Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Meisen, Deng, Hao, Bao, Wei, Yuanxiao, Ma, Wang, Chengjie, Tian, Zhiqiang, Du, Shaoyi, Li, Siqi
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2605.08825
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916012455100416
author Wang, Meisen
Deng, Hao
Bao, Wei
Yuanxiao, Ma
Wang, Chengjie
Tian, Zhiqiang
Du, Shaoyi
Li, Siqi
author_facet Wang, Meisen
Deng, Hao
Bao, Wei
Yuanxiao, Ma
Wang, Chengjie
Tian, Zhiqiang
Du, Shaoyi
Li, Siqi
contents Event cameras provide microsecond-level temporal resolution, low latency, and high dynamic range, offering potential for perception under fast motion and challenging illumination conditions. However, existing Event-based Object Detection (EOD) methods face limitations at both the representation and model levels: prior event representations usually encode temporal information indirectly through redundant structures, while detection models struggle to explicitly aggregate fragmented event responses into coherent high-order object features. To address these limitations, we present Event Dual Temporal-Relational Aggregation Detector (Ev-DTAD), a unified EOD framework that integrates representation-level temporal encoding with model-level temporal-hypergraph reasoning. Specifically, we introduce Hierarchical Temporal Aggregation (HTA), a compact three-channel pseudo-RGB representation that explicitly embeds temporal information across intra- and inter-window events. To further enhance detection under sparse and fragmented event responses, we propose Frequency-aware Hypergraph Temporal Fusion (FHTF), which refines multi-scale event features through temporal evolution modeling and high-order relational reasoning. Extensive experiments on Gen1 (+0.8 mAP and 1.7$\times$ faster), 1Mpx/Gen4 (+0.5 mAP and 1.6$\times$ faster), and eTraM (+3.0 mAP and 2.0$\times$ faster) demonstrate that Ev-DTAD achieves a competitive accuracy-efficiency trade-off, validating the complementarity between compact temporal representation and temporal-hypergraph feature reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2605_08825
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Rethinking Event-Based Object Dtection through Representation-Level Temporal Aggregation and Model-Level Hypergraph Reasoning
Wang, Meisen
Deng, Hao
Bao, Wei
Yuanxiao, Ma
Wang, Chengjie
Tian, Zhiqiang
Du, Shaoyi
Li, Siqi
Computer Vision and Pattern Recognition
Event cameras provide microsecond-level temporal resolution, low latency, and high dynamic range, offering potential for perception under fast motion and challenging illumination conditions. However, existing Event-based Object Detection (EOD) methods face limitations at both the representation and model levels: prior event representations usually encode temporal information indirectly through redundant structures, while detection models struggle to explicitly aggregate fragmented event responses into coherent high-order object features. To address these limitations, we present Event Dual Temporal-Relational Aggregation Detector (Ev-DTAD), a unified EOD framework that integrates representation-level temporal encoding with model-level temporal-hypergraph reasoning. Specifically, we introduce Hierarchical Temporal Aggregation (HTA), a compact three-channel pseudo-RGB representation that explicitly embeds temporal information across intra- and inter-window events. To further enhance detection under sparse and fragmented event responses, we propose Frequency-aware Hypergraph Temporal Fusion (FHTF), which refines multi-scale event features through temporal evolution modeling and high-order relational reasoning. Extensive experiments on Gen1 (+0.8 mAP and 1.7$\times$ faster), 1Mpx/Gen4 (+0.5 mAP and 1.6$\times$ faster), and eTraM (+3.0 mAP and 2.0$\times$ faster) demonstrate that Ev-DTAD achieves a competitive accuracy-efficiency trade-off, validating the complementarity between compact temporal representation and temporal-hypergraph feature reasoning.
title Rethinking Event-Based Object Dtection through Representation-Level Temporal Aggregation and Model-Level Hypergraph Reasoning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.08825