{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fourier-disentangled-space-time-attention-for","title":"FAR: Fourier Aerial Video Recognition","arxiv_id":"2203.10694","date":"2022-03-21","proceeding":null,"authors":["Divya Kothandaraman","Tianrui Guan","Xijun Wang","Sean Hu","Ming Lin","Dinesh Manocha"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2203.10694v2","url_pdf":"https://arxiv.org/pdf/2203.10694v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fourier-disentangled-space-time-attention-for","repo_url":"https://github.com/divyakraman/ECCV2022_FARFourierAerialVideoRecognition","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"activity-recognition","task_name":"Activity Recognition"},{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"video-recognition","task_name":"Video Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-recognition-on-drone-action","task":"Action Recognition","dataset":"Drone-Action","model":"FAR","rank_in_archive_order":1,"of":2,"metrics":{"Top 1 Accuracy":"92.7"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-on-nec-drone","task":"Action Recognition","dataset":"NEC Drone","model":"FAR","rank_in_archive_order":1,"of":1,"metrics":{"Top 1 Accuracy":"71.46"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-on-uav-human-1","task":"Action Recognition","dataset":"UAV Human","model":"FAR","rank_in_archive_order":1,"of":1,"metrics":{"Top 1 Accuracy":"38.6"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-on-uav-human","task":"Action Recognition","dataset":"UAV-Human","model":"FAR","rank_in_archive_order":4,"of":4,"metrics":{"Top 1 Accuracy":"39.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.10694","atlas_url":"https://app.syntology.ai/?focus=2203.10694","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}