{"url":"/dataset/nvgesture-1","name":"NVGesture","full_name":null,"description_markdown":"The **NVGesture** dataset focuses on touchless driver controlling. It contains 1532 dynamic gestures fallen into 25 classes. It includes 1050 samples for training and 482 for testing. The videos are recorded with three modalities (RGB, depth, and infrared).\n\nSource: [Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognition](https://arxiv.org/abs/2008.09412)\nImage Source: [Online Detection and Classification of Dynamic Hand Gestures With Recurrent 3D Convolutional Neural Network](https://paperswithcode.com/paper/online-detection-and-classification-of/)","description_withheld":null,"homepage":"https://research.nvidia.com/publication/online-detection-and-classification-dynamic-hand-gestures-recurrent-3d-convolutional","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/online-detection-and-classification-of","title":"Online Detection and Classification of Dynamic Hand Gestures With Recurrent 3D Convolutional Neural Network","first_author":"Pavlo Molchanov","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Hand Gesture Recognition","url":"/task/hand-gesture-recognition","datasets_with_task":"/datasets/task/hand-gesture-recognition"}],"languages":[],"variants":[" NVGesture","NVGesture"],"data_loaders":[],"num_papers_in_archive":29,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/hand-gesture-recognition-on-nvgesture-1","task":"Hand Gesture Recognition","dataset_variant":"NVGesture","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"De+Recouple","paper":"/paper/decoupling-and-recoupling-spatiotemporal","metrics":{"Accuracy":"91.70"},"code_links":[{"title":"damo-cv/motionrgbd","url":"https://github.com/damo-cv/motionrgbd"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/decoupling-and-recoupling-spatiotemporal","title":"Decoupling and Recoupling Spatiotemporal Representation for RGB-D-based Motion Recognition","date":"2021-12-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/an-efficient-pointlstm-for-point-clouds-based","title":"An Efficient PointLSTM for Point Clouds Based Gesture Recognition","date":"2020-06-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mmtm-multimodal-transfer-module-for-cnn","title":"MMTM: Multimodal Transfer Module for CNN Fusion","date":"2019-11-20","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improving-the-performance-of-unimodal-dynamic","title":"Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition with Multimodal Training","date":"2018-12-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/motion-fused-frames-data-level-fusion","title":"Motion Fused Frames: Data Level Fusion Strategy for Hand Gesture Recognition","date":"2018-04-19","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}