Related papers: Graph Neural Networks for 3D Multi-Object Tracking

Multiobject tracking (MOT) is an important task in robotics, autonomous driving, and maritime surveillance. Traditional work on MOT is model-based and aims to establish algorithms in the framework of sequential Bayesian estimation. More…

In recent times, the scope of LIDAR (Light Detection and Ranging) sensor-based technology has spread across numerous fields. It is popularly used to map terrain and navigation information into reliable 3D point cloud data, potentially…

Infrared and visible image fusion has gradually proved to be a vital fork in the field of multi-modality imaging technologies. In recent developments, researchers not only focus on the quality of fused images but also evaluate their…

State-of-the-art multi-object tracking~(MOT) methods follow the tracking-by-detection paradigm, where object trajectories are obtained by associating per-frame outputs of object detectors. In crowded scenes, however, detectors often fail to…

Human-Object Interaction (HOI) recognition in videos requires understanding both visual patterns and geometric relationships as they evolve over time. Visual and geometric features offer complementary strengths. Visual features capture…

Autonomous driving requires 3D perception of vehicles and other objects in the in environment. Much of the current methods support 2D vehicle detection. This paper proposes a flexible pipeline to adopt any 2D detection network and fuse it…

Accurate interpretation of street-level imagery is essential for large-scale urban mapping and the creation of Spatial Digital Twin (SDT) environments. This work presents a unified framework for joint 2D-3D segmentation and association that…

Objects rarely sit in isolation in human environments. As such, we'd like our robots to reason about how multiple objects relate to one another and how those relations may change as the robot interacts with the world. To this end, we…

In the existing literature, most 3D multi-object tracking algorithms based on the tracking-by-detection framework employed deterministic tracks and detections for similarity calculation in the data association stage. Namely, the inherent…

Feature-based image matching has extensive applications in computer vision. Keypoints detected in images can be naturally represented as graph structures, and Graph Neural Networks (GNNs) have been shown to outperform traditional deep…

The advancement of computer vision has pushed visual analysis tasks from still images to the video domain. In recent years, video instance segmentation, which aims to track and segment multiple objects in video frames, has drawn much…

Bottom-up approaches for image-based multi-person pose estimation consist of two stages: (1) keypoint detection and (2) grouping of the detected keypoints to form person instances. Current grouping approaches rely on learned embedding from…

Graph neural network (GNN) is a popular tool to learn the lower-dimensional representation of a graph. It facilitates the applicability of machine learning tasks on graphs by incorporating domain-specific features. There are various options…

We propose a novel approach for joint 3D multi-object tracking and reconstruction from RGB-D sequences in indoor environments. To this end, we detect and reconstruct objects in each frame while predicting dense correspondences mappings into…

In this paper we propose a novel approach to tracking by detection that can exploit both cameras as well as LIDAR data to produce very accurate 3D trajectories. Towards this goal, we formulate the problem as a linear program that can be…

We address the problem of merging graph and feature-space information while learning a metric from structured data. Existing algorithms tackle the problem in an asymmetric way, by either extracting vectorized summaries of the graph…

Multi-object tracking (MOT) is a core task in computer vision that involves detecting objects in video frames and associating them across time. The rise of deep learning has significantly advanced MOT, particularly within the…

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…

Designing a robust affinity model is the key issue in multiple target tracking (MTT). This paper proposes a novel affinity model by learning feature representation and distance metric jointly in a unified deep architecture. Specifically, we…

Learning data-efficient object dynamics models for robotic manipulation remains challenging, especially for deformable objects. A popular approach is to model objects as sets of 3D particles and learn their motion using graph neural…