Related papers: A Twofold Siamese Network for Real-Time Object Tra…
Current convolutional neural networks algorithms for video object tracking spend the same amount of computation for each object and video frame. However, it is harder to track an object in some frames than others, due to the varying amount…
Mirror detection aims to identify the mirror regions in the given input image. Existing works mainly focus on integrating the semantic features and structural features to mine specific relations between mirror and non-mirror regions, or…
In recent years, building change detection methods have made great progress by introducing deep learning, but they still suffer from the problem of the extracted features not being discriminative enough, resulting in incomplete regions and…
Self-supervised learning has become a popular way to pretrain a deep learning model and then transfer it to perform downstream tasks. However, most of these methods are developed on large-scale image datasets that contain natural objects…
\noindent Memory has become the central mechanism enabling robust visual object tracking in modern segmentation-based frameworks. Recent methods built upon Segment Anything Model 2 (SAM2) have demonstrated strong performance by refining how…
Recent studies of two-view correspondence learning usually establish an end-to-end network to jointly predict correspondence reliability and relative pose. We improve such a framework from two aspects. First, we propose a Local Feature…
Semantic segmentation is a fundamental task in computer vision that involves dense pixel-wise classification for scene understanding. Despite significant progress, achieving high accuracy while maintaining real-time performance remains a…
Most Siamese network-based trackers perform the tracking process without model update, and cannot learn targetspecific variation adaptively. Moreover, Siamese-based trackers infer the new state of tracked objects by generating axis-aligned…
Efficient visual trackers overfit to their training distributions and lack generalization abilities, resulting in them performing well on their respective in-distribution (ID) test sets and not as well on out-of-distribution (OOD)…
Multi-modal semantic segmentation significantly enhances AI agents' perception and scene understanding, especially under adverse conditions like low-light or overexposed environments. Leveraging additional modalities (X-modality) like…
Aerial object tracking remains a challenging task due to scale variations, dynamic backgrounds, clutter, and frequent occlusions. While most existing trackers emphasize spatial cues, they often overlook temporal dependencies, resulting in…
As an essential processing step before the fusing of infrared and visible images, the performance of image registration determines whether the two images can be fused at correct spatial position. In the actual scenario, the varied imaging…
In this study, a Semi-Supervised Learning (SSL) method for improving urban change detection from bi-temporal image pairs was presented. The proposed method adapted a Dual-Task Siamese Difference network that not only predicts changes with…
6DOF camera relocalization is an important component of autonomous driving and navigation. Deep learning has recently emerged as a promising technique to tackle this problem. In this paper, we present a novel relative geometry-aware Siamese…
In video object tracking, there exist rich temporal contexts among successive frames, which have been largely overlooked in existing trackers. In this work, we bridge the individual video frames and explore the temporal contexts across them…
Extreme Learning Machine is a powerful classification method very competitive existing classification methods. It is extremely fast at training. Nevertheless, it cannot perform face verification tasks properly because face verification…
Current 3D single object tracking methods primarily rely on the Siamese matching-based paradigm, which struggles with textureless and incomplete LiDAR point clouds. Conversely, the motion-centric paradigm avoids appearance matching, thus…
Semantic Segmentation (SS) is the task to assign a semantic label to each pixel of the observed images, which is of crucial significance for autonomous vehicles, navigation assistance systems for the visually impaired, and augmented reality…
Boosting performance of the offline trained siamese trackers is getting harder nowadays since the fixed information of the template cropped from the first frame has been almost thoroughly mined, but they are poorly capable of resisting…
Visual object tracking is an important application of computer vision. Recently, Siamese based trackers have achieved good accuracy. However, most of Siamese based trackers are not efficient, as they exhaustively search potential object…