{"url":"/task/gesture-recognition","name":"Gesture Recognition","slug":"gesture-recognition","description_markdown":"**Gesture Recognition** is an active field of research with applications such as automatic recognition of sign language, interaction of humans and robots or for new ways of controlling video games.\n\n\n<span class=\"description-source\">Source: [Gesture Recognition in RGB Videos Using Human Body Keypoints and Dynamic Time Warping ](https://arxiv.org/abs/1906.12171)</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":572,"papers_with_code":149,"benchmarks":13,"benchmark_tables_in_archive":13,"benchmark_tables_shown":13,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":15,"subtasks":3,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/gesture-recognition-on-dvs128-gesture","slug":"gesture-recognition-on-dvs128-gesture","dataset":"DVS128 Gesture","dataset_url":"/dataset/dvs128-gesture-dataset","rows_in_archive":14,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"TENNs-PLEIADES","paper_title":"TENNs-PLEIADES: Building Temporal Kernels with Orthogonal Polynomials","paper_url":"/paper/building-temporal-kernels-with-orthogonal","paper_date":"2024-05-20","arxiv_id":"2405.12179","code_links":[{"title":"peabrane/pleiades","url":"https://github.com/peabrane/pleiades"}],"syntology":null}},{"leaderboard":"/sota/gesture-recognition-on-capgmyo-db-a","slug":"gesture-recognition-on-capgmyo-db-a","dataset":"CapgMyo DB-a","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"2SRNN","paper_title":"Domain Adaptation for sEMG-based Gesture Recognition with Recurrent Neural Networks","paper_url":"/paper/domain-adaptation-for-semg-based-gesture","paper_date":"2019-01-21","arxiv_id":"1901.06958","code_links":[{"title":"ketyi/2SRNN","url":"https://github.com/ketyi/2SRNN"}],"syntology":null}},{"leaderboard":"/sota/gesture-recognition-on-capgmyo-db-b","slug":"gesture-recognition-on-capgmyo-db-b","dataset":"CapgMyo DB-b","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"2SRNN","paper_title":"Domain Adaptation for sEMG-based Gesture Recognition with Recurrent Neural Networks","paper_url":"/paper/domain-adaptation-for-semg-based-gesture","paper_date":"2019-01-21","arxiv_id":"1901.06958","code_links":[{"title":"ketyi/2SRNN","url":"https://github.com/ketyi/2SRNN"}],"syntology":null}},{"leaderboard":"/sota/gesture-recognition-on-capgmyo-db-c","slug":"gesture-recognition-on-capgmyo-db-c","dataset":"CapgMyo DB-c","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"2SRNN","paper_title":"Domain Adaptation for sEMG-based Gesture Recognition with Recurrent Neural Networks","paper_url":"/paper/domain-adaptation-for-semg-based-gesture","paper_date":"2019-01-21","arxiv_id":"1901.06958","code_links":[{"title":"ketyi/2SRNN","url":"https://github.com/ketyi/2SRNN"}],"syntology":null}},{"leaderboard":"/sota/gesture-recognition-on-chalearn-2013","slug":"gesture-recognition-on-chalearn-2013","dataset":"ChaLearn 2013","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"3S Net TTM","paper_title":"Skeleton-based Gesture Recognition Using Several Fully Connected Layers with Path Signature Features and Temporal Transformer Module","paper_url":"/paper/skeleton-based-gesture-recognition-using","paper_date":"2018-11-17","arxiv_id":"1811.07081","code_links":[{"title":"LiChenyang-Github/Temporal-Transformer-Module","url":"https://github.com/LiChenyang-Github/Temporal-Transformer-Module"}],"syntology":null}},{"leaderboard":"/sota/gesture-recognition-on-chalearn-2014","slug":"gesture-recognition-on-chalearn-2014","dataset":"Chalearn 2014","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"3D-CNN + LSTM","paper_title":"Learning Deep and Compact Models for Gesture Recognition","paper_url":"/paper/learning-deep-and-compact-models-for-gesture","paper_date":"2017-12-29","arxiv_id":"1712.10136","code_links":[{"title":"chriswegmann/drone_steering","url":"https://github.com/chriswegmann/drone_steering"}],"syntology":null}},{"leaderboard":"/sota/gesture-recognition-on-chalearn-2016","slug":"gesture-recognition-on-chalearn-2016","dataset":"ChaLearn 2016","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"3S Net TTM","paper_title":"Skeleton-based Gesture Recognition Using Several Fully Connected Layers with Path Signature Features