Uncertainty-aware Bridge based Mobile-Former Network for Event-based Pattern Recognition
Not on the map. Why?
Abstract (arXiv)
The mainstream human activity recognition (HAR) algorithms are developed based on RGB cameras, which are easily influenced by low-quality images (e.g., low illumination, motion blur). Meanwhile, the privacy protection issue caused by ultra-high definition (HD) RGB cameras aroused more and more people's attention. Inspired by the success of event cameras which perform better on high dynamic range, no motion blur, and low energy consumption, we propose to recognize human actions based on the event stream. We propose a lightweight uncertainty-aware information propagation based Mobile-Former network for efficient pattern recognition, which aggregates the MobileNet and Transformer network effectively. Specifically, we first embed the event images using a stem network into feature representations, then, feed them into uncertainty-aware Mobile-Former blocks for local and global feature learning and fusion. Finally, the features from MobileNet and Transformer branches are concatenated for pattern recognition. Extensive experiments on multiple event-based recognition datasets fully validated the effectiveness of our model. The source code of this work will be released at https://github.com/Event-AHU/Uncertainty_aware_MobileFormer.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 27 of its 49 references that are in the map. First posted on arXiv 20 Jan 2024.
Builds on
27 of 49 references.
References · 27
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
- 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
- 2019Event-based Vision: A Surveycited by 1,016
- 2021Transformers in Vision: A Surveycited by 1,013
- 2015Variational Dropout and the Local Reparameterization Trickcited by 490
- 2016Tutorial on Variational Autoencoderscited by 409
- 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 345
- 2021Deep Residual Learning in Spiking Neural Networkscited by 331
- 2015Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccadescited by 314
- 2021Mobile-Former: Bridging MobileNet and Transformercited by 235
- 2018Human Action Recognition and Prediction: A Surveycited by 227
15 more
- 2018HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classificationcited by 218
- 2019End-to-End Learning of Representations for Asynchronous Event-Based Datacited by 217
- 2020Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wildcited by 134
- 2021VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flowscited by 129
- 2022Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representationcited by 89
- 2019Graph-Based Object Classification for Neuromorphic Vision Sensingcited by 85
- 2021Time-Ordered Recent Event (TORE) Volumes for Event Camerascited by 73
- 2018EventNet: Asynchronous Recursive Event Processingcited by 58
- 2021Sparse Spiking Gradient Descentcited by 41
- 2020Exploiting Neuron and Synapse Filter Dynamics in Spatial Temporal Learning of Deep Spiking Neural Networkcited by 37
- 2022Uncertainty-aware Label Distribution Learning for Facial Expression Recognitioncited by 30
- 2021Representation Learning for Event-based Visuomotor Policiescited by 20
- 2023SSTFormer: Bridging Spiking Neural Network and Memory Support Transformer for Frame-Event based Recognitioncited by 20
- 2021Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identificationcited by 15
- 2023Unleashing the Power of CNN and Transformer for Balanced RGB-Event Video Recognitioncited by 5
Built on by
Citing papers per year: 2024: 1.
1 paper.