# DashNet: A Hybrid Artificial and Spiking Neural Network for High-speed Object Tracking

arXiv: https://arxiv.org/abs/1909.12942 · HTML: https://mlsanity.com/paper/1909.12942/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Sep 2019.

## Built on by (most cited first, 19 of 19)

- [VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows](https://mlsanity.com/paper/2108.05015/) (2021)
- [Advancing Spiking Neural Networks towards Deep Residual Learning](https://mlsanity.com/paper/2112.08954/) (2021)
- [Revisiting Color-Event based Tracking: A Unified Network, Dataset, and Metric](https://mlsanity.com/paper/2211.11010/) (2022)
- [TimeReplayer: Unlocking the Potential of Event Cameras for Video Interpolation](https://mlsanity.com/paper/2203.13859/) (2022)
- [ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks](https://mlsanity.com/paper/2110.12211/) (2021)
- [CRSOT: Cross-Resolution Object Tracking using Unaligned Frame and Event Cameras](https://mlsanity.com/paper/2401.02826/) (2024)
- [A Hybrid ANN-SNN Architecture for Low-Power and Low-Latency Visual Perception](https://mlsanity.com/paper/2303.14176/) (2023)
- [SDTrack: A Baseline for Event-based Tracking via Spiking Neural Networks](https://mlsanity.com/paper/2503.08703/) (2025)
- [eMoE-Tracker: Environmental MoE-based Transformer for Robust Event-guided Object Tracking](https://mlsanity.com/paper/2406.20024/) (2024)
- [Reliable Object Tracking by Multimodal Hybrid Feature Extraction and Transformer-Based Fusion](https://mlsanity.com/paper/2405.17903/) (2024)
- [Spiking Generative Adversarial Networks With a Neural Network Discriminator: Local Training, Bayesian Models, and Continual Meta-Learning](https://mlsanity.com/paper/2111.01750/) (2021)
- [Spiking SiamFC++: Deep Spiking Neural Network for Object Tracking](https://mlsanity.com/paper/2209.12010/) (2022)
- [A Spatial-channel-temporal-fused Attention for Spiking Neural Networks](https://mlsanity.com/paper/2209.10837/) (2022)
- [Spiking NeRF: Representing the Real-World Geometry by a Discontinuous Representation](https://mlsanity.com/paper/2311.09077/) (2023)
- [Efficient Event-Based Object Detection: A Hybrid Neural Network with Spatial and Temporal Attention](https://mlsanity.com/paper/2403.10173/) (2024)
- [Spiking Meets Attention: Efficient Remote Sensing Image Super-Resolution with Attention Spiking Neural Networks](https://mlsanity.com/paper/2503.04223/) (2025)
- [Advancing Deep Residual Learning by Solving the Crux of Degradation in Spiking Neural Networks](https://mlsanity.com/paper/2201.07209/) (2021)
- [Spike-TBR: a Noise Resilient Neuromorphic Event Representation](https://mlsanity.com/paper/2506.04817/) (2025)
- [Temporal Misalignment in ANN-SNN Conversion and Its Mitigation via Probabilistic Spiking Neurons](https://mlsanity.com/paper/2502.14487/) (2025)

## Abstract (arXiv)

Computer-science-oriented artificial neural networks (ANNs) have achieved tremendous success in a variety of scenarios via powerful feature extraction and high-precision data operations. It is well known, however, that ANNs usually suffer from expensive processing resources and costs. In contrast, neuroscience-oriented spiking neural networks (SNNs) are promising for energy-efficient information processing benefit from the event-driven spike activities, whereas, they are yet be evidenced to achieve impressive effectiveness on real complicated tasks. How to combine the advantage of these two model families is an open question of great interest. Two significant challenges need to be addressed: (1) lack of benchmark datasets including both ANN-oriented (frames) and SNN-oriented (spikes) signal resources; (2) the difficulty in jointly processing the synchronous activation from ANNs and event-driven spikes from SNNs. In this work, we proposed a hybrid paradigm, named as DashNet, to demonstrate the advantages of combining ANNs and SNNs in a single model. A simulator and benchmark dataset NFS-DAVIS is built, and a temporal complementary filter (TCF) and attention module are designed to address the two mentioned challenges, respectively. In this way, it is shown that DashNet achieves the record-breaking speed of 2083FPS on neuromorphic chips and the best tracking performance on NFS-DAVIS and PRED18 datasets. To the best of our knowledge, DashNet is the first framework that can integrate and process ANNs and SNNs in a hybrid paradigm, which provides a novel solution to achieve both effectiveness and efficiency for high-speed object tracking.