and Temporal Transformer Module","paper_url":"/paper/skeleton-based-gesture-recognition-using","paper_date":"2018-11-17","arxiv_id":"1811.07081","code_links":[{"title":"LiChenyang-Github/Temporal-Transformer-Module","url":"https://github.com/LiChenyang-Github/Temporal-Transformer-Module"}],"syntology":null}},{"leaderboard":"/sota/gesture-recognition-on-gesturepod","slug":"gesture-recognition-on-gesturepod","dataset":"GesturePod","dataset_url":null,"rows_in_archive":1,"metrics":["Real World Accuracy"],"first_row_in_archive_order":{"model":"GesturePod","paper_title":"GesturePod: Enabling On-device Gesture-based Interaction for White Cane Users","paper_url":"/paper/gesturepod-enabling-on-device-gesture-based","paper_date":"2019-10-20","arxiv_id":null,"code_links":[{"title":"Microsoft/EdgeML","url":"https://github.com/Microsoft/EdgeML"}],"syntology":null}},{"leaderboard":"/sota/gesture-recognition-on-montalbano","slug":"gesture-recognition-on-montalbano","dataset":"Montalbano","dataset_url":null,"rows_in_archive":1,"metrics":["Error rate","Jaccard (Mean)","Precision","Recall"],"first_row_in_archive_order":{"model":"Temp Conv + LSTM","paper_title":"Beyond Temporal Pooling: Recurrence and Temporal Convolutions for Gesture Recognition in Video","paper_url":"/paper/beyond-temporal-pooling-recurrence-and","paper_date":"2015-06-05","arxiv_id":"1506.01911","code_links":[{"title":"chriswegmann/drone_steering","url":"https://github.com/chriswegmann/drone_steering"}],"syntology":null}},{"leaderboard":"/sota/gesture-recognition-on-msrc-12","slug":"gesture-recognition-on-msrc-12","dataset":"MSRC-12","dataset_url":"/dataset/msrc-12","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"3S Net TTM","paper_title":"Skeleton-based Gesture Recognition Using Several Fully Connected Layers with Path Signature Features and Temporal Transformer Module","paper_url":"/paper/skeleton-based-gesture-recognition-using","paper_date":"2018-11-17","arxiv_id":"1811.07081","code_links":[{"title":"LiChenyang-Github/Temporal-Transformer-Module","url":"https://github.com/LiChenyang-Github/Temporal-Transformer-Module"}],"syntology":null}},{"leaderboard":"/sota/gesture-recognition-on-ninapro-db-1-12","slug":"gesture-recognition-on-ninapro-db-1-12","dataset":"Ninapro DB-1 12 gestures","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"2SRNN","paper_title":"Domain Adaptation for sEMG-based Gesture Recognition with Recurrent Neural Networks","paper_url":"/paper/domain-adaptation-for-semg-based-gesture","paper_date":"2019-01-21","arxiv_id":"1901.06958","code_links":[{"title":"ketyi/2SRNN","url":"https://github.com/ketyi/2SRNN"}],"syntology":null}},{"leaderboard":"/sota/gesture-recognition-on-ninapro-db-1-8","slug":"gesture-recognition-on-ninapro-db-1-8","dataset":"Ninapro DB-1 8 gestures","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"2SRNN","paper_title":"Domain Adaptation for sEMG-based Gesture Recognition with Recurrent Neural Networks","paper_url":"/paper/domain-adaptation-for-semg-based-gesture","paper_date":"2019-01-21","arxiv_id":"1901.06958","code_links":[{"title":"ketyi/2SRNN","url":"https://github.com/ketyi/2SRNN"}],"syntology":null}},{"leaderboard":"/sota/gesture-recognition-on-shrec-2017-track-on-3d","slug":"gesture-recognition-on-shrec-2017-track-on-3d","dataset":"SHREC 2017 track on 3D Hand Gesture Recognition","dataset_url":"/dataset/shrec","rows_in_archive":1,"metrics":["14 gestures accuracy"],"first_row_in_archive_order":{"model":"PointLSTM","paper_title":"An Efficient PointLSTM for Point Clouds Based Gesture Recognition","paper_url":"/paper/an-efficient-pointlstm-for-point-clouds-based","paper_date":"2020-06-01","arxiv_id":null,"code_links":[{"title":"Blueprintf/pointlstm-gesture-recognition-pytorch","url":"https://github.com/Blueprintf/pointlstm-gesture-recognition-pytorch"}],"syntology":null}}],"datasets":[{"url":"/dataset/aff-wild","name":"Aff-Wild","full_name":"","num_papers_in_archive":125},{"url":"/dataset/dvs128-gesture-dataset","name":"DVS128 Gesture","full_name":"","num_papers_in_archive":103},{"url":"/dataset/11k-hands","name":"11k Hands","full_name":"","num_papers_in_archive":82},{"url":"/dataset/shrec","name":"SHREC","full_name":"SHape REtrieval Contest","num_papers_in_archive":32},{"url":"/dataset/msrc-12","name":"MSRC-12","full_name":"MSRC-12 