mlsanityData to 7 Oct 2026

LIGAR: Lightweight General-purpose Action Recognition

arXiv 2108.13153 ↗First posted 30 Aug 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Growing amount of different practical tasks in a video understanding problem has addressed the great challenge aiming to design an universal solution, which should be available for broad masses and suitable for the demanding edge-oriented inference. In this paper we are focused on designing a network architecture and a training pipeline to tackle the mentioned challenges. Our architecture takes the best from the previous ones and brings the ability to be successful not only in appearance-based action recognition tasks but in motion-based problems too. Furthermore, the induced label noise problem is formulated and Adaptive Clip Selection (ACS) framework is proposed to deal with it. Together it makes the LIGAR framework the general-purpose action recognition solution. We also have reported the extensive analysis on the general and gesture datasets to show the excellent trade-off between the performance and the accuracy in comparison to the state-of-the-art solutions. Training code is available at: https://github.com/openvinotoolkit/training_extensions. For the efficient edge-oriented inference all trained models can be exported into the OpenVINO format.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 46 of its 58 references that are in the map. First posted on arXiv 30 Aug 2021.

Builds on

46 of 58 references.

References · 46

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  7. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  8. 2017Non-local Neural Networkscited by 2,290
  9. 2018SlowFast Networks for Video Recognitioncited by 1,862
  10. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  11. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  12. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
34 more
  1. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
  2. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  3. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 899
  4. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  5. 2020X3D: Expanding Architectures for Efficient Video Recognitioncited by 635
  6. 2017Deep Mutual Learningcited by 621
  7. 2021ImageNet-21K Pretraining for the Massescited by 607
  8. 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
  9. 2017Learning Spatio-Temporal Representation with Pseudo-3D Residual Networkscited by 386
  10. 2016Convolutional Two-Stream Network Fusion for Video Action Recognitioncited by 384
  11. 2021High-Performance Large-Scale Image Recognition Without Normalizationcited by 359
  12. 2016YouTube-8M: A Large-Scale Video Classification Benchmarkcited by 324
  13. 2017Temporal Relational Reasoning in Videoscited by 324
  14. 2019A Short Note on the Kinetics-700 Human Action Datasetcited by 308
  15. 2018Additive Margin Softmax for Face Verificationcited by 275
  16. 2019STM: SpatioTemporal and Motion Encoding for Action Recognitioncited by 142
  17. 2021MoViNets: Mobile Video Networks for Efficient Video Recognitioncited by 135
  18. 2018MS-ASL: A Large-Scale Data Set and Benchmark for Understanding American Sign Languagecited by 118
  19. 2019Learning Generalisable Omni-Scale Representations for Person Re-Identificationcited by 73
  20. 2019Learning Spatio-Temporal Representation with Local and Global Diffusioncited by 61
  21. 2020Informative Dropout for Robust Representation Learning: A Shape-bias Perspectivecited by 57
  22. 2019Resource Efficient 3D Convolutional Neural Networkscited by 50
  23. 2019AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architecturescited by 46
  24. 2014Learning Spatiotemporal Features with 3D Convolutional Networkscited by 43
  25. 2019Divide and Conquer the Embedding Space for Metric Learningcited by 39
  26. 2020Global Context Networkscited by 35
  27. 2021Noise-resistant Deep Metric Learning with Ranking-based Instance Selectioncited by 23
  28. 2020PAN: Towards Fast Action Recognition via Learning Persistence of Appearancecited by 12
  29. 2019Continuous Dropoutcited by 7
  30. 2021Learning to Combat Noisy Labels via Classification Marginscited by 4
  31. 2021FocusedDropout for Convolutional Neural Networkcited by 3
  32. 2021A New Training Framework for Deep Neural Networkcited by 2
  33. 2020ASL Recognition with Metric-Learning based Lightweight Networkcited by 1
  34. 2021Efficient Spatialtemporal Context Modeling for Action Recognitioncited by 1

Built on by

Not cited yet.