Pith. sign in

REVIEW 1 cited by

A Dynamic Graph CNN with Cross-Representation Distillation for Event-Based Recognition

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2302.04177 v2 pith:6YD7NXP6 submitted 2023-02-08 cs.CV

classification cs.CV
keywords graphcnnscross-representationdistillationevent-basedlearningattributesdense
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Recent advances in event-based research prioritize sparsity and temporal precision. Approaches using dense frame-based representations processed via well-pretrained CNNs are being replaced by the use of sparse point-based representations learned through graph CNNs (GCN). Yet, the efficacy of these graph methods is far behind their frame-based counterparts with two limitations. ($i$) Biased graph construction without carefully integrating variant attributes ($i.e.$, semantics, spatial and temporal cues) for each vertex, leading to imprecise graph representation. ($ii$) Deficient learning because of the lack of well-pretrained models available. 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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Symmetry Understanding of 3D Shapes via Chirality Disentanglement

    cs.CV 2025-08 unverdicted novelty 5.0 of 10

    Abstract-level claim: decorate 3D shape vertices with chirality features drawn from 2D foundation models via Diff3F, enabling left-right disentanglement; the supplied full text is a different paper, so the claim is un...

Pith tools