paper-with-me

Papers

Multi-Scene Generalized Trajectory Global Graph Solver with Composite Nodes for Multiple Object Tracking

2023-12-14 · Yan Gao, Haojun Xu, Nannan Wang, Jie Li, Xinbo Gao

The global multi-object tracking (MOT) system can consider interaction, occlusion, and other ``visual blur'' scenarios to ensure effective object tracking in long videos. Among them, graph-based tracking-by-detection paradigms achieve surprising performance. However, their fully-connected nature poses storage space requirements that challenge algorithm handling long videos. Currently, commonly used methods are still generated trajectories by building one-forward associations across frames. Such matches produced under the guidance of first-order similarity information may not be optimal from a longer-time perspective. Moreover, they often lack an end-to-end scheme for correcting mismatches. This paper proposes the Composite Node Message Passing Network (CoNo-Link), a multi-scene generalized framework for modeling ultra-long frames information for association. CoNo-Link's solution is a low-storage overhead method for building constrained connected graphs. In addition to the previous method of treating objects as nodes, the network innovatively treats object trajectories as nodes for information interaction, improving the graph neural network's feature representation capability. Specifically, we formulate the graph-building problem as a top-k selection task for some reliable objects or trajectories. Our model can learn better predictions on longer-time scales by adding composite nodes. As a result, our method outperforms the state-of-the-art in several commonly used datasets.

📄 PDF Abstract BibTeX arXiv:2312.08951

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Object TrackingMultiple Object TrackingObjectObject Tracking

Similar Papers 제목 키워드 기반

PreGSU-A Generalized Traffic Scene Understanding Model for Autonomous Driving based on Pre-trained Graph Attention Network

2024-04-16 · Yuning Wang, Zhiyuan Liu, Haotian Lin, Junkai Jiang 외

Scene understanding, defined as learning, extraction, and representation of interactions among traffic elements, is one of the critical challenges toward high-level autonomous driving (AD). Current scene understanding me…

Autonomous DrivingFeature EngineeringGraph AttentionIntent Detection+2

Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos

2026-02-26 · Ziqi Gao, Jieyu Zhang, Wisdom Oluchi Ikezogwo, Jae Sung Park 외 arxiv

We introduce Synthetic Visual Genome 2 (SVG2), a large-scale panoptic video scene graph dataset. SVG2 contains over 636K videos with 6.6M objects, 52.0M attributes, and 6.7M relations, providing an order-of-magnitude inc…

Video scene graph generationVideo Question AnsweringPanoptic SegmentationSemantic Parsing

GTT-Net: Learned Generalized Trajectory Triangulation

2021-09-08 · ICCV 2021 10 · Xiangyu Xu, Enrique Dunn

We present GTT-Net, a supervised learning framework for the reconstruction of sparse dynamic 3D geometry. We build on a graph-theoretic formulation of the generalized trajectory triangulation problem, where non-concurren…

3D geometryEvent Segmentation

HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding

2022-04-30 · Xiaosong Jia, Penghao Wu, Li Chen, Yu Liu 외

Encoding a driving scene into vector representations has been an essential task for autonomous driving that can benefit downstream tasks e.g. trajectory prediction. The driving scene often involves heterogeneous elements…

Autonomous Drivinggraph constructionGraph Neural NetworkRelation+1

ReefMapGS: Enabling Large-Scale Underwater Reconstruction by Closing the Loop Between Multimodal SLAM and Gaussian Splatting

2026-04-13 · Daniel Yang, Jungseok Hong, John J. Leonard, Yogesh Girdhar arxiv

3D Gaussian Splatting is a powerful visual representation, providing high-quality and efficient 3D scene reconstruction, but it is crucially dependent on accurate camera poses typically obtained from computationally inte…

3D ReconstructionPose Estimation