Related papers: Tracking Different Ant Species: An Unsupervised Do…
Tiny objects, frequently appearing in practical applications, have weak appearance and features, and receive increasing interests in meany vision tasks, such as object detection and segmentation. To promote the research and development of…
This paper addresses the problem of multi-object tracking in Unmanned Aerial Vehicle (UAV) footage. It plays a critical role in various UAV applications, including traffic monitoring systems and real-time suspect tracking by the police.…
Unsupervised domain adaptation for object detection addresses the adaption of detectors trained in a source domain to work accurately in an unseen target domain. Recently, methods approaching the alignment of the intermediate features…
The challenging task of multi-object tracking (MOT) requires simultaneous reasoning about track initialization, identity, and spatio-temporal trajectories. We formulate this task as a frame-to-frame set prediction problem and introduce…
Existing visual trackers mainly operate in a non-interactive, fire-and-forget manner, making them impractical for real-world scenarios that require human-in-the-loop adaptation. To overcome this limitation, we introduce Interactive…
In recent years, object detection has shown impressive results using supervised deep learning, but it remains challenging in a cross-domain environment. The variations of illumination, style, scale, and appearance in different domains can…
Drones, or general UAVs, equipped with a single camera have been widely deployed to a broad range of applications, such as aerial photography, fast goods delivery and most importantly, surveillance. Despite the great progress achieved in…
We consider the problem of domain adaptation in LiDAR-based 3D object detection. Towards this, we propose a simple yet effective training strategy called Gradual Batch Alternation that can adapt from a large labeled source domain to an…
In this paper, SIA_Track is presented which is developed by a research team from SI Analytics. The proposed method was built from pre-existing detector and tracker under the tracking-by-detection paradigm. The tracker we used is an online…
Multi-object tracking (MOT) is a vital component of intelligent video analytics applications such as surveillance and autonomous driving. The time and storage complexity required to execute deep learning models for visual object tracking…
While fine-grained object recognition is an important problem in computer vision, current models are unlikely to accurately classify objects in the wild. These fully supervised models need additional annotated images to classify objects in…
Visual multi-object tracking has the potential to accelerate many forms of quantitative analyses, especially in research communities investigating the motion, behavior, or social interactions within groups of animals. Despite its potential…
Multiple Object Tracking (MOT) is a core capability in modern computer vision, essential to autonomous driving, surveillance, sports analytics, robotics, and biomedical imaging. Persistent identity assignment across frames remains…
Multimodal vision-language (VL) learning has noticeably pushed the tendency toward generic intelligence owing to emerging large foundation models. However, tracking, as a fundamental vision problem, surprisingly enjoys less bonus from…
Recent works in multiple object tracking use sequence model to calculate the similarity score between the detections and the previous tracklets. However, the forced exposure to ground-truth in the training stage leads to the…
We present a novel multi-attentional convolutional architecture to tackle the problem of real-time RGB-D 6D object pose tracking of single, known objects. Such a problem poses multiple challenges originating both from the objects' nature…
Object tracking quality usually depends on video context (e.g. object occlusion level, object density). In order to decrease this dependency, this paper presents a learning approach to adapt the tracker parameters to the context variations.…
Benefit from large-scale training data, recent advances in Siamese-based object tracking have achieved compelling results on the normal sequences. Whilst Siamese-based trackers assume training and test data follow an identical distribution.…
Annotating large scale datasets to train modern convolutional neural networks is prohibitively expensive and time-consuming for many real tasks. One alternative is to train the model on labeled synthetic datasets and apply it in the real…
Object detection models trained on a source domain often exhibit significant performance degradation when deployed in unseen target domains, due to various kinds of variations, such as sensing conditions, environments and data…