mlsanityData to 7 Oct 2026

E2(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition

arXiv 2112.03596 ↗First posted 7 Dec 2021cs.CVcited by 50

Not on the map. Why?

Abstract (arXiv)

Event cameras are novel bio-inspired sensors, which asynchronously capture pixel-level intensity changes in the form of "events". Due to their sensing mechanism, event cameras have little to no motion blur, a very high temporal resolution and require significantly less power and memory than traditional frame-based cameras. These characteristics make them a perfect fit to several real-world applications such as egocentric action recognition on wearable devices, where fast camera motion and limited power challenge traditional vision sensors. However, the ever-growing field of event-based vision has, to date, overlooked the potential of event cameras in such applications. In this paper, we show that event data is a very valuable modality for egocentric action recognition. To do so, we introduce N-EPIC-Kitchens, the first event-based camera extension of the large-scale EPIC-Kitchens dataset. In this context, we propose two strategies: (i) directly processing event-camera data with traditional video-processing architectures (E2(GO)) and (ii) using event-data to distill optical flow information (E2(GO)MO). On our proposed benchmark, we show that event data provides a comparable performance to RGB and optical flow, yet without any additional flow computation at deploy time, and an improved performance of up to 4% with respect to RGB only information.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). Builds on 73 of its 114 references that are in the map. First posted on arXiv 7 Dec 2021.

Builds on

73 of 114 references.

References · 73

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  5. 2017Squeeze-and-Excitation Networkscited by 4,763
  6. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  7. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
  8. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  9. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
  10. 2019Event-based Vision: A Surveycited by 1,010
  11. 2021Scaling Vision Transformerscited by 993
  12. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
38 more
  1. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 899
  2. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 852
  3. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 789
  4. 2020X3D: Expanding Architectures for Efficient Video Recognitioncited by 635
  5. 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 566
  6. 2020Rescaling Egocentric Visioncited by 529
  7. 2017Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classificationcited by 521
  8. 2014Long-term Recurrent Convolutional Networks for Visual Recognition and Descriptioncited by 483
  9. 2017Learning Spatio-Temporal Representation with Pseudo-3D Residual Networkscited by 386
  10. 2020Meta Pseudo Labelscited by 372
  11. 2017Temporal Relational Reasoning in Videoscited by 324
  12. 2017Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolationcited by 321
  13. 2018Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotioncited by 304
  14. 2021DSEC: A Stereo Event Camera Dataset for Driving Scenarioscited by 297
  15. 2019Video Classification with Channel-Separated Convolutional Networkscited by 290
  16. 2017Temporal Segment Networks for Action Recognition in Videoscited by 279
  17. 2017First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotationscited by 229
  18. 2019EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognitioncited by 226
  19. 2019End-to-End Learning of Representations for Asynchronous Event-Based Datacited by 216
  20. 2018HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classificationcited by 215
  21. 2021Anticipative Video Transformercited by 197
  22. 2020Learning to Detect Objects with a 1 Megapixel Event Cameracited by 184
  23. 2019Video to Events: Recycling Video Datasets for Event Camerascited by 162
  24. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  25. 2021TimeLens: Event-based Video Frame Interpolationcited by 150
  26. 2021E-RAFT: Dense Optical Flow from Event Camerascited by 149
  27. 2020Rolling-Unrolling LSTMs for Action Anticipation from First-Person Videocited by 119
  28. 2020Multi-Modal Domain Adaptation for Fine-Grained Action Recognitioncited by 115
  29. 2020A Large Scale Event-based Detection Dataset for Automotivecited by 108
  30. 2018When will you do what? - Anticipating Temporal Occurrences of Activitiescited by 106
  31. 2020Event-based Asynchronous Sparse Convolutional Networkscited by 103
  32. 2019Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statisticscited by 92
  33. 2021N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Camerascited by 91
  34. 2021Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Predictioncited by 88
  35. 2020Learning Monocular Dense Depth from Eventscited by 84
  36. 2017Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognitioncited by 82
  37. 2019Event-Based Motion Segmentation by Motion Compensationcited by 78
  38. 2020In the Eye of the Beholder: Gaze and Actions in First Person Videocited by 68

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 8; 2023: 6; 2024: 13; 2025: 14; 2026: 9.

50 papers.

