Related papers: Decoupled Spatio-Temporal Consistency Learning for…
In this paper, we propose a simple yet effective transformer framework for self-supervised learning called DenseDINO to learn dense visual representations. To exploit the spatial information that the dense prediction tasks require but…
One of the most important factors in training object recognition networks using convolutional neural networks (CNNs) is the provision of annotated data accompanying human judgment. Particularly, in object detection or semantic segmentation,…
The presence of objects that are confusingly similar to the tracked target, poses a fundamental challenge in appearance-based visual tracking. Such distractor objects are easily misclassified as the target itself, leading to eventual…
Unsupervised disentanglement is a long-standing challenge in representation learning. Recently, self-supervised techniques achieved impressive results in the sequential setting, where data is time-dependent. However, the latter methods…
Modern visual object trackers show impressive results on general targets, yet their performance drops substantially when dealing with scene text. Although currently underexplored, tracking text in videos is essential for dynamic text…
Dense point tracking is a fundamental problem in computer vision, with applications ranging from video analysis to robotic manipulation. State-of-the-art trackers typically rely on cost volumes to match features across frames, but this…
Template-matching methods for visual tracking have gained popularity recently due to their comparable performance and fast speed. However, they lack effective ways to adapt to changes in the target object's appearance, making their tracking…
Training image-based object detectors presents formidable challenges, as it entails not only the complexities of object detection but also the added intricacies of precisely localizing objects within potentially diverse and noisy…
As an important area in computer vision, object tracking has formed two separate communities that respectively study Single Object Tracking (SOT) and Multiple Object Tracking (MOT). However, current methods in one tracking scenario are not…
Predicting traffic conditions has been recently explored as a way to relieve traffic congestion. Several pioneering approaches have been proposed based on traffic observations of the target location as well as its adjacent regions, but they…
Most deep trackers still follow the guidance of the siamese paradigms and use a template that contains only the target without any contextual information, which makes it difficult for the tracker to cope with large appearance changes, rapid…
Existing Visual Object Tracking (VOT) only takes the target area in the first frame as a template. This causes tracking to inevitably fail in fast-changing and crowded scenes, as it cannot account for changes in object appearance between…
Discriminative Correlation Filters (DCF) are efficient in visual tracking but suffer from unwanted boundary effects. Spatially Regularized DCF (SRDCF) has been suggested to resolve this issue by enforcing spatial penalty on DCF…
Children learn to build a visual representation of the world from unsupervised exploration and we hypothesize that a key part of this learning ability is the use of self-generated navigational information as a similarity label to drive a…
Contrastive learning methods have significantly narrowed the gap between supervised and unsupervised learning on computer vision tasks. In this paper, we explore their application to geo-located datasets, e.g. remote sensing, where…
We propose a novel meta-learning framework for real-time object tracking with efficient model adaptation and channel pruning. Given an object tracker, our framework learns to fine-tune its model parameters in only a few iterations of…
Distantly-Supervised Named Entity Recognition (DS-NER) effectively alleviates the data scarcity problem in NER by automatically generating training samples. Unfortunately, the distant supervision may induce noisy labels, thus undermining…
In this paper, we present a novel cross-consistency based semi-supervised approach for semantic segmentation. Consistency training has proven to be a powerful semi-supervised learning framework for leveraging unlabeled data under the…
The instance discrimination paradigm has become dominant in unsupervised learning. It always adopts a teacher-student framework, in which the teacher provides embedded knowledge as a supervision signal for the student. The student learns…
While unsupervised change detection using contrastive learning has been significantly improved the performance of literature techniques, at present, it only focuses on the bi-temporal change detection scenario. Previous state-of-the-art…