Related papers: mEBAL2 Database and Benchmark: Image-based Multisp…
The defocus deblurring raised from the finite aperture size and exposure time is an essential problem in the computational photography. It is very challenging because the blur kernel is spatially varying and difficult to estimate by…
In this work, we introduce our submission to the 2nd Affective Behavior Analysis in-the-wild (ABAW) 2021 competition. We train a unified deep learning model on multi-databases to perform two tasks: seven basic facial expressions prediction…
It is a long-term goal to transfer biological processing principles as well as the power of human recognition into machine vision and engineering systems. One of such principles is visual attention, a smart human concept which focuses…
We introduce Net2Brain, a graphical and command-line user interface toolbox for comparing the representational spaces of artificial deep neural networks (DNNs) and human brain recordings. While different toolboxes facilitate only single…
Preventable or undiagnosed visual impairment and blindness affect billion of people worldwide. Automated multi-disease detection models offer great potential to address this problem via clinical decision support in diagnosis. In this work,…
Recent successes in learning-based image classification, however, heavily rely on the large number of annotated training samples, which may require considerable human efforts. In this paper, we propose a novel active learning framework,…
Low-light image enhancement is challenging in that it needs to consider not only brightness recovery but also complex issues like color distortion and noise, which usually hide in the dark. Simply adjusting the brightness of a low-light…
Whole-slide image classification represents a key challenge in computational pathology and medicine. Attention-based multiple instance learning (MIL) has emerged as an effective approach for this problem. However, the effect of attention…
Recent deep face hallucination methods show stunning performance in super-resolving severely degraded facial images, even surpassing human ability. However, these algorithms are mainly evaluated on non-public synthetic datasets. It is thus…
Decoding visual stimuli from neural population activity is crucial for understanding the brain and for applications in brain-machine interfaces. However, such biological data is often scarce, particularly in primates or humans, where…
Despite growing interest in hallucination in Multimodal Large Language Models, existing studies primarily focus on single-image settings, leaving hallucination in multi-image scenarios largely unexplored. To address this gap, we conduct the…
The goal of few-shot learning is to generalize and achieve high performance on new unseen learning tasks, where each task has only a limited number of examples available. Gradient-based meta-learning attempts to address this challenging…
Vision-Language Models have made significant progress on many perception-focused tasks. However, their progress on reasoning-focused tasks remains limited due to the lack of high-quality and diverse training data. In this work, we aim to…
Few-shot learning is devoted to training a model on few samples. Most of these approaches learn a model based on a pixel-level or global-level feature representation. However, using global features may lose local information, and using…
Digital pathology has recently been revolutionized by advancements in artificial intelligence, deep learning, and high-performance computing. With its advanced tools, digital pathology can help improve and speed up the diagnostic process,…
Seeing-in-the-dark is one of the most important and challenging computer vision tasks due to its wide applications and extreme complexities of in-the-wild scenarios. Existing arts can be mainly divided into two threads: 1) RGB-dependent…
Recent advances in appearance-based models have shown improved eye tracking performance in difficult scenarios like occlusion due to eyelashes, eyelids or camera placement, and environmental reflections on the cornea and glasses. The key…
Retinal imaging provides a non-invasive window into systemic microvascular health and has emerged as a potential biomarker for systemic diseases. However, whether retinal features encode biologically meaningful systemic signals that can be…
Visual illusions play a significant role in understanding visual perception. Current methods in understanding and evaluating visual illusions are mostly deterministic filtering based approach and they evaluate on a handful of visual…
In recent years many different deep neural networks were developed, but due to a large number of layers in deep networks, their training requires a long time and a large number of datasets. Today is popular to use trained deep neural…