Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction

• URL: http://arxiv.org/abs/2207.09953v1
• Date: Wed, 20 Jul 2022 14:58:13 GMT
• Title: Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction
• Authors: Inhwan Bae, Jin-Hwi Park, Hae-Gon Jeon
• Abstract summary: GP-Graph has collective group representations for effective pedestrian trajectory prediction in crowded environments. A key idea of GP-Graph is to model both individual-wise and group-wise relations as graph representations. We propose group pooling&unpooling operations to represent a group with multiple pedestrians as one graph node.
• Score: 16.676008193894223
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modeling the dynamics of people walking is a problem of long-standing interest in computer vision. Many previous works involving pedestrian trajectory prediction define a particular set of individual actions to implicitly model group actions. In this paper, we present a novel architecture named GP-Graph which has collective group representations for effective pedestrian trajectory prediction in crowded environments, and is compatible with all types of existing approaches. A key idea of GP-Graph is to model both individual-wise and group-wise relations as graph representations. To do this, GP-Graph first learns to assign each pedestrian into the most likely behavior group. Using this assignment information, GP-Graph then forms both intra- and inter-group interactions as graphs, accounting for human-human relations within a group and group-group relations, respectively. To be specific, for the intra-group interaction, we mask pedestrian graph edges out of an associated group. We also propose group pooling&unpooling operations to represent a group with multiple pedestrians as one graph node. Lastly, GP-Graph infers a probability map for socially-acceptable future trajectories from the integrated features of both group interactions. Moreover, we introduce a group-level latent vector sampling to ensure collective inferences over a set of possible future trajectories. Extensive experiments are conducted to validate the effectiveness of our architecture, which demonstrates consistent performance improvements with publicly available benchmarks. Code is publicly available at https://github.com/inhwanbae/GPGraph.

Related papers

• Skeleton-based Group Activity Recognition via Spatial-Temporal Panoramic Graph [4.075741925017479]
  Group Activity Recognition aims to understand collective activities from videos. Existing solutions rely on the RGB modality, which encounters challenges such as background variations. We design a panoramic graph that incorporates multi-person skeletons and objects to encapsulate group activity.
  arXiv  Detail & Related papers  (2024-07-28T13:57:03Z)
• Learning Long Range Dependencies on Graphs via Random Walks [6.7864586321550595]
  Message-passing graph neural networks (GNNs) excel at capturing local relationships but struggle with long-range dependencies in graphs. graph transformers (GTs) enable global information exchange but often oversimplify the graph structure by representing graphs as sets of fixed-length vectors. This work introduces a novel architecture that overcomes the shortcomings of both approaches by combining the long-range information of random walks with local message passing.
  arXiv  Detail & Related papers  (2024-06-05T15:36:57Z)
• Higher-order Clustering and Pooling for Graph Neural Networks [77.47617360812023]
  Graph Neural Networks achieve state-of-the-art performance on a plethora of graph classification tasks. HoscPool is a clustering-based graph pooling operator that captures higher-order information hierarchically. We evaluate HoscPool on graph classification tasks and its clustering component on graphs with ground-truth community structure.
  arXiv  Detail & Related papers  (2022-09-02T09:17:10Z)
• Similarity-aware Positive Instance Sampling for Graph Contrastive Pre-training [82.68805025636165]
  We propose to select positive graph instances directly from existing graphs in the training set. Our selection is based on certain domain-specific pair-wise similarity measurements. Besides, we develop an adaptive node-level pre-training method to dynamically mask nodes to distribute them evenly in the graph.
  arXiv  Detail & Related papers  (2022-06-23T20:12:51Z)
• CGMN: A Contrastive Graph Matching Network for Self-Supervised Graph Similarity Learning [65.1042892570989]
  We propose a contrastive graph matching network (CGMN) for self-supervised graph similarity learning. We employ two strategies, namely cross-view interaction and cross-graph interaction, for effective node representation learning. We transform node representations into graph-level representations via pooling operations for graph similarity computation.
  arXiv  Detail & Related papers  (2022-05-30T13:20:26Z)
• Graph Representation Learning via Contrasting Cluster Assignments [57.87743170674533]
  We propose a novel unsupervised graph representation model by contrasting cluster assignments, called as GRCCA. It is motivated to make good use of local and global information synthetically through combining clustering algorithms and contrastive learning. GRCCA has strong competitiveness in most tasks.
  arXiv  Detail & Related papers  (2021-12-15T07:28:58Z)
• Graph Neural Netwrok with Interaction Pattern for Group Recommendation [1.066048003460524]
  We propose the model GIP4GR (Graph Neural Network with Interaction Pattern For Group Recommendation) Specifically, our model use the graph neural network framework with powerful representation capabilities to represent the interaction between group-user-items in the topological structure of the graph. We conducted a lot of experiments on two real-world datasets to illustrate the superior performance of our model.
  arXiv  Detail & Related papers  (2021-09-21T13:42:46Z)
• HGCN-GJS: Hierarchical Graph Convolutional Network with Groupwise Joint Sampling for Trajectory Prediction [14.57655217378212]
  In this work, we propose a hierarchical graph convolutional network, HGCN-GJS, for trajectory prediction. We introduce a novel joint sampling scheme for modeling the joint distribution of multiple pedestrians in the future trajectories. We demonstrate the performance of our network on several trajectory prediction datasets, achieving state-of-the-art results on all datasets considered.
  arXiv  Detail & Related papers  (2020-09-15T14:51:10Z)
• Inverse Graph Identification: Can We Identify Node Labels Given Graph Labels? [89.13567439679709]
  Graph Identification (GI) has long been researched in graph learning and is essential in certain applications. This paper defines a novel problem dubbed Inverse Graph Identification (IGI) We propose a simple yet effective method that makes the node-level message passing process using Graph Attention Network (GAT) under the protocol of GI.
  arXiv  Detail & Related papers  (2020-07-12T12:06:17Z)
• Multilevel Graph Matching Networks for Deep Graph Similarity Learning [79.3213351477689]
  We propose a multi-level graph matching network (MGMN) framework for computing the graph similarity between any pair of graph-structured objects. To compensate for the lack of standard benchmark datasets, we have created and collected a set of datasets for both the graph-graph classification and graph-graph regression tasks. Comprehensive experiments demonstrate that MGMN consistently outperforms state-of-the-art baseline models on both the graph-graph classification and graph-graph regression tasks.
  arXiv  Detail & Related papers  (2020-07-08T19:48:19Z)
• CoMoGCN: Coherent Motion Aware Trajectory Prediction with Graph Representation [12.580809204729583]
  We propose a novel framework, coherent motion aware graph convolutional network (CoMoGCN), for trajectory prediction in crowded scenes with group constraints. Our method achieves state-of-the-art performance on several different trajectory prediction benchmarks, and the best average performance among all benchmarks considered.
  arXiv  Detail & Related papers  (2020-05-02T09:10:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.