Kinect Gesture Dataset","num_papers_in_archive":31},{"url":"/dataset/salsa","name":"SALSA","full_name":"","num_papers_in_archive":18},{"url":"/dataset/jester-gesture-recognition","name":"Jester (Gesture Recognition)","full_name":"","num_papers_in_archive":16},{"url":"/dataset/ipn-hand","name":"IPN Hand","full_name":null,"num_papers_in_archive":5},{"url":"/dataset/wigesture","name":"WiGesture","full_name":"Wireless Sensing Dataset for Gesture Recognition and People ID Identification with ESP32","num_papers_in_archive":5},{"url":"/dataset/tcg","name":"TCG","full_name":"Traffic Control Gesture","num_papers_in_archive":4},{"url":"/dataset/tim-tremor","name":"TIM-Tremor","full_name":"Technology in Motion Tremor","num_papers_in_archive":3},{"url":"/dataset/florentine","name":"Florentine","full_name":"Florentine","num_papers_in_archive":1},{"url":"/dataset/kinteract","name":"Kinteract","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mlgesture-dataset","name":"MLGESTURE DATASET","full_name":"","num_papers_in_archive":1},{"url":"/dataset/slovo-russian-sign-language-dataset","name":"Slovo: Russian Sign Language Dataset","full_name":"Slovo: Russian Sign Language Dataset","num_papers_in_archive":1}],"subtasks":[{"url":"/task/hand-gesture-recognition","name":"Hand Gesture Recognition"},{"url":"/task/hand-gesture-recognition-1","name":"Hand-Gesture Recognition"},{"url":"/task/rf-based-gesture-recognition","name":"RF-based Gesture Recognition"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":149,"tagged_in_all":572,"items":[{"url":"/paper/deep-learning-for-electromyographic-hand","title":"Deep Learning for Electromyographic Hand Gesture Signal Classification Using Transfer Learning","date":"2018-01-10","arxiv_id":"1801.07756","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/word-level-deep-sign-language-recognition","title":"Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison","date":"2019-10-24","arxiv_id":"1910.11006","repositories_listed":3,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/using-deep-convolutional-networks-for-gesture","title":"Using Deep Convolutional Networks for Gesture Recognition in American Sign Language","date":"2017-10-18","arxiv_id":"1710.06836","repositories_listed":3,"syntology":null},{"url":"/paper/cloud-dictionary-sparse-coding-and-modeling","title":"Cloud Dictionary: Sparse Coding and Modeling for Point Clouds","date":"2016-12-15","arxiv_id":"1612.04956","repositories_listed":3,"syntology":null},{"url":"/paper/recognizing-surgical-activities-with","title":"Recognizing Surgical Activities with Recurrent Neural Networks","date":"2016-06-20","arxiv_id":"1606.06329","repositories_listed":3,"syntology":null},{"url":"/paper/hagridv2-1m-images-for-static-and-dynamic","title":"HaGRIDv2: 1M Images for Static and Dynamic Hand Gesture Recognition","date":"2024-12-02","arxiv_id":"2412.01508","repositories_listed":2,"syntology":null},{"url":"/paper/milliflow-scene-flow-estimation-on-mmwave","title":"milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing","date":"2023-06-29","arxiv_id":"2306.17010","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/deep-learning-and-its-applications-to-wifi","title":"SenseFi: A Library and Benchmark on Deep-Learning-Empowered WiFi Human Sensing","date":"2022-07-16","arxiv_id":"2207.07859","repositories_listed":2,"syntology":{"n":12,"n_ran":3,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/towards-domain-independent-and-real-time","title":"Towards Domain-Independent and Real-Time Gesture Recognition Using mmWave Signal","date":"2021-11-11","arxiv_id":"2111.06195","repositories_listed":2,"syntology":null},{"url":"/paper/gesture-recognition-for-initiating-human-to","title":"Gesture Recognition for Initiating Human-to-Robot Handovers","date":"2020-07-20","arxiv_id":"2007.09945","repositories_listed":2,"syntology":null},{"url":"/paper/semg-gesture-recognition-with-a-simple-model","title":"sEMG Gesture Recognition with a Simple Model of Attention","date":"2020-06-05","arxiv_id":"2006.03645","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/recognizing-families-in-the-wild-rfiw-the-4th","title":"Recognizing Families In the Wild: White Paper for the 4th Edition Data