Applications of graph convolutional networks in computer vision

P Cao, Z Zhu, Z Wang, Y Zhu, Q Niu - Neural computing and applications, 2022‏ - Springer
Abstract Graph Convolutional Network (GCN) which models the potential relationship
between non-Euclidean spatial data has attracted researchers' attention in deep learning in …

Simpletrack: Understanding and rethinking 3d multi-object tracking

Z Pang, Z Li, N Wang - European conference on computer vision, 2022‏ - Springer
Abstract 3D multi-object tracking (MOT) has witnessed numerous novel benchmarks and
approaches in recent years, especially those under the “tracking-by-detection” paradigm …

Learnable graph matching: Incorporating graph partitioning with deep feature learning for multiple object tracking

J He, Z Huang, N Wang… - Proceedings of the IEEE …, 2021‏ - openaccess.thecvf.com
Data association across frames is at the core of Multiple Object Tracking (MOT) task. This
problem is usually solved by a traditional graph-based optimization or directly learned via …

Recent advances in embedding methods for multi-object tracking: A survey

G Wang, M Song, JN Hwang - arxiv preprint arxiv:2205.10766, 2022‏ - arxiv.org
Multi-object tracking (MOT) aims to associate target objects across video frames in order to
obtain entire moving trajectories. With the advancement of deep neural networks and the …

Triplettrack: 3d object tracking using triplet embeddings and lstm

N Marinello, M Proesmans… - Proceedings of the …, 2022‏ - openaccess.thecvf.com
Abstract 3D object tracking is a critical task in autonomous driving systems. It plays an
essential role for the system's awareness about the surrounding environment. At the same …

Diffusiontrack: Diffusion model for multi-object tracking

R Luo, Z Song, L Ma, J Wei, W Yang… - Proceedings of the AAAI …, 2024‏ - ojs.aaai.org
Multi-object tracking (MOT) is a challenging vision task that aims to detect individual objects
within a single frame and associate them across multiple frames. Recent MOT approaches …

Multiple source domain adaptation for multiple object tracking in satellite video

X Zheng, H Cui, X Lu - IEEE Transactions on Geoscience and …, 2023‏ - ieeexplore.ieee.org
Satellite videos capture the dynamic changes in a large observed sense, which provides an
opportunity to track the object trajectories. However, existing multiple object tracking (MOT) …

Exploiting temporal relations on radar perception for autonomous driving

P Li, P Wang, K Berntorp, H Liu - Proceedings of the IEEE …, 2022‏ - openaccess.thecvf.com
We consider the object recognition problem in autonomous driving using automotive radar
sensors. Comparing to Lidar sensors, radar is cost-effective and robust in all-weather …

Gcnnmatch: Graph convolutional neural networks for multi-object tracking via sinkhorn normalization

I Papakis, A Sarkar, A Karpatne - arxiv preprint arxiv:2010.00067, 2020‏ - arxiv.org
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 …

Learning of global objective for network flow in multi-object tracking

S Li, Y Kong, H Rezatofighi - Proceedings of the IEEE/CVF …, 2022‏ - openaccess.thecvf.com
This paper concerns the problem of multi-object tracking based on the min-cost flow (MCF)
formulation, which is conventionally studied as an instance of linear program. Given its …