• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Deng, Yongjian (Deng, Yongjian.) | Chen, Hao (Chen, Hao.) | Li, Youfu (Li, Youfu.)

收录:

EI Scopus

摘要:

Recent advances in event-based research prioritize sparsity and temporal precision. Approaches learning sparse point-based representations through graph CNNs (GCN) become more popular. Yet, these graph techniques hold lower performance than their frame-based counterpart due to two issues: (i) Biased graph structures that don’t properly incorporate varied attributes (such as semantics, and spatial and temporal signals) for each vertex, resulting in inaccurate graph representations. (ii) A shortage of robust pretrained models. Here we solve the first problem by proposing a new event-based GCN (EDGCN), with a dynamic aggregation module to integrate all attributes of vertices adaptively. To address the second problem, we introduce a novel learning framework called cross-representation distillation (CRD), which leverages the dense representation of events as a cross-representation auxiliary to provide additional supervision and prior knowledge for the event graph. This frame-to-graph distillation allows us to benefit from the large-scale priors provided by CNNs while still retaining the advantages of graph-based models. Extensive experiments show our model and learning framework are effective and generalize well across multiple vision tasks. © 2024, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

关键词:

Graphic methods Learning systems Artificial intelligence Graph theory Distillation Semantics

作者机构:

  • [ 1 ] [Deng, Yongjian]College of Computer Science, Beijing University of Technology, China
  • [ 2 ] [Deng, Yongjian]Engineering Research Center of Intelligence Perception and Autonomous Control, Ministry of Education, Beijing, China
  • [ 3 ] [Chen, Hao]School of Computer Science and Engineering, Southeast University, China
  • [ 4 ] [Li, Youfu]Department of Mechanical Engineering, City University of Hong Kong, Hong Kong

通讯作者信息:

电子邮件地址:

查看成果更多字段

相关关键词:

相关文章:

来源 :

ISSN: 2159-5399

年份: 2024

期: 2

卷: 38

页码: 1492-1500

语种: 英文

被引次数:

WoS核心集被引频次:

SCOPUS被引频次: 3

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 0

归属院系:

在线人数/总访问数:588/4963826
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司