{"list":"other","total":75,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"1909.12828","title":"Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop","created":"2019-09-27","cited_by_count":627},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"id":"2004.00452","title":"PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization","created":"2020-04-01","cited_by_count":521},{"id":"1611.09813","title":"Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision","created":"2016-11-29","cited_by_count":494},{"id":"2104.04631","title":"DexYCB: A Benchmark for Capturing Hand Grasping of Objects","created":"2021-04-09","cited_by_count":325},{"id":"1812.01601","title":"Learning 3D Human Dynamics from Video","created":"2018-12-04","cited_by_count":316},{"id":"1909.04349","title":"FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images","created":"2019-09-10","cited_by_count":271},{"id":"1905.03244","title":"Convolutional Mesh Regression for Single-Image Human Shape Reconstruction","created":"2019-05-08","cited_by_count":270},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"id":"2008.09309","title":"InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image","created":"2020-08-21","cited_by_count":245},{"id":"1801.01615","title":"Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies","created":"2018-01-05","cited_by_count":239},{"id":"1705.01389","title":"Learning to Estimate 3D Hand Pose from Single RGB Images","created":"2017-05-03","cited_by_count":234},{"id":"1704.02463","title":"First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations","created":"2017-04-08","cited_by_count":230},{"id":"1805.04092","title":"Learning to Estimate 3D Human Pose and Shape from a Single Color Image","created":"2018-05-10","cited_by_count":226},{"id":"1910.11006","title":"Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison","created":"2019-10-24","cited_by_count":218},{"id":"2008.04451","title":"Grasping Field: Learning Implicit Representations for Human Grasps","created":"2020-08-10","cited_by_count":179},{"id":"1710.10000","title":"PoseTrack: A Benchmark for Human Pose Estimation and Tracking","created":"2017-10-27","cited_by_count":173},{"id":"2108.06428","title":"FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration","created":"2021-08-13","cited_by_count":169},{"id":"1712.01057","title":"GANerated Hands for Real-time 3D Hand Tracking from Monocular RGB","created":"2017-12-04","cited_by_count":147},{"id":"1908.02486","title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","created":"2019-08-07","cited_by_count":142},{"id":"1804.04875","title":"BodyNet: Volumetric Inference of 3D Human Body Shapes","created":"2018-04-13","cited_by_count":141},{"id":"1812.01053","title":"MS-ASL: A Large-Scale Data Set and Benchmark for Understanding American Sign Language","created":"2018-12-03","cited_by_count":118},{"id":"1506.02178","title":"Capturing Hands in Action using Discriminative Salient Points and Physics Simulation","created":"2015-06-06","cited_by_count":115},{"id":"2001.09691","title":"Multi-Modal Domain Adaptation for Fine-Grained Action Recognition","created":"2020-01-27","cited_by_count":115},{"id":"1804.09534","title":"Hand Pose Estimation via Latent 2.5D Heatmap Regression","created":"2018-04-25","cited_by_count":111},{"id":"2103.08833","title":"Skeleton Aware Multi-modal Sign Language Recognition","created":"2021-03-16","cited_by_count":101},{"id":"1711.04305","title":"Latent Dirichlet Allocation (LDA) and Topic modeling: models, applications, a survey","created":"2017-11-12","cited_by_count":91},{"id":"1704.02201","title":"Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor","created":"2017-04-07","cited_by_count":84},{"id":"2008.00932","title":"AUTSL: A Large Scale Multi-modal Turkish Sign Language Dataset and Baseline Methods","created":"2020-08-03","cited_by_count":75},{"id":"1610.04889","title":"Real-time Joint Tracking of a Hand Manipulating an Object from RGB-D Input","created":"2016-10-16","cited_by_count":56},{"id":"1712.03866","title":"Using a single RGB frame for real time 3D hand pose estimation in the wild","created":"2017-12-11","cited_by_count":39},{"id":"1610.07214","title":"3D Hand Pose Tracking and Estimation Using Stereo Matching","created":"2016-10-23","cited_by_count":35},{"id":"1901.10323","title":"Real-time