. Recently, depth-wise…

Shot boundary detection (SBD) is an important first step in many video processing applications. This paper presents a simple modular convolutional neural network architecture that achieves state-of-the-art results on the RAI dataset with…

For the task of change detection (CD) in remote sensing images, deep convolution neural networks (CNNs)-based methods have recently aggregated transformer modules to improve the capability of global feature extraction. However, they suffer…

The detection and analysis of transient astronomical sources is of great importance to understand their time evolution. Traditional pipelines identify transient sources from difference (D) images derived by subtracting prior-observed…

Small object detection is a broadly investigated research task and is commonly conceptualized as a "pipeline-style" engineering process. In the upstream, images serve as raw materials for processing in the detection pipeline, where…

Recently, deep learning technology have been extensively used in the field of image recognition. However, its main application is the recognition and detection of ordinary pictures and common scenes. It is challenging to effectively and…

Lossy compression introduces complex compression artifacts, particularly blocking artifacts, ringing effects and blurring. Existing algorithms either focus on removing blocking artifacts and produce blurred output, or restore sharpened…

Face anti-spoofing is crucial for the security of face recognition system, by avoiding invaded with presentation attack. Previous works have shown the effectiveness of using depth and temporal supervision for this task. However, depth…

The paper presents a new model for single channel images low-level interpretation. The image is decomposed into a graph which captures a complete set of structural features. The description allows to accurately identify every edge location…

Time-domain surveys such as the Zwicky Transient Facility (ZTF) have opened a new frontier in the discovery and characterization of transients. While photometric light curves provide broad temporal coverage, spectroscopic observations…

Background subtraction is a fundamental task in computer vision with numerous real-world applications, ranging from object tracking to video surveillance. Dynamic backgrounds poses a significant challenge here. Supervised deep…

As deep learning technology continues to evolve, the images yielded by generative models are becoming more and more realistic, triggering people to question the authenticity of images. Existing generated image detection methods detect…

Astronomers require efficient automated detection and classification pipelines when conducting large-scale surveys of the (optical) sky for variable and transient sources. Such pipelines are fundamentally important, as they permit rapid…

Deepfakes are the result of digital manipulation to forge realistic yet fake imagery. With the astonishing advances in deep generative models, fake images or videos are nowadays obtained using variational autoencoders (VAEs) or Generative…

Deep convolutional neural network (CNN) based salient object detection methods have achieved state-of-the-art performance and outperform those unsupervised methods with a wide margin. In this paper, we propose to integrate deep and…

This paper presents a new state-of-the-art for document image classification and retrieval, using features learned by deep convolutional neural networks (CNNs). In object and scene analysis, deep neural nets are capable of learning a…

Deep learning algorithms have recently achieved promising deraining performances on both the natural and synthetic rainy datasets. As an essential low-level pre-processing stage, a deraining network should clear the rain streaks and…

Palmprint recognition has drawn a lot of attention during the recent years. Many algorithms have been proposed for palmprint recognition in the past, majority of them being based on features extracted from the transform domain. Many of…

[abridged] In large-scale time-domain surveys, the processing of data, from procurement up to the detection of sources, is generally automated. One of the main challenges is contamination by artifacts, especially in regions of strong…