Sort:

By area:

  1. 2024EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real Worldcited by 93
  2. 2025EgoLife: Towards Egocentric Life Assistantcited by 86
  3. 2023An Outlook into the Future of Egocentric Visioncited by 84
  4. 2024Recent Event Camera Innovations: A Surveycited by 67
  5. 2022Masked Event Modeling: Self-Supervised Pretraining for Event Camerascited by 40
  6. 2024ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and Morecited by 33
  7. 2023EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understandingcited by 32
  8. 2025Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learningcited by 20
  9. 2025Challenges and Trends in Egocentric Vision: A Surveycited by 20
  10. 2024Hypergraph-based Multi-View Action Recognition using Event Camerascited by 19
  11. 2023Instance Tracking in 3D Scenes from Egocentric Videoscited by 17
  12. 20233D Pose Estimation of Two Interacting Hands from a Monocular Event Cameracited by 17
38 more
  1. 2024Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognitioncited by 14
  2. 2024Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithmscited by 11
  3. 2023EventTransAct: A video transformer-based framework for Event-camera based action recognitioncited by 10
  4. 2023Event-Free Moving Object Segmentation from Moving Ego Vehiclecited by 8
  5. 2024GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognitioncited by 8
  6. 2024Language Model Guided Interpretable Video Action Reasoningcited by 8
  7. 2024EMAG: Ego-motion Aware and Generalizable 2D Hand Forecasting from Egocentric Videoscited by 8
  8. 2025An Egocentric Vision-Language Model based Portable Real-time Smart Assistantcited by 7
  9. 2024Egocentric zone-aware action recognition across environmentscited by 6
  10. 2025Bootstrap Your Own Views: Masked Ego-Exo Modeling for Fine-grained View-invariant Video Representationscited by 6
  11. 2025EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perceptioncited by 4
  12. 2025SkillSight: Efficient First-Person Skill Assessment with Gazecited by 4
  13. 2022Improving Transfer Learning with a Dual Image and Video Transformer for Multi-label Movie Trailer Genre Classificationcited by 3
  14. 2025EgoEvGesture: Gesture Recognition Based on Egocentric Event Cameracited by 3
  15. 2022Event-based Stereo Depth Estimation from Ego-motion using Ray Density Fusioncited by 2
  16. 2022Adversarially Robust Video Perception by Seeing Motioncited by 2
  17. 2024Integrating Audio Narrations to Strengthen Domain Generalization in Multimodal First-Person Action Recognitioncited by 2
  18. 2025Event-based Solutions for Human-centered Applications: A Comprehensive Reviewcited by 2
  19. 2025Neural Ganglion Sensors: Learning Task-specific Event Cameras Inspired by the Neural Circuit of the Human Retinacited by 2
  20. 2025Reading in the Dark with Foveated Event Visioncited by 2
  21. 2026EgoEV-HandPose: Egocentric 3D Hand Pose Estimation and Gesture Recognition with Stereo Event Camerascited by 2
  22. 2026Vinci2: Providing Proactive Assistance in Continuous Egocentric Videoscited by 2
  23. 2022Bringing Online Egocentric Action Recognition into the wildcited by 1
  24. 2025Raw2Event: Converting Raw Frame Camera into Event Cameracited by 1
  25. 2026LAND: A Longitudinal Analysis of Neuromorphic Datasetscited by 1
  26. 2026EgoReasoner: Learning Egocentric 4D Reasoning via Task-Adaptive Structured Thinkingcited by 1
  27. 2022PoliTO-IIT-CINI Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognitioncited by 0
  28. 2022Spatio-Temporal-based Context Fusion for Video Anomaly Detectioncited by 0
  29. 2022A Survey on Human Action Recognitioncited by 0
  30. 2024Adversarially Masked Video Consistency for Unsupervised Domain Adaptationcited by 0
  31. 2024PASS: Path-selective State Space Model for Event-based Recognitioncited by 0
  32. 2025Multimodal Knowledge Distillation for Egocentric Action Recognition Robust to Missing Modalitiescited by 0
  33. 2025EgoEMS: A High-Fidelity Multimodal Egocentric Dataset for Cognitive Assistance in Emergency Medical Servicescited by 0
  34. 2026SAVA-X: Ego-to-Exo Imitation Error Detection via Scene-Adaptive View Alignment and Bidirectional Cross View Fusioncited by 0
  35. 2026FS-DVS: A Frequency-Selective Dynamic Visual Sensing Paradigm for Enhancing Information Completenesscited by 0
  36. 2026OpenGlass: Ultra-Low-Power On-Device AI Eyewear with Event-based Visioncited by 0
  37. 2026GoStop: Reinforcement Learning for Adaptive Temporal Aggregation in Event-Based Feature Trackingcited by 0
  38. 2026Cooking beyond Frames: A Stereo Event Camera Dataset in the Kitchencited by 0