mlsanityData to 7 Oct 2026

GTM: Gray Temporal Model for Video Recognition

arXiv 2110.10348 ↗First posted 20 Oct 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Data input modality plays an important role in video action recognition. Normally, there are three types of input: RGB, flow stream and compressed data. In this paper, we proposed a new input modality: gray stream. Specifically, taken the stacked consecutive 3 gray images as input, which is the same size of RGB, can not only skip the conversion process from video decoding data to RGB, but also improve the spatio-temporal modeling ability at zero computation and zero parameters. Meanwhile, we proposed a 1D Identity Channel-wise Spatio-temporal Convolution(1D-ICSC) which captures the temporal relationship at channel-feature level within a controllable computation budget(by parameters G & R). Finally, we confirm its effectiveness and efficiency on several action recognition benchmarks, such as Kinetics, Something-Something, HMDB-51 and UCF-101, and achieve impressive results.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 50 references that are in the map. First posted on arXiv 20 Oct 2021.

Builds on

29 of 50 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  5. 2014Going Deeper with Convolutionscited by 4,231
  6. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  7. 2017Non-local Neural Networkscited by 2,290
  8. 2017The Kinetics Human Action Video Datasetcited by 1,894
  9. 2018SlowFast Networks for Video Recognitioncited by 1,862
  10. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
  11. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,092
  12. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
17 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. 2020X3D: Expanding Architectures for Efficient Video Recognitioncited by 635
  4. 2016Convolutional Two-Stream Network Fusion for Video Action Recognitioncited by 384
  5. 2017Temporal Relational Reasoning in Videoscited by 324
  6. 2015Beyond Short Snippets: Deep Networks for Video Classificationcited by 233
  7. 2020TDN: Temporal Difference Networks for Efficient Action Recognitioncited by 183
  8. 2020TEA: Temporal Excitation and Aggregation for Action Recognitioncited by 165
  9. 2019STM: SpatioTemporal and Motion Encoding for Action Recognitioncited by 142
  10. 2018ECO: Efficient Convolutional Network for Online Video Understandingcited by 115
  11. 2017Compressed Video Action Recognitioncited by 102
  12. 2019TEINet: Towards an Efficient Architecture for Video Recognitioncited by 92
  13. 2018Fast Object Detection in Compressed Videocited by 33
  14. 2019Dance with Flow: Two-in-One Stream Action Detectioncited by 30
  15. 2018StNet: Local and Global Spatial-Temporal Modeling for Action Recognitioncited by 28
  16. 2020Dynamic Inference: A New Approach Toward Efficient Video Action Recognitioncited by 25
  17. 2019Mimic The Raw Domain: Accelerating Action Recognition in the Compressed Domaincited by 8

Built on by

Not cited yet.