mlsanityData to 7 Oct 2026

FAR: Fourier Aerial Video Recognition

arXiv 2203.10694 ↗First posted 21 Mar 2022cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

We present an algorithm, Fourier Activity Recognition (FAR), for UAV video activity recognition. Our formulation uses a novel Fourier object disentanglement method to innately separate out the human agent (which is typically small) from the background. Our disentanglement technique operates in the frequency domain to characterize the extent of temporal change of spatial pixels, and exploits convolution-multiplication properties of Fourier transform to map this representation to the corresponding object-background entangled features obtained from the network. To encapsulate contextual information and long-range space-time dependencies, we present a novel Fourier Attention algorithm, which emulates the benefits of self-attention by modeling the weighted outer product in the frequency domain. Our Fourier attention formulation uses much fewer computations than self-attention. We have evaluated our approach on multiple UAV datasets including UAV Human RGB, UAV Human Night, Drone Action, and NEC Drone. We demonstrate a relative improvement of 8.02% - 38.69% in top-1 accuracy and up to 3 times faster over prior works.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 60 of its 84 references that are in the map. First posted on arXiv 21 Mar 2022.

Builds on

60 of 84 references.

References · 60

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  5. 2017Non-local Neural Networkscited by 2,290
  6. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  7. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 1,979
  8. 2018SlowFast Networks for Video Recognitioncited by 1,862
  9. 2021ViViT: A Video Vision Transformercited by 1,610
  10. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,609
  11. 2020Linformer: Self-Attention with Linear Complexitycited by 1,462
  12. 2021Video Swin Transformercited by 1,090
38 more
  1. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
  2. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  3. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  4. 2021Multiscale Vision Transformerscited by 896
  5. 2018Self-Attention Generative Adversarial Networkscited by 809
  6. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
  7. 2020X3D: Expanding Architectures for Efficient Video Recognitioncited by 635
  8. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  9. 2017Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?cited by 551
  10. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
  11. 2019Object Detection in 20 Years: A Surveycited by 528
  12. 2021Linear Transformers Are Secretly Fast Weight Programmerscited by 471
  13. 2021Nystr"omformer: A Nystr"om-Based Algorithm for Approximating Self-Attentioncited by 468
  14. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
  15. 2016Convolutional Two-Stream Network Fusion for Video Action Recognitioncited by 384
  16. 2018Efficient Attention: Attention with Linear Complexitiescited by 366
  17. 2021FNet: Mixing Tokens with Fourier Transformscited by 343
  18. 2018Video Action Transformer Networkcited by 316
  19. 2019Video Classification with Channel-Separated Convolutional Networkscited by 290
  20. 2019Learning Correspondence from the Cycle-Consistency of Timecited by 269
  21. 2018Moments in Time Dataset: one million videos for event understandingcited by 215
  22. 2018The Unmanned Aerial Vehicle Benchmark: Object Detection and Trackingcited by 207
  23. 2020Learning in the Frequency Domaincited by 196
  24. 2018Tell Me Where to Look: Guided Attention Inference Networkcited by 168
  25. 2019SCSampler: Sampling Salient Clips from Video for Efficient Action Recognitioncited by 133
  26. 2018Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videoscited by 127
  27. 2019Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognitioncited by 117
  28. 2020Background Matting: The World is Your Green Screencited by 104
  29. 2015Fast Algorithms for Convolutional Neural Networkscited by 102
  30. 2021UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehiclescited by 95
  31. 2018Timeception for Complex Action Recognitioncited by 89
  32. 2020Spatial Temporal Transformer Network for Skeleton-based Action Recognitioncited by 76
  33. 2020SMART Frame Selection for Action Recognitioncited by 73
  34. 2015P-CNN: Pose-based CNN Features for Action Recognitioncited by 58
  35. 2018Representation Flow for Action Recognitioncited by 51
  36. 2021MGSampler: An Explainable Sampling Strategy for Video Action Recognitioncited by 49
  37. 2017Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detectioncited by 45
  38. 2018Motion Feature Network: Fixed Motion Filter for Action Recognitioncited by 34

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 1; 2025: 1; 2026: 2.

10 papers.

  1. 2023AZTR: Aerial Video Action Recognition with Auto Zoom and Temporal Reasoningcited by 8
  2. 2023PMI Sampler: Patch Similarity Guided Frame Selection for Aerial Action Recognitioncited by 7
  3. 2023MITFAS: Mutual Information based Temporal Feature Alignment and Sampling for Aerial Video Action Recognitioncited by 4
  4. 2023Aerial Diffusion: Text Guided Ground-to-Aerial View Translation from a Single Image using Diffusion Modelscited by 4
  5. 2023HawkI: Homography & Mutual Information Guidance for 3D-free Single Image to Aerial Viewcited by 1
  6. 2025Heatmap Pooling Network for Action Recognition from RGB Videoscited by 1
  7. 2023SCP: Soft Conditional Prompt Learning for Aerial Video Action Recognitioncited by 0
  8. 2024FALCON: Future-Aware Learning with Contextual Object-Centric Pretraining for UAV Action Recognitioncited by 0
  9. 2026Spectral Scalpel: Amplifying Adjacent Action Discrepancy via Frequency-Selective Filtering for Skeleton-Based Action Segmentationcited by 0
  10. 2026UAV-OVO: Out-of-Viewpoint Generalization in UAV Action Recognitioncited by 0