mlsanityData to 7 Oct 2026

Busy-Quiet Video Disentangling for Video Classification

arXiv 2103.15584 ↗First posted 29 Mar 2021cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

In video data, busy motion details from moving regions are conveyed within a specific frequency bandwidth in the frequency domain. Meanwhile, the rest of the frequencies of video data are encoded with quiet information with substantial redundancy, which causes low processing efficiency in existing video models that take as input raw RGB frames. In this paper, we consider allocating intenser computation for the processing of the important busy information and less computation for that of the quiet information. We design a trainable Motion Band-Pass Module (MBPM) for separating busy information from quiet information in raw video data. By embedding the MBPM into a two-pathway CNN architecture, we define a Busy-Quiet Net (BQN). The efficiency of BQN is determined by avoiding redundancy in the feature space processed by the two pathways: one operating on Quiet features of low-resolution, while the other processes Busy features. The proposed BQN outperforms many recent video processing models on Something-Something V1, Kinetics400, UCF101 and HMDB51 datasets.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 44 of its 58 references that are in the map. First posted on arXiv 29 Mar 2021.

Builds on

44 of 58 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  7. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  8. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  9. 2014Going Deeper with Convolutionscited by 4,231
  10. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  11. 2017Non-local Neural Networkscited by 2,290
  12. 2018SlowFast Networks for Video Recognitioncited by 1,862
32 more
  1. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
  2. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,092
  3. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
  4. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  5. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 899
  6. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 852
  7. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
  8. 2020X3D: Expanding Architectures for Efficient Video Recognitioncited by 635
  9. 2017Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?cited by 551
  10. 2017Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classificationcited by 521
  11. 2014Long-term Recurrent Convolutional Networks for Visual Recognition and Descriptioncited by 483
  12. 2017Learning Spatio-Temporal Representation with Pseudo-3D Residual Networkscited by 386
  13. 2016Convolutional Two-Stream Network Fusion for Video Action Recognitioncited by 384
  14. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  15. 2017Temporal Relational Reasoning in Videoscited by 324
  16. 2019Video Classification with Channel-Separated Convolutional Networkscited by 290
  17. 2015Beyond Short Snippets: Deep Networks for Video Classificationcited by 233
  18. 2018Videos as Space-Time Region Graphscited by 221
  19. 2020TEA: Temporal Excitation and Aggregation for Action Recognitioncited by 165
  20. 2019STM: SpatioTemporal and Motion Encoding for Action Recognitioncited by 142
  21. 2019Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolutioncited by 140
  22. 2016Spatiotemporal Residual Networks for Video Action Recognitioncited by 91
  23. 2017Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognitioncited by 82
  24. 2019More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal Aggregationcited by 64
  25. 2018Representation Flow for Action Recognitioncited by 51
  26. 2018End-to-End Learning of Motion Representation for Video Understandingcited by 43
  27. 2020SmallBigNet: Integrating Core and Contextual Views for Video Classificationcited by 40
  28. 2018StNet: Local and Global Spatial-Temporal Modeling for Action Recognitioncited by 28
  29. 2018Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognitioncited by 22
  30. 2018Video Representation Learning Using Discriminative Poolingcited by 7
  31. 2020Region-based Non-local Operation for Video Classificationcited by 4
  32. 2020Learning spatio-temporal representations with temporal squeeze poolingcited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 1.

2 papers.

  1. 2024Computer Vision for Primate Behavior Analysis in the Wildcited by 10
  2. 2022Context-LSTM: a robust classifier for video detection on UCF101cited by 0