Related papers: Test-Time Intensity Consistency Adaptation for Sha…

In digital imaging, enhancing visual content in poorly lit environments is a significant challenge, as images often suffer from inadequate brightness, hidden details, and an overall reduction in quality. This issue is especially critical in…

Feature descriptor matching is a critical step is many computer vision applications such as image stitching, image retrieval and visual localization. However, it is often affected by many practical factors which will degrade its…

Image shadow removal is a crucial task in computer vision. In real-world scenes, shadows alter image color and brightness, posing challenges for perception and texture recognition. Traditional and deep learning methods often overlook the…

Many software engineering tasks, such as testing, and anomaly detection can benefit from the ability to infer a behavioral model of the software.Most existing inference approaches assume access to code to collect execution sequences. In…

Connectionist Temporal Classification (CTC) and attention mechanism are two main approaches used in recent scene text recognition works. Compared with attention-based methods, CTC decoder has a much shorter inference time, yet a lower…

Infrared small target detection (ISTD) is highly sensitive to sensor type, observation conditions, and the intrinsic properties of the target. These factors can introduce substantial variations in the distribution of acquired infrared image…

Digital camera pipelines employ color constancy methods to estimate an unknown scene illuminant, in order to re-illuminate images as if they were acquired under an achromatic light source. Fully-supervised learning approaches exhibit…

Continual Test-time adaptation (CTTA) continuously adapts the deployed model on every incoming batch of data. While achieving optimal accuracy, existing CTTA approaches present poor real-world applicability on resource-constrained edge…

Applying an object detector, which is neither trained nor fine-tuned on data close to the final application, often leads to a substantial performance drop. In order to overcome this problem, it is necessary to consider a shift between…

Deepfake (DF) detectors face significant challenges when deployed in real-world environments, particularly when encountering test samples deviated from training data through either postprocessing manipulations or distribution shifts. We…

Recent advances in computer vision and deep learning have led to breakthroughs in the development of automated skin image analysis. In particular, skin cancer classification models have achieved performance higher than trained expert…

Domain shift widely exists in the visual world, while modern deep neural networks commonly suffer from severe performance degradation under domain shift due to the poor generalization ability, which limits the real-world applications. The…

Deep learning models perform poorly when domain shifts exist between training and test data. Test-time adaptation (TTA) is a paradigm to mitigate this issue by adapting pre-trained models using only unlabeled test samples. However, existing…

In this paper, we focus on improving the online face liveness detection system to enhance the security of the downstream face recognition system. Most of the existing frame-based methods are suffering from the prediction inconsistency…

Existing shadow detection models struggle to differentiate dark image areas from shadows. In this paper, we tackle this issue by verifying that all detected shadows are real, i.e. they have paired shadow casters. We perform this step in a…

Local structures of shadow boundaries as well as complex interactions of image regions remain largely unexploited by previous shadow detection approaches. In this paper, we present a novel learning-based framework for shadow region recovery…

Context-consistency checking is challenging in the dynamic and uncertain ubiquitous computing environments. This is because contexts are often noisy owing to unreliable sensing data streams, inaccurate data measurement, fragile connectivity…

Although deep convolutional neural networks achieve state-of-the-art performance across nearly all image classification tasks, their decisions are difficult to interpret. One approach that offers some level of interpretability by design is…

Infrared Small Target Detection (IRSTD) faces significant challenges due to low signal-to-noise ratios, complex backgrounds, and the absence of discernible target features. While deep learning-based encoder-decoder frameworks have advanced…

To ensure reliable object detection in autonomous systems, the detector must be able to adapt to changes in appearance caused by environmental factors such as time of day, weather, and seasons. Continually adapting the detector to…