Event Voxel Set Transformer for Spatiotemporal Representation Learning on Event Streams

• URL: http://arxiv.org/abs/2303.03856v3
• Date: Mon, 2 Sep 2024 03:56:06 GMT
• Title: Event Voxel Set Transformer for Spatiotemporal Representation Learning on Event Streams
• Authors: Bochen Xie, Yongjian Deng, Zhanpeng Shao, Qingsong Xu, Youfu Li,
• Abstract summary: Event cameras are neuromorphic vision sensors that record a scene as sparse and asynchronous event streams. We propose an attentionaware model named Event Voxel Set Transformer (EVSTr) for efficient representation learning on event streams. Experiments show that EVSTr achieves state-of-the-art performance while maintaining low model complexity.
• Score: 19.957857885844838
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Event cameras are neuromorphic vision sensors that record a scene as sparse and asynchronous event streams. Most event-based methods project events into dense frames and process them using conventional vision models, resulting in high computational complexity. A recent trend is to develop point-based networks that achieve efficient event processing by learning sparse representations. However, existing works may lack robust local information aggregators and effective feature interaction operations, thus limiting their modeling capabilities. To this end, we propose an attention-aware model named Event Voxel Set Transformer (EVSTr) for efficient spatiotemporal representation learning on event streams. It first converts the event stream into voxel sets and then hierarchically aggregates voxel features to obtain robust representations. The core of EVSTr is an event voxel transformer encoder that consists of two well-designed components, including the Multi-Scale Neighbor Embedding Layer (MNEL) for local information aggregation and the Voxel Self-Attention Layer (VSAL) for global feature interaction. Enabling the network to incorporate a long-range temporal structure, we introduce a segment modeling strategy (S$^{2}$TM) to learn motion patterns from a sequence of segmented voxel sets. The proposed model is evaluated on two recognition tasks, including object classification and action recognition. To provide a convincing model evaluation, we present a new event-based action recognition dataset (NeuroHAR) recorded in challenging scenarios. Comprehensive experiments show that EVSTr achieves state-of-the-art performance while maintaining low model complexity.

Related papers

• A dynamic vision sensor object recognition model based on trainable event-driven convolution and spiking attention mechanism [9.745798797360886]
  Spiking Neural Networks (SNNs) are well-suited for processing event streams from Dynamic Visual Sensors (DVSs) To extract features from DVS objects, SNNs commonly use event-driven convolution with fixed kernel parameters. We propose a DVS object recognition model that utilizes a trainable event-driven convolution and a spiking attention mechanism.
  arXiv  Detail & Related papers  (2024-09-19T12:01:05Z)
• Retain, Blend, and Exchange: A Quality-aware Spatial-Stereo Fusion Approach for Event Stream Recognition [57.74076383449153]
  We propose a novel dual-stream framework for event stream-based pattern recognition via differentiated fusion, termed EFV++. It models two common event representations simultaneously, i.e., event images and event voxels. We achieve new state-of-the-art performance on the Bullying10k dataset, i.e., $90.51%$, which exceeds the second place by $+2.21%$.
  arXiv  Detail & Related papers  (2024-06-27T02:32:46Z)
• GET: Group Event Transformer for Event-Based Vision [82.312736707534]
  Event cameras are a type of novel neuromorphic sen-sor that has been gaining increasing attention. We propose a novel Group-based vision Transformer backbone for Event-based vision, called Group Event Transformer (GET) GET de-couples temporal-polarity information from spatial infor-mation throughout the feature extraction process.
  arXiv  Detail & Related papers  (2023-10-04T08:02:33Z)
• EventTransAct: A video transformer-based framework for Event-camera based action recognition [52.537021302246664]
  Event cameras offer new opportunities compared to standard action recognition in RGB videos. In this study, we employ a computationally efficient model, namely the video transformer network (VTN), which initially acquires spatial embeddings per event-frame. In order to better adopt the VTN for the sparse and fine-grained nature of event data, we design Event-Contrastive Loss ($mathcalL_EC$) and event-specific augmentations.
  arXiv  Detail & Related papers  (2023-08-25T23:51:07Z)
• Learning Bottleneck Transformer for Event Image-Voxel Feature Fusion based Classification [6.550582412924754]
  This paper proposes a novel dual-stream framework for event representation, extraction, and fusion. Experiments demonstrate that our proposed framework achieves state-of-the-art performance on two widely used event-based classification datasets.
  arXiv  Detail & Related papers  (2023-08-23T06:07:56Z)
• Dual Memory Aggregation Network for Event-Based Object Detection with Learnable Representation [79.02808071245634]
  Event-based cameras are bio-inspired sensors that capture brightness change of every pixel in an asynchronous manner. Event streams are divided into grids in the x-y-t coordinates for both positive and negative polarity, producing a set of pillars as 3D tensor representation. Long memory is encoded in the hidden state of adaptive convLSTMs while short memory is modeled by computing spatial-temporal correlation between event pillars.
  arXiv  Detail & Related papers  (2023-03-17T12:12:41Z)
• EAN: Event Adaptive Network for Enhanced Action Recognition [66.81780707955852]
  We propose a unified action recognition framework to investigate the dynamic nature of video content. First, when extracting local cues, we generate the spatial-temporal kernels of dynamic-scale to adaptively fit the diverse events. Second, to accurately aggregate these cues into a global video representation, we propose to mine the interactions only among a few selected foreground objects by a Transformer.
  arXiv  Detail & Related papers  (2021-07-22T15:57:18Z)
• EV-VGCNN: A Voxel Graph CNN for Event-based Object Classification [18.154951807178943]
  Event cameras report sparse intensity changes and hold noticeable advantages of low power consumption, high dynamic range, and high response speed for visual perception and understanding on portable devices. Event-based learning methods have recently achieved massive success on object recognition by integrating events into dense frame-based representations to apply traditional 2D learning algorithms. These approaches introduce much redundant information during the sparse-to-dense conversion and necessitate models with heavy-weight and large capacities, limiting the potential of event cameras on real-life applications.
  arXiv  Detail & Related papers  (2021-06-01T04:07:03Z)
• Superevents: Towards Native Semantic Segmentation for Event-based Cameras [13.099264910430986]
  Most successful computer vision models transform low-level features, such as Gabor filter responses, into richer representations of intermediate or mid-level complexity for downstream visual tasks. We present a novel method that employs lifetime augmentation for obtaining an event stream representation that is fed to a fully convolutional network to extract superevents.
  arXiv  Detail & Related papers  (2021-05-13T05:49:41Z)
• Event-based Asynchronous Sparse Convolutional Networks [54.094244806123235]
  Event cameras are bio-inspired sensors that respond to per-pixel brightness changes in the form of asynchronous and sparse "events" We present a general framework for converting models trained on synchronous image-like event representations into asynchronous models with identical output. We show both theoretically and experimentally that this drastically reduces the computational complexity and latency of high-capacity, synchronous neural networks.
  arXiv  Detail & Related papers  (2020-03-20T08:39:49Z)
• A Differentiable Recurrent Surface for Asynchronous Event-Based Data [19.605628378366667]
  We propose Matrix-LSTM, a grid of Long Short-Term Memory (LSTM) cells that efficiently process events and learn end-to-end task-dependent event-surfaces. Compared to existing reconstruction approaches, our learned event-surface shows good flexibility and on optical flow estimation. It improves the state-of-the-art of event-based object classification on the N-Cars dataset.
  arXiv  Detail & Related papers  (2020-01-10T14:09:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.