mlsanityData to 7 Oct 2026

Event-based Timestamp Image Encoding Network for Human Action Recognition and Anticipation

arXiv 2104.05145 ↗First posted 12 Apr 2021cs.CV cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

Event camera is an asynchronous, high frequency vision sensor with low power consumption, which is suitable for human action understanding task. It is vital to encode the spatial-temporal information of event data properly and use standard computer vision tool to learn from the data. In this work, we propose a timestamp image encoding 2D network, which takes the encoded spatial-temporal images with polarity information of the event data as input and output the action label. In addition, we propose a future timestamp image generator to generate futureaction information to aid the model to anticipate the human action when the action is not completed. Experiment results show that our method can achieve the same level of performance as those RGB-based benchmarks on real world action recognition,and also achieve the state of the art (SOTA) result on gesture recognition. Our future timestamp image generating model can effectively improve the prediction accuracy when the action is not completed. We also provide insight discussion on the importance of motion and appearance information in action recognition and anticipation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 45 references that are in the map. First posted on arXiv 12 Apr 2021.

Builds on

22 of 45 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  6. 2018Human Action Recognition and Prediction: A Surveycited by 226
  7. 2018EV-FlowNet: Self-Supervised Optical Flow Estimation for Event-based Camerascited by 223
  8. 2019End-to-End Learning of Representations for Asynchronous Event-Based Datacited by 216
  9. 2018Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Carscited by 197
  10. 2019Events-to-Video: Bringing Modern Computer Vision to Event Camerascited by 191
  11. 2018Bringing a Blurry Frame Alive at High Frame-Rate with an Event Cameracited by 141
  12. 2018Asynchronous, Photometric Feature Tracking using Events and Framescited by 118
10 more
  1. 2017DDD17: End-To-End DAVIS Driving Datasetcited by 83
  2. 2016Online Real-time Multiple Spatiotemporal Action Localisation and Predictioncited by 57
  3. 2019CED: Color Event Camera Datasetcited by 37
  4. 2018Compressing Recurrent Neural Networks with Tensor Ring for Action Recognitioncited by 34
  5. 2015Event-based Camera Pose Tracking using a Generative Event Modelcited by 23
  6. 2018VIENA2: A Driving Anticipation Datasetcited by 19
  7. 2017Two Stream LSTM: A Deep Fusion Framework for Human Action Recognitioncited by 18
  8. 2018Action Anticipation By Predicting Future Dynamic Imagescited by 18
  9. 2018Action Anticipation: Reading the Intentions of Humans and Robotscited by 17
  10. 2018Dynamic Vision Sensors for Human Activity Recognitioncited by 6

Built on by

Not cited yet.