Related papers: UniTrack: Differentiable Graph Representation Lear…
This paper proposes a novel method for online Multi-Object Tracking (MOT) using Graph Convolutional Neural Network (GCNN) based feature extraction and end-to-end feature matching for object association. The Graph based approach incorporates…
Multi-object tracking (MOT) in videos remains challenging due to complex object motions and crowded scenes. Recent DETR-based frameworks offer end-to-end solutions but typically process detection and tracking queries jointly within a single…
We introduce UniLoss, a unified framework to generate surrogate losses for training deep networks with gradient descent, reducing the amount of manual design of task-specific surrogate losses. Our key observation is that in many cases,…
Multi-view multi-object tracking (MVMOT) has found widespread applications in intelligent transportation, surveillance systems, and urban management. However, existing studies rarely address genuinely free-viewpoint MVMOT systems, which…
Single object tracking (SOT) heavily relies on the representation of the target object as a bounding box. However, due to the potential deformation and rotation experienced by the tracked targets, the genuine bounding box fails to capture…
Existing 3D multi-object tracking (MOT) methods often sacrifice efficiency and generalizability for robustness, largely relying on complex association metrics derived from multi-modal architectures and class-specific motion priors.…
Temporal modeling of objects is a key challenge in multiple object tracking (MOT). Existing methods track by associating detections through motion-based and appearance-based similarity heuristics. The post-processing nature of association…
Achieving expressive and generalizable whole-body motion control is essential for deploying humanoid robots in real-world environments. In this work, we propose UniTracker, a three-stage training framework that enables robust and scalable…
We present DroTrack, a high-speed visual single-object tracking framework for drone-captured video sequences. Most of the existing object tracking methods are designed to tackle well-known challenges, such as occlusion and cluttered…
We propose a universal video-level modality-awareness tracking model with online dense temporal token learning (called {\modaltracker}). It is designed to support various tracking tasks, including RGB, RGB+Thermal, RGB+Depth, and RGB+Event,…
Transfer learning has the potential to reduce the burden of data collection and to decrease the unavoidable risks of the training phase. In this letter, we introduce a multirobot, multitask transfer learning framework that allows a system…
Data association is at the core of many computer vision tasks, e.g., multiple object tracking, image matching, and point cloud registration. however, current data association solutions have some defects: they mostly ignore the intra-view…
Multi-Object Tracking (MOT) has been a long-standing challenge in video understanding. A natural and intuitive approach is to split this task into two parts: object detection and association. Most mainstream methods employ meticulously…
UAV tracking faces significant challenges in real-world scenarios, such as small-size targets and occlusions, which limit the performance of RGB-based trackers. Multispectral images (MSI), which capture additional spectral information,…
Tracking multiple tiny objects is highly challenging due to their weak appearance and limited features. Existing multi-object tracking algorithms generally focus on single-modality scenes, and overlook the complementary characteristics of…
Effective urban traffic management is vital for sustainable city development, relying on intelligent systems with machine learning tasks such as traffic flow prediction and travel time estimation. Traditional approaches usually focus on…
Transformer-based models have improved visual tracking, but most still cannot run in real time on resource-limited devices, especially for unmanned aerial vehicle (UAV) tracking. To achieve a better balance between performance and…
Objection detection (OD) has been one of the most fundamental tasks in computer vision. Recent developments in deep learning have pushed the performance of image OD to new heights by learning-based, data-driven approaches. On the other…
Multimodal sensing has proven valuable for visual tracking, as different sensor types offer unique strengths in handling one specific challenging scene where object appearance varies. While a generalist model capable of leveraging all…
Unsupervised pre-training has shown great success in skeleton-based action understanding recently. Existing works typically train separate modality-specific models, then integrate the multi-modal information for action understanding by a…