Most red–green–blue and thermal (RGB-T) salient object detection methods require high
memory consumption and incur large computational costs, which limit their applicability. To …

In this paper, we introduce TIVE, a Toolbox for Identifying Video instance segmentation
Errors. By directly operating output prediction files, TIVE defines isolated error types and …

Multi-modal learning aims at simultaneously modelling data from several modalities such as
image, text and speech. The goal is to simultaneously learn representations and make them …

Memory-based methods in semi-supervised video object segmentation (VOS) achieve
competitive performance by performing feature similarity between the current frame and …

Video target segmentation is a fundamental problem in computer vision that aims to
segment targets from a background by learning their appearance information and movement …

Deep learning models have been proven to be susceptible to malicious adversarial attacks,
which manipulate input images to deceive the model into making erroneous decisions …

Video object segmentation is a popular area of research in computer vision. Traditional
models are trained using annotated data, which is both time-consuming and expensive …

Abstract Like Gaussian distribution, Laplacian distribution is also a location-scale family of
distributions. So we can choose the standard Laplace distribution (with location= 0, scale …

Single object tracking (SOT) finds the object correspondence in a spatio-temporal domain,
and incorporates various applications in Computer Vision. The Siamese trackers have …