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

arXiv: https://arxiv.org/abs/2302.04177 · HTML: https://mlsanity.com/paper/2302.04177/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 54 references that are in the map.
- First posted on arXiv 8 Feb 2023.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [High Speed and High Dynamic Range Video with an Event Camera](https://mlsanity.com/paper/1906.07165/) (2019)
- [Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades](https://mlsanity.com/paper/1507.07629/) (2015)
- [HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classification](https://mlsanity.com/paper/1803.07913/) (2018)
- [End-to-End Learning of Representations for Asynchronous Event-Based Data](https://mlsanity.com/paper/1904.08245/) (2019)
- [Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds](https://mlsanity.com/paper/2109.00179/) (2021)
- [Video to Events: Recycling Video Datasets for Event Cameras](https://mlsanity.com/paper/1912.03095/) (2019)
- [AEGNN: Asynchronous Event-based Graph Neural Networks](https://mlsanity.com/paper/2203.17149/) (2022)
- [Time Lens++: Event-based Frame Interpolation with Parametric Non-linear Flow and Multi-scale Fusion](https://mlsanity.com/paper/2203.17191/) (2022)
- [Temporal-wise Attention Spiking Neural Networks for Event Streams Classification](https://mlsanity.com/paper/2107.11711/) (2021)
- [Event-based Asynchronous Sparse Convolutional Networks](https://mlsanity.com/paper/2003.09148/) (2020)
- [Self-Supervised Learning of Event-Based Optical Flow with Spiking Neural Networks](https://mlsanity.com/paper/2106.01862/) (2021)
- [ESS: Learning Event-based Semantic Segmentation from Still Images](https://mlsanity.com/paper/2203.10016/) (2022)
- [Time-Ordered Recent Event (TORE) Volumes for Event Cameras](https://mlsanity.com/paper/2103.06108/) (2021)
- [Event-based Video Reconstruction via Potential-assisted Spiking Neural Network](https://mlsanity.com/paper/2201.10943/) (2022)
- [EventNet: Asynchronous Recursive Event Processing](https://mlsanity.com/paper/1812.07045/) (2018)
- [Asynchronous Convolutional Networks for Object Detection in Neuromorphic Cameras](https://mlsanity.com/paper/1805.07931/) (2018)
- [LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing](https://mlsanity.com/paper/2011.06176/) (2020)
- [HFirst: A Temporal Approach to Object Recognition](https://mlsanity.com/paper/1508.01176/) (2015)
- [Deep Analysis of CNN-based Spatio-temporal Representations for Action Recognition](https://mlsanity.com/paper/2010.11757/) (2020)
- [EventSR: From Asynchronous Events to Image Reconstruction, Restoration, and Super-Resolution via End-to-End Adversarial Learning](https://mlsanity.com/paper/2003.07640/) (2020)
- [A Voxel Graph CNN for Object Classification with Event Cameras](https://mlsanity.com/paper/2106.00216/) (2021)

## Built on by (most cited first, 7 of 7)

- [Spatially-guided Temporal Aggregation for Robust Event-RGB Optical Flow Estimation](https://mlsanity.com/paper/2501.00838/) (2025)
- [Retain, Blend, and Exchange: A Quality-aware Spatial-Stereo Fusion Approach for Event Stream Recognition](https://mlsanity.com/paper/2406.18845/) (2024)
- [Scalable Event Cloud Network for Event-based Classification](https://mlsanity.com/paper/2412.20803/) (2024)
- [Event-based Graph Representation with Spatial and Motion Vectors for Asynchronous Object Detection](https://mlsanity.com/paper/2507.15150/) (2025)
- [PASS: Path-selective State Space Model for Event-based Recognition](https://mlsanity.com/paper/2409.16953/) (2024)
- [EHGCN: Hierarchical Euclidean-Hyperbolic Fusion via Motion-Aware GCN for Hybrid Event Stream Perception](https://mlsanity.com/paper/2504.16616/) (2025)
- [SMV-EAR: Bring Spatiotemporal Multi-View Representation Learning into Efficient Event-Based Action Recognition](https://mlsanity.com/paper/2601.17391/) (2026)

## Abstract (arXiv)

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.