首页/论文/2011.09214

arXiv 2011.092142020-11-18cs.CV

Res-GCNN: A Lightweight Residual Graph Convolutional Neural Networks for Human Trajectory Forecasting

Yanwu Ge, Mingliang Song

备注：: 8 pages, 3 figures

英文摘要：

Autonomous driving vehicles (ADVs) hold great hopes to solve traffic congestion problems and reduce the number of traffic accidents. Accurate trajectories prediction of other traffic agents around ADVs is of key importance to achieve safe and efficient driving. Pedestrians, particularly, are more challenging to forecast due to their complex social in-teractions and randomly moving patterns. We propose a Residual Graph Convolutional Neural Network (Res-GCNN), which models the interactive behaviors of pedes-trians by using the adjacent matrix of the constructed graph for the current scene. Though the proposed Res-GCNN is quite lightweight with only about 6.4 kilo parameters which outperforms all other methods in terms of parameters size, our experimental results show an improvement over the state of art by 13.3% on the Final Displacement Error (FDE) which reaches 0.65 meter. As for the Average Dis-placement Error (ADE), we achieve a suboptimal result (the value is 0.37 meter), which is also very competitive. The Res-GCNN is evaluated in the platform with an NVIDIA GeForce RTX1080Ti GPU, and its mean inference time of the whole dataset is only about 2.2 microseconds. Compared with other methods, the proposed method shows strong potential for onboard application accounting for forecasting accuracy and time efficiency. The code will be made publicly available on GitHub.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization

Virginia Tech（弗吉尼亚理工大学）

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 both appearance and geometry of objects at past frames as well as the current frame into the task of feature learning. This new paradigm enables the network to leverage the "context" information of the geometry of objects and allows us to model the interactions among the features of multiple objects. Another central innovation of our proposed framework is t…

2021-04-16cs.CV

Dynamic Spatio-temporal Graph-based CNNs for Traffic Prediction

Alibaba Damo Academy, Alibaba Group（阿里巴巴集团阿里巴巴达摩院）；Alibaba Cloud, Alibaba Group（阿里巴巴集团阿里云）

Forecasting future traffic flows from previous ones is a challenging problem because of their complex and dynamic nature of spatio-temporal structures. Most existing graph-based CNNs attempt to capture the static relations while largely neglecting the dynamics underlying sequential data. In this paper, we present dynamic spatio-temporal graph-based CNNs (DST-GCNNs) by learning expressive features to represent spatio-temporal structures and predict future traffic flows from surveillance video data. In particular, DST-GCNN is a two stream network. In the flow prediction stream, we present a nove…

2020-03-05cs.CV

Crowd Density Forecasting by Modeling Patch-based Dynamics

Chubu University（中部大学）；OMRON SINIC X（欧姆龙 SINIC X 研究院）

Forecasting human activities observed in videos is a long-standing challenge in computer vision, which leads to various real-world applications such as mobile robots, autonomous driving, and assistive systems. In this work, we present a new visual forecasting task called crowd density forecasting. Given a video of a crowd captured by a surveillance camera, our goal is to predict how that crowd will move in future frames. To address this task, we have developed the patch-based density forecasting network (PDFN), which enables forecasting over a sequence of crowd density maps describing how crow…

2019-11-22cs.CV

Mesh Graphormer

Microsoft（微软）

We present a graph-convolution-reinforced transformer, named Mesh Graphormer, for 3D human pose and mesh reconstruction from a single image. Recently both transformers and graph convolutional neural networks (GCNNs) have shown promising progress in human mesh reconstruction. Transformer-based approaches are effective in modeling non-local interactions among 3D mesh vertices and body joints, whereas GCNNs are good at exploiting neighborhood vertex interactions based on a pre-specified mesh topology. In this paper, we study how to combine graph convolutions and self-attentions in a transformer t…

