# HaGRID - HAnd Gesture Recognition Image Dataset arXiv: https://arxiv.org/abs/2206.08219 ยท HTML: https://mlsanity.com/paper/2206.08219/ ## Key facts - Cited by 43 papers in the map (data through 14 Oct 2026). - Builds on 7 of its 44 references that are in the map. - First posted on arXiv 16 Jun 2022. ## Builds on (most cited first, 7 of 7) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020) - [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014) - [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018) - [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016) - [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019) - [IPN Hand: A Video Dataset and Benchmark for Real-Time Continuous Hand Gesture Recognition](https://mlsanity.com/paper/2005.02134/) (2020) ## Built on by (most cited first, 30 of 43) - [HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances](https://mlsanity.com/paper/2403.01693/) (2024) - [From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users](https://mlsanity.com/paper/2508.17281/) (2025) - [Visual Question Answering Instruction: Unlocking Multimodal Large Language Model To Domain-Specific Visual Multitasks](https://mlsanity.com/paper/2402.08360/) (2024) - [Giving a Hand to Diffusion Models: a Two-Stage Approach to Improving Conditional Human Image Generation](https://mlsanity.com/paper/2403.10731/) (2024) - [Towards Online Multi-Modal Social Interaction Understanding](https://mlsanity.com/paper/2503.19851/) (2025) - [Hand1000: Generating Realistic Hands from Text with Only 1,000 Images](https://mlsanity.com/paper/2408.15461/) (2024) - [SocialGesture: Delving into Multi-person Gesture Understanding](https://mlsanity.com/paper/2504.02244/) (2025) - [RHanDS: Refining Malformed Hands for Generated Images with Decoupled Structure and Style Guidance](https://mlsanity.com/paper/2404.13984/) (2024) - [Identity-free Artificial Emotional Intelligence via Micro-Gesture Understanding](https://mlsanity.com/paper/2405.13206/) (2024) - [FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generation](https://mlsanity.com/paper/2412.02690/) (2024) - [Cross-view and Cross-pose Completion for 3D Human Understanding](https://mlsanity.com/paper/2311.09104/) (2023) - [HandCraft: Anatomically Correct Restoration of Malformed Hands in Diffusion Generated Images](https://mlsanity.com/paper/2411.04332/) (2024) - [Omni-MMSI: Toward Identity-attributed Social Interaction Understanding](https://mlsanity.com/paper/2604.00267/) (2026) - [Detecting and Restoring Non-Standard Hands in Stable Diffusion Generated Images](https://mlsanity.com/paper/2312.04236/) (2023) - [HaGRIDv2: 1M Images for Static and Dynamic Hand Gesture Recognition](https://mlsanity.com/paper/2412.01508/) (2024) - [HandEval: Taking the First Step Towards Hand Quality Evaluation in Generated Images](https://mlsanity.com/paper/2510.08978/) (2025) - [FORS-EMG: A Novel sEMG Dataset for Hand Gesture Recognition Across Multiple Forearm Orientations](https://mlsanity.com/paper/2409.07484/) (2024) - [Can Vision Language Models Understand Mimed Actions?](https://mlsanity.com/paper/2506.21586/) (2025) - [EHWGesture -- A dataset for multimodal understanding of clinical gestures](https://mlsanity.com/paper/2509.07525/) (2025) - [VIBE: Visual Instruction Based Editor](https://mlsanity.com/paper/2601.02242/) (2026) - [HanDrawer: Leveraging Spatial Information to Render Realistic Hands Using a Conditional Diffusion Model in Single Stage](https://mlsanity.com/paper/2503.02127/) (2025) - [MGHanD: Multi-modal Guidance for authentic Hand Diffusion](https://mlsanity.com/paper/2503.08133/) (2025) - [Swapped Logit Distillation via Bi-level Teacher Alignment](https://mlsanity.com/paper/2504.20108/) (2025) - [FingerVeinSyn-5M: A Million-Scale Dataset and Benchmark for Finger Vein Recognition](https://mlsanity.com/paper/2506.03635/) (2025) - [Multimodal Evaluation of Russian-language Architectures](https://mlsanity.com/paper/2511.15552/) (2025) - [SocialFusion: Addressing Social Degradation in Pre-trained Vision-Language Models](https://mlsanity.com/paper/2512.01148/) (2025) - [FR-GESTURE: An RGBD Dataset For Gesture-based Human-Robot Interaction In First Responder Operations](https://mlsanity.com/paper/2602.17573/) (2026) - [On the Evaluation Protocol of Gesture Recognition for UAV-based Rescue Operation based on Deep Learning: A Subject-Independence Perspective](https://mlsanity.com/paper/2602.17854/) (2026) - [GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions](https://mlsanity.com/paper/2605.15764/) (2026) - [Spiking Neural Network Enhanced Hand Gesture Recognition Using Low-Cost Single-photon Avalanche Diode Array](https://mlsanity.com/paper/2402.05441/) (2024) ## Abstract (arXiv) This paper introduces an enormous dataset, HaGRID (HAnd Gesture Recognition Image Dataset), to build a hand gesture recognition (HGR) system concentrating on interaction with devices to manage them. That is why all 18 chosen gestures are endowed with the semiotic function and can be interpreted as a specific action. Although the gestures are static, they were picked up, especially for the ability to design several dynamic gestures. It allows the trained model to recognize not only static gestures such as "like" and "stop" but also "swipes" and "drag and drop" dynamic gestures. The HaGRID contains 554,800 images and bounding box annotations with gesture labels to solve hand detection and gesture classification tasks. The low variability in context and subjects of other datasets was the reason for creating the dataset without such limitations. Utilizing crowdsourcing platforms allowed us to collect samples recorded by 37,583 subjects in at least as many scenes with subject-to-camera distances from 0.5 to 4 meters in various natural light conditions. The influence of the diversity characteristics was assessed in ablation study experiments. Also, we demonstrate the HaGRID ability to be used for pretraining models in HGR tasks. The HaGRID and pretrained models are publicly available.