Related papers: Enhancing Feature Tracking With Gyro Regularizatio…
Variations of target appearance such as deformations, illumination variance, occlusion, etc., are the major challenges of visual object tracking that negatively impact the performance of a tracker. An effective method to tackle these…
Few-shot image classification remains challenging due to the scarcity of labeled training examples. Augmenting them with synthetic data has emerged as a promising way to alleviate this issue, but models trained on synthetic samples often…
Traditionally multi-object tracking and object detection are performed using separate systems with most prior works focusing exclusively on one of these aspects over the other. Tracking systems clearly benefit from having access to accurate…
Pre-trained vision-language models, such as CLIP, show impressive zero-shot recognition ability and can be easily transferred to specific downstream tasks via prompt tuning, even with limited training data. However, existing prompt tuning…
Correlation filter (CF)-based trackers have gained significant attention for their computational efficiency in thermal infrared (TIR) target tracking. However, ex-isting methods struggle with challenges such as low-resolution imagery,…
Track geometry monitoring is essential for maintaining the safety and efficiency of railway operations. While Track Recording Cars (TRCs) provide accurate measurements of track geometry indicators, their limited availability and high…
Fine-tuning large-scale pretrained models is prohibitively expensive in terms of computational and memory costs. LoRA, as one of the most popular Parameter-Efficient Fine-Tuning (PEFT) methods, offers a cost-effective alternative by…
Regularization is used in many different areas of optimization when solutions are sought which not only minimize a given function, but also possess a certain degree of regularity. Popular applications are image denoising, sparse regression…
Most tracking-by-detection methods employ a local search window around the predicted object location in the current frame assuming the previous location is accurate, the trajectory is smooth, and the computational capacity permits a search…
The current popular two-stream, two-stage tracking framework extracts the template and the search region features separately and then performs relation modeling, thus the extracted features lack the awareness of the target and have limited…
Generalizable Image Super-Resolution aims to enhance model generalization capabilities under unknown degradations. To achieve this goal, the models are expected to focus only on image content-related features instead of overfitting…
Tracking specific targets, such as pedestrians and vehicles, has been the focus of recent vision-based multitarget tracking studies. However, in some real-world scenarios, unseen categories often challenge existing methods due to…
Low-rank matrix completion has achieved great success in many real-world data applications. A matrix factorization model that learns latent features is usually employed and, to improve prediction performance, the similarities between latent…
Accurate object tracking in low-light environments is crucial, particularly in surveillance and ethology applications. However, achieving this is significantly challenging due to the poor quality of captured sequences. Factors such as…
Sparse-view 3D Gaussian Splatting (3DGS) often overfits to the training views, leading to artifacts like blurring in novel view rendering. Prior work addresses it either by enhancing the initialization (\emph{i.e.}, the point cloud from…
We present DINO-Tracker -- a new framework for long-term dense tracking in video. The pillar of our approach is combining test-time training on a single video, with the powerful localized semantic features learned by a pre-trained DINO-ViT…
Correlation filtering based tracking model has received lots of attention and achieved great success in real-time tracking, however, the lost function in current correlation filtering paradigm could not reliably response to the appearance…
Spectral methods are popular in detecting global structures in the given data that can be represented as a matrix. However when the data matrix is sparse or noisy, classic spectral methods usually fail to work, due to localization of…
Multi-object tracking plays a crucial role in various applications, such as autonomous driving and security surveillance. This study introduces Deep LG-Track, a novel multi-object tracker that incorporates three key enhancements to improve…
Trace norm regularization is a widely used approach for learning low rank matrices. A standard optimization strategy is based on formulating the problem as one of low rank matrix factorization which, however, leads to a non-convex problem.…