Challenge","date":"2020-02-15","arxiv_id":"2002.06303","repositories_listed":2,"syntology":null},{"url":"/paper/hgr-net-a-fusion-network-for-hand-gesture","title":"HGR-Net: A Fusion Network for Hand Gesture Segmentation and Recognition","date":"2018-06-14","arxiv_id":"1806.05653","repositories_listed":2,"syntology":null},{"url":"/paper/intel-realsense-stereoscopic-depth-cameras","title":"Intel RealSense Stereoscopic Depth Cameras","date":"2017-05-16","arxiv_id":"1705.05548","repositories_listed":2,"syntology":null},{"url":"/paper/times-series-averaging-and-denoising-from-a","title":"Times series averaging and denoising from a probabilistic perspective on time-elastic kernels","date":"2016-11-28","arxiv_id":"1611.09194","repositories_listed":2,"syntology":null},{"url":"/paper/a-study-of-vision-based-human-motion","title":"A Study of Vision based Human Motion Recognition and Analysis","date":"2016-08-24","arxiv_id":"1608.06761","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-deployment-of-spiking-neural","title":"Efficient Deployment of Spiking Neural Networks on SpiNNaker2 for DVS Gesture Recognition Using Neuromorphic Intermediate Representation","date":"2025-09-04","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/slrnet-a-real-time-lstm-based-sign-language","title":"SLRNet: A Real-Time LSTM-Based Sign Language Recognition System","date":"2025-06-11","arxiv_id":"2506.11154","repositories_listed":1,"syntology":null},{"url":"/paper/data-free-class-incremental-gesture-1","title":"Data-Free Class-Incremental Gesture Recognition with Prototype-Guided Pseudo Feature Replay","date":"2025-05-26","arxiv_id":"2505.20049","repositories_listed":1,"syntology":null},{"url":"/paper/egoevgesture-gesture-recognition-based-on","title":"EgoEvGesture: Gesture Recognition Based on Egocentric Event Camera","date":"2025-03-16","arxiv_id":"2503.12419","repositories_listed":1,"syntology":null},{"url":"/paper/duo-streamers-a-streaming-gesture-recognition","title":"Duo Streamers: A Streaming Gesture Recognition Framework","date":"2025-02-17","arxiv_id":"2502.12297","repositories_listed":1,"syntology":null},{"url":"/paper/egohand-ego-centric-hand-pose-estimation-and","title":"EgoHand: Ego-centric Hand Pose Estimation and Gesture Recognition with Head-mounted Millimeter-wave Radar and IMUs","date":"2025-01-23","arxiv_id":"2501.13805","repositories_listed":1,"syntology":null},{"url":"/paper/dstsa-gcn-advancing-skeleton-based-gesture","title":"DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling","date":"2025-01-21","arxiv_id":"2501.12086","repositories_listed":1,"syntology":null},{"url":"/paper/knn-mmd-cross-domain-wi-fi-sensing-based-on","title":"KNN-MMD: Cross Domain Wireless Sensing via Local Distribution Alignment","date":"2024-12-06","arxiv_id":"2412.04783","repositories_listed":1,"syntology":null},{"url":"/paper/azsld-azerbaijani-sign-language-dataset-for","title":"AzSLD: Azerbaijani Sign Language Dataset for Fingerspelling, Word, and Sentence Translation with Baseline Software","date":"2024-11-19","arxiv_id":"2411.12865","repositories_listed":1,"syntology":null},{"url":"/paper/generative-ai-for-data-augmentation-in","title":"Generative AI for Data Augmentation in Wireless Networks: Analysis, Applications, and Case Study","date":"2024-11-13","arxiv_id":"2411.08341","repositories_listed":1,"syntology":null},{"url":"/paper/convmixformer-a-resource-efficient","title":"ConvMixFormer- A Resource-efficient Convolution Mixer for Transformer-based Dynamic Hand Gesture Recognition","date":"2024-11-11","arxiv_id":"2411.07118","repositories_listed":1,"syntology":null},{"url":"/paper/x-rage-extended-reality-action-gesture-events","title":"x-RAGE: eXtended Reality -- Action & Gesture Events Dataset","date":"2024-10-25","arxiv_id":"2410.19486","repositories_listed":1,"syntology":null},{"url":"/paper/context-aware-predictive-coding-a","title":"Context-Aware Predictive Coding: A Representation Learning Framework for WiFi Sensing","date":"2024-09-20","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mvtn-a-multiscale-video-transformer-network","title":"MVTN: A Multiscale Video Transformer Network for Hand Gesture Recognition","date":"2024-09-05","arxiv_id":"2409.03890","repositories_listed":1,"syntology":null}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}