Filters








4,139 Hits in 8.1 sec

Trajectory Prediction with Graph-based Dual-scale Context Fusion [article]

Lu Zhang, Peiliang Li, Jing Chen, Shaojie Shen
2022 arXiv   pre-print
In this paper, we present a graph-based trajectory prediction network named the Dual Scale Predictor (DSP), which encodes both the static and dynamical driving context in a hierarchical manner.  ...  Thanks to the proposed dual-scale context fusion network, our DSP is able to generate accurate and human-like multi-modal trajectories.  ...  To address the issue, we present a graph-based trajectory prediction network named the Dual Scale Predictor (DSP).  ... 
arXiv:2111.01592v2 fatcat:v4zhbtthtvh6vkesosrxd5fb7u

ICDE conference 2015 detailed author index

2015 2015 IEEE 31st International Conference on Data Engineering  
Model for Recommendation in Event-Based Social Networks Li, Yanhua 1376 Growing the Charging Station Network for Electric Vehicles with Trajectory Data Analytics Li, Youhuan 1508 A Graph-Based  ...  Trajectory Data Analytics Christensen, Kenneth Fuglsang 687 Searchlight: Context-Aware Predictive Continuous Querying of Moving Objects in Symbolic Space Christiansen, Lasse Linnerup 687 Searchlight  ... 
doi:10.1109/icde.2015.7113260 fatcat:ep7pomkm55f45j33tkpoc5asim

Dual Subgraph-based Graph Neural Network for Friendship Prediction in Location-Based Social Networks

Xuemei Wei, Yezheng Liu, Jianshan Sun, Yuanchun Jiang, Qifeng Tang, Kun Yuan
2022 ACM Transactions on Knowledge Discovery from Data  
In this regard, we propose a dual subgraph-based pairwise graph neural network (DSGNN) for friendship prediction in LBSNs, which extracts a pairwise social subgraph and a trajectory subgraph to model the  ...  With the wide use of Location-Based Social Networks (LBSNs), predicting user friendship from online social relations and offline trajectory data is of great value to improve the platform service quality  ...  subgraph structure with dual GNNs.  ... 
doi:10.1145/3554981 fatcat:pvvxbb72bvb2pnkmv5bd56wjk4

TPCN: Temporal Point Cloud Networks for Motion Forecasting [article]

Maosheng Ye, Tongyi Cao, Qifeng Chen
2021 arXiv   pre-print
We propose the Temporal Point Cloud Networks (TPCN), a novel and flexible framework with joint spatial and temporal learning for trajectory prediction.  ...  to capture both spatial and temporal information by splitting trajectory prediction into both spatial and temporal dimensions.  ...  Dual-representation Fusion. With pointwise and voxelwise features, we fuse these two types of features by feature concatenation.  ... 
arXiv:2103.03067v1 fatcat:iurux366xzb6vihcuyj3ucbbhm

Is an Object-Centric Video Representation Beneficial for Transfer? [article]

Chuhan Zhang, Ankush Gupta, Andrew Zisserman
2022 arXiv   pre-print
To this end, we introduce a new object-centric video recognition model based on a transformer architecture.  ...  We also introduce a novel trajectory contrast loss to further enhance objectness in these summary vectors.  ...  We adopt STLT's hierarchical trajectory encoder, and develop a more performant cross-attention based fusion method. Multi-modal fusion.  ... 
arXiv:2207.10075v1 fatcat:3xmj55mrajhuzczaprlf5hvf64

Graph Convolutional Networks for Road Networks

Tobias Skovgaard Jepsen, Christian S. Jensen, Thomas Dyhre Nielsen
2019 Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems - SIGSPATIAL '19  
In road networks, prediction tasks concern edges representing road segments, and many tasks involve regression.  ...  We introduce the notion of Relational Fusion Network (RFN), a novel type of GCN designed specifically for machine learning on road networks.  ...  With K layers, the relational fusion operators in the nodeand edge-relational views aggregate information up to a distance K from nodes in the primal graph and edges in the dual graph, respectively.  ... 
doi:10.1145/3347146.3359094 dblp:conf/gis/JepsenJN19 fatcat:s6cvzxuporg4perriir3ios7uu

Crowd Flow Prediction for Irregular Regions with Semantic Graph Attention Network

Fuxian Li, Jie Feng, Huan Yan, Depeng Jin, Yong Li
2022 ACM Transactions on Intelligent Systems and Technology  
However, prior works mainly focus on grid-based crowd flow prediction, where a city is divided into many regular grids.  ...  Further, we think highly of the dynamic inter-region correlations and propose a location-aware and time-aware graph attention mechanism named Semantic Graph Attention Network (Semantic-GAT), based on dynamic  ...  -DCRNN [9]: This is a GNN-based and RNN-based model which integrates GRU with dual directional diffusion convolution.  ... 
doi:10.1145/3501805 fatcat:bptqckhd4vb4ffhb7beg6sny5m

ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning [article]

Shengchao Hu and Li Chen and Penghao Wu and Hongyang Li and Junchi Yan and Dacheng Tao
2022 arXiv   pre-print
devised to take past motion variations into account for future prediction; a temporal-based refinement unit is introduced to compensate for recognizing vision-based elements for planning.  ...  Specifically, an egocentric-aligned accumulation technique is proposed to preserve geometry information in 3D space before the bird's eye view transformation for perception; a dual pathway modeling is  ...  Exp.4-6 is on prediction module, with "Dual." representing Dual Modelling and "LFA." indicating loss for all timestamps.  ... 
arXiv:2207.07601v2 fatcat:gyj67ir7x5avfk3i2fahhb2hpu

Crowd understanding and analysis

Qi Wang, Bo Liu, Jianzhe Lin
2021 IET Image Processing  
With the development of modern life, all kinds of social activities have become more frequent.  ...  It accelerates the pedestrian trajectory prediction training process of spatiotemporal graph transformer networks.  ...  as appearance, scale, and context.  ... 
doi:10.1049/ipr2.12379 fatcat:shshhjjoxngotplvg7xzefpsne

Relational Fusion Networks: Graph Convolutional Networks for Road Networks [article]

Tobias Skovgaard Jepsen, Christian S. Jensen, Thomas Dyhre Nielsen
2020 arXiv   pre-print
We introduce the Relational Fusion Network (RFN), a novel type of GCN designed specifically for road networks.  ...  Graph Convolutional Networks (GCNs) are neural networks that are capable of leveraging the structure of a network. However, many implicit assumptions of GCNs do not apply to road networks.  ...  All authors are affiliated with the Department of Computer Science at Aalborg University, Denmark. Manuscript received by ...  ... 
arXiv:2006.09030v1 fatcat:lizutmknm5fwfczwtchsdpkfbq

A Review of Tracking and Trajectory Prediction Methods for Autonomous Driving

Florin Leon, Marius Gavrilescu
2021 Mathematics  
., identifying pedestrians, cars or obstacles from images, observations or sensor data, and prediction, i.e., anticipating the future trajectories and motion of other vehicles in order to facilitate navigating  ...  Approaches based on deep neural networks and others, especially stochastic techniques, are reported.  ...  In the domain of trajectory prediction, Social GAN [118] uses a GAN where the generator is composed of an LSTM-based encoder, a context-pooling module, and an LSTM-based decoder.  ... 
doi:10.3390/math9060660 fatcat:qvikrr32tzd7fnjzs22u3ago4m

Learning to Drive Off Road on Smooth Terrain in Unstructured Environments Using an On-Board Camera and Sparse Aerial Images [article]

Travis Manderson, Stefan Wapnick, David Meger, Gregory Dudek
2020 arXiv   pre-print
Our results show the ability to generalize to environments with plentiful vegetation, various types of rock, and sandy trails.  ...  We find that the fusion of these complementary inputs improves planning foresight and makes the model robust to visual obstructions.  ...  Fig. 4 shows sample trajectories generated by the fusion model.  ... 
arXiv:2004.04697v1 fatcat:vpzlpsl2czcwvilh3z3blirore

Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies [article]

Yu Huang, Yue Chen
2020 arXiv   pre-print
level respectively, behavior modelling and prediction of vehicle driving and pedestrian trajectories.  ...  This is a survey of autonomous driving technologies with deep learning methods.  ...  also applies ST-graph (edge LSTM and node LSTM) for trajectory prediction.  ... 
arXiv:2006.06091v3 fatcat:nhdgivmtrzcarp463xzqvnxlwq

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
Li, K., +, TIP 2020 3311-3320 Visual Tracking With Multiview Trajectory Prediction.  ...  Dhiman, C., +, TIP 2020 3835-3844 Visual Tracking With Multiview Trajectory Prediction.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

A Dual-Masked Auto-Encoder for Robust Motion Capture with Spatial-Temporal Skeletal Token Completion [article]

Junkun Jiang, Jie Chen, Yike Guo
2022 arXiv   pre-print
To generate complete 3D skeletal motion, we then propose a Dual-Masked Auto-Encoder (D-MAE) which encodes the joint status with both skeletal-structural and temporal position encoding for trajectory completion  ...  In order to demonstrate the proposed model's capability in dealing with severe data loss scenarios, we contribute a high-accuracy and challenging motion capture dataset of multi-person interactions with  ...  ACKNOWLEDGMENTS The research was supported by the Theme-based Research Scheme, Research Grants Council of Hong Kong (T45-205/21-N).  ... 
arXiv:2207.07381v1 fatcat:kdsltgxavrbphknqfr6rnvbatu
« Previous Showing results 1 — 15 out of 4,139 results