Hand Gesture Detection and Classification Using Convolutional Neural Networks","created":"2019-01-29","cited_by_count":30},{"id":"2201.09548","title":"Consistent 3D Hand Reconstruction in Video via self-supervised Learning","created":"2022-01-24","cited_by_count":28},{"id":"2306.05731","title":"Multimodal Explainable Artificial Intelligence: A Comprehensive Review of Methodological Advances and Future Research Directions","created":"2023-06-09","cited_by_count":25},{"id":"1901.11164","title":"Spatial-Temporal Graph Convolutional Networks for Sign Language Recognition","created":"2019-01-31","cited_by_count":23},{"id":"2312.16737","title":"HMP: Hand Motion Priors for Pose and Shape Estimation from Video","created":"2023-12-27","cited_by_count":23},{"id":"2004.01283","title":"BosphorusSign22k Sign Language Recognition Dataset","created":"2020-04-02","cited_by_count":19},{"id":"1412.0065","title":"3D Hand Pose Detection in Egocentric RGB-D Images","created":"2014-11-29","cited_by_count":17},{"id":"1504.06378","title":"Depth-based hand pose estimation: methods, data, and challenges","created":"2015-04-24","cited_by_count":16},{"id":"2007.11983","title":"CNN+RNN Depth and Skeleton based Dynamic Hand Gesture Recognition","created":"2020-07-22","cited_by_count":16},{"id":"1506.01911","title":"Beyond Temporal Pooling: Recurrence and Temporal Convolutions for Gesture Recognition in Video","created":"2015-06-05","cited_by_count":15},{"id":"1804.07187","title":"Motion Fused Frames: Data Level Fusion Strategy for Hand Gesture Recognition","created":"2018-04-19","cited_by_count":15},{"id":"2110.12396","title":"Using Motion History Images with 3D Convolutional Networks in Isolated Sign Language Recognition","created":"2021-10-24","cited_by_count":12},{"id":"2404.09308","title":"In My Perspective, In My Hands: Accurate Egocentric 2D Hand Pose and Action Recognition","created":"2024-04-14","cited_by_count":12},{"id":"1705.05301","title":"Back to RGB: 3D tracking of hands and hand-object interactions based on short-baseline stereo","created":"2017-05-15","cited_by_count":8},{"id":"2408.05436","title":"A Methodological and Structural Review of Hand Gesture Recognition Across Diverse Data Modalities","created":"2024-08-10","cited_by_count":8},{"id":"2110.00869","title":"BdSL36: A Dataset for Bangladeshi Sign Letters Recognition","created":"2021-10-02","cited_by_count":7},{"id":"2110.15639","title":"Multi-Task and Multi-Modal Learning for RGB Dynamic Gesture Recognition","created":"2021-10-29","cited_by_count":7},{"id":"2405.11180","title":"GestFormer: Multiscale Wavelet Pooling Transformer Network for Dynamic Hand Gesture Recognition","created":"2024-05-18","cited_by_count":7},{"id":"1509.03001","title":"Real-time Sign Language Fingerspelling Recognition using Convolutional Neural Networks from Depth map","created":"2015-09-10","cited_by_count":6},{"id":"1707.02237","title":"The 2017 Hands in the Million Challenge on 3D Hand Pose Estimation","created":"2017-07-07","cited_by_count":6},{"id":"1808.09208","title":"DeepHPS: End-to-end Estimation of 3D Hand Pose and Shape by Learning from Synthetic Depth","created":"2018-08-28","cited_by_count":6},{"id":"2106.13391","title":"HAN: An Efficient Hierarchical Self-Attention Network for Skeleton-Based Gesture Recognition","created":"2021-06-25","cited_by_count":6},{"id":"2311.15361","title":"Ultra-Range Gesture Recognition using a Web-Camera in Human-Robot Interaction","created":"2023-11-26","cited_by_count":6},{"id":"2109.13879","title":"3D Hand Pose and Shape Estimation from RGB Images for Keypoint-Based Hand Gesture Recognition","created":"2021-09-28","cited_by_count":5},{"id":"2301.11932","title":"RGB Arabic Alphabets Sign Language Dataset","created":"2023-01-30","cited_by_count":5},{"id":"2205.15862","title":"Snapture -- A Novel Neural Architecture for Combined Static and Dynamic Hand Gesture Recognition","created":"2022-05-28","cited_by_count":2},{"id":"2403.01733","title":"3D Hand Reconstruction via Aggregating Intra and Inter Graphs Guided by Prior Knowledge for Hand-Object Interaction Scenario","created":"2024-03-04","cited_by_count":2},{"id":"2411.07118","title":"ConvMixFormer- A Resource-efficient Convolution Mixer for Transformer-based Dynamic Hand Gesture Recognition","created":"2024-11-11","cited_by_count":2}],"next_cursor":null}