EHGCN: Hierarchical Euclidean-Hyperbolic Fusion via Motion-Aware GCN for Hybrid Event Stream Perception

2025-04-23

AI Summary

To address the challenge of modeling long-range dependencies and intrinsic hierarchical structures of event streams in Euclidean space, this paper proposes the first Euclidean–hyperbolic hybrid event-aware framework. Methodologically: (1) a motion-aware hypergraph is constructed, where dynamic hyperedges are generated by a Markovian vector field; (2) an adaptive event sampling strategy is designed to suppress noise while preserving discriminative events; (3) Euclidean graph convolution is jointly optimized with hyperbolic embedding to enable heterogeneous graph fusion and hierarchical representation learning. Evaluated on event-driven object detection and recognition tasks, the framework significantly outperforms existing GNN-based approaches. It achieves breakthrough improvements in both long-range relational modeling capability and noise-robustness, demonstrating superior generalization under sparse and noisy event data.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Computer Vision: Motion & Tracking
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Event cameras, with microsecond temporal resolution and high dynamic range (HDR) characteristics, emit high-speed event stream for perception tasks. Despite the recent advancement in GNN-based perception methods, they are prone to use straightforward pairwise connectivity mechanisms in the pure Euclidean space where they struggle to capture long-range dependencies and fail to effectively characterize the inherent hierarchical structures of non-uniformly distributed event stream. To this end, in this paper we propose a novel approach named EHGCN, which is a pioneer to perceive event stream in both Euclidean and hyperbolic spaces for event vision. In EHGCN, we introduce an adaptive sampling strategy to dynamically regulate sampling rates, retaining discriminative events while attenuating chaotic noise. Then we present a Markov Vector Field (MVF)-driven motion-aware hyperedge generation method based on motion state transition probabilities, thereby eliminating cross-target spurious associations and providing critically topological priors while capturing long-range dependencies between events. Finally, we propose a Euclidean-Hyperbolic GCN to fuse the information locally aggregated and globally hierarchically modeled in Euclidean and hyperbolic spaces, respectively, to achieve hybrid event perception. Experimental results on event perception tasks such as object detection and recognition validate the effectiveness of our approach.

Problem

• Captures long-range dependencies in event streams
• Models hierarchical structures in non-uniform event data
• Reduces noise and spurious associations in event perception

Innovation

• Adaptive sampling strategy for discriminative events
• Motion-aware hyperedge generation using Markov Vector Field
• Euclidean-Hyperbolic GCN for hybrid event perception