2021-08-15cs.CV

学习颜色等变表示

Learning Color Equivariant Representations

Princeton University（普林斯顿大学）；University of Oxford（牛津大学）

本文提出颜色等变图卷积神经网络，解决颜色变化下的等变问题，通过提升等变性并扩展到饱和度和亮度变化，提升模型泛化能力和样本效率。

2026-04-12cs.CVcs.LG

Graph Classification via Discriminative Edge Feature Learning

Deakin University（迪肯大学）；Fudan University（复旦大学）

Spectral graph convolutional neural networks (GCNNs) have been producing encouraging results in graph classification tasks. However, most spectral GCNNs utilize fixed graphs when aggregating node features, while omitting edge feature learning and failing to get an optimal graph structure. Moreover, many existing graph datasets do not provide initialized edge features, further restraining the ability of learning edge features via spectral GCNNs. In this paper, we try to address this issue by designing an edge feature scheme and an add-on layer between every two stacked graph convolution layers …

2022-10-05cs.CVcs.LG

更多相关论文收起更多论文

对特征空间中的群卷积神经网络进行离散化以处理3D几何

Discretizing Group-Convolutional Neural Networks for 3D Geometry in Feature Space

Johannes Gutenberg University Mainz（美因茨约翰内斯·古腾堡大学）

本文提出在特征空间中进行采样，通过特征相似性选择代表性样本，从而解耦几何分辨率与内存处理成本，实现计算效率与精度的平衡。实验表明粗粒度的特征空间采样能有效保持分类精度，加速等变3D分类器的训练。

2026-05-14cs.CVcs.GRcs.LG

提高面向FPGA实现的基于事件视觉的图卷积的可扩展性

Increasing the scalability of graph convolution for FPGA-implemented event-based vision

AGH University of Krakow（克拉科夫AGH科技大学）；Sorbonne University（索邦大学）

本文针对FPGA上事件视觉图卷积的资源瓶颈，提出利用额外BRAM缓冲区的“两步卷积”方法，可减少高达94%的乘法LUT使用量，从而显著提升GCNNs的可扩展性。

2024-11-25cs.CV

Improving anatomical plausibility in medical image segmentation via hybrid graph neural networks: applications to chest x-ray analysis

Institute for Signals, Systems and Computational Intelligence, sinc(i) CONICET-UNL（信号、系统与计算智能研究所，sinc(i) 阿根廷国家科学技术研究委员会-国立利托拉尔大学）；Hospital Italiano de Buenos Aires（布宜诺斯艾利斯意大利医院）；Universidad Tecnológica Nacional（国立技术大学）

Anatomical segmentation is a fundamental task in medical image computing, generally tackled with fully convolutional neural networks which produce dense segmentation masks. These models are often trained with loss functions such as cross-entropy or Dice, which assume pixels to be independent of each other, thus ignoring topological errors and anatomical inconsistencies. We address this limitation by moving from pixel-level to graph representations, which allow to naturally incorporate anatomical constraints by construction. To this end, we introduce HybridGNet, an encoder-decoder neural archit…

2022-11-14cs.CVeess.IV

紧凑且强大：利用图神经网络与边卷积实现医学图像分类

Compact & Capable: Harnessing Graph Neural Networks and Edge Convolution for Medical Image Classification

University of Limerick（利默里克大学）

本研究提出一种结合图神经网络与边卷积的新型医学图像分类模型，参数量仅为现有先进深度神经网络的千分之一，在MedMNIST数据集上性能相当，为医学图像分析提供了更轻量可靠的方案。

2023-07-24cs.CVcs.LGeess.IV

Hi-EF：人机交互中的情感预测基准测试

Hi-EF: Benchmarking Emotion Forecasting in Human-interaction

Hi-EF提出了一种基于人机交互的人机情感预测方法，通过动态交互视角提升情感预测的可行性与准确性。

2025-12-01cs.CVcs.LG

Learning to Transfer for Traffic Forecasting via Multi-task Learning

Layer 6 AI

Deep neural networks have demonstrated superior performance in short-term traffic forecasting. However, most existing traffic forecasting systems assume that the training and testing data are drawn from the same underlying distribution, which limits their practical applicability. The NeurIPS 2021 Traffic4cast challenge is the first of its kind dedicated to benchmarking the robustness of traffic forecasting models towards domain shifts in space and time. This technical report describes our solution to this challenge. In particular, we present a multi-task learning framework for temporal and spa…

2021-11-27cs.CVcs.LG