{"total":73,"rows":[{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287,"area":null},{"id":"2108.07181","title":"Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation","created":"2021-08-16","cited_by_count":62,"area":null},{"id":"2208.05318","title":"Generative Action Description Prompts for Skeleton-based Action Recognition","created":"2022-08-10","cited_by_count":43,"area":null},{"id":"2207.02803","title":"Delving into Sequential Patches for Deepfake Detection","created":"2022-07-06","cited_by_count":41,"area":null},{"id":"2303.05234","title":"GPGait: Generalized Pose-based Gait Recognition","created":"2023-03-09","cited_by_count":40,"area":null},{"id":"2203.04570","title":"CP-ViT: Cascade Vision Transformer Pruning via Progressive Sparsity Prediction","created":"2022-03-09","cited_by_count":39,"area":null},{"id":"2211.09590","title":"Hypergraph Transformer for Skeleton-based Action Recognition","created":"2022-11-17","cited_by_count":36,"area":null},{"id":"2204.03873","title":"Spatial Transformer Network on Skeleton-based Gait Recognition","created":"2022-04-08","cited_by_count":33,"area":null},{"id":"2207.06101","title":"Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning","created":"2022-07-13","cited_by_count":33,"area":null},{"id":"2203.10233","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","created":"2022-03-19","cited_by_count":31,"area":null},{"id":"2207.09644","title":"Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning","created":"2022-07-20","cited_by_count":30,"area":null},{"id":"2209.02399","title":"SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition","created":"2022-09-01","cited_by_count":29,"area":null},{"id":"2203.00927","title":"TransDARC: Transformer-based Driver Activity Recognition with Latent Space Feature Calibration","created":"2022-03-02","cited_by_count":25,"area":null},{"id":"2209.05700","title":"Vision Transformers for Action Recognition: A Survey","created":"2022-09-13","cited_by_count":25,"area":null},{"id":"2305.00666","title":"Part Aware Contrastive Learning for Self-Supervised Action Recognition","created":"2023-05-01","cited_by_count":21,"area":null},{"id":"2206.06131","title":"Seeing the forest and the tree: Building representations of both individual and collective dynamics with transformers","created":"2022-06-10","cited_by_count":18,"area":null},{"id":"2210.15491","title":"GaitMixer: Skeleton-based Gait Representation Learning via Wide-spectrum Multi-axial Mixer","created":"2022-10-27","cited_by_count":18,"area":null},{"id":"2312.06330","title":"Navigating Open Set Scenarios for Skeleton-based Action Recognition","created":"2023-12-11","cited_by_count":17,"area":null},{"id":"2403.09805","title":"On the Utility of 3D Hand Poses for Action Recognition","created":"2024-03-14","cited_by_count":17,"area":null},{"id":"2202.11423","title":"Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions","created":"2022-02-23","cited_by_count":13,"area":null},{"id":"2109.02860","title":"Hierarchical Graph Convolutional Skeleton Transformer for Action Recognition","created":"2021-09-07","cited_by_count":12,"area":null},{"id":"2204.04564","title":"Multimodal Transformer for Nursing Activity Recognition","created":"2022-04-09","cited_by_count":12,"area":null},{"id":"2302.02327","title":"Pyramid Self-attention Polymerization Learning for Semi-supervised Skeleton-based Action Recognition","created":"2023-02-05","cited_by_count":11,"area":null},{"id":"2308.10623","title":"GaitPT: Skeletons Are All You Need For Gait Recognition","created":"2023-08-21","cited_by_count":11,"area":null},{"id":"2403.10082","title":"CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner","created":"2024-03-15","cited_by_count":11,"area":null},{"id":"2411.14796","title":"Adaptive Hyper-Graph Convolution Network for Skeleton-based Human Action Recognition with Virtual Connections","created":"2024-11-22","cited_by_count":11,"area":null},{"id":"2203.10694","title":"FAR: Fourier Aerial Video Recognition","created":"2022-03-21","cited_by_count":10,"area":null},{"id":"2207.12842","title":"Unsupervised Domain Adaptation for Video Transformers in Action Recognition","created":"2022-07-26","cited_by_count":10,"area":null},{"id":"2402.04599","title":"Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment","created":"2024-02-07","cited_by_count":10,"area":null},{"id":"2112.10570","title":"Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognition","created":"2021-12-20","cited_by_count":9,"area":null},{"id":"2102.05624","title":"NAST: Non-Autoregressive Spatial-Temporal Transformer for Time Series Forecasting","created":"2021-02-10","cited_by_count":8,"area":null},{"id":"2107.07089","title":"STAR: Sparse Transformer-based Action Recognition","created":"2021-07-15","cited_by_count":8,"area":null},{"id":"2305.11468","title":"Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness","created":"2023-05-19","cited_by_count":8,"area":null},{"id":"2308.09305","title":"Human Part-wise 3D Motion Context Learning for Sign Language Recognition","created":"2023-08-18","cited_by_count":8,"area":null},{"id":"2311.16497","title":"GaitContour: Efficient Gait Recognition based on a Contour-Pose Representation","created":"2023-11-27","cited_by_count":8,"area":null},{"id":"2310.19418","title":"GaitFormer: Learning Gait Representations with Noisy Multi-Task Learning","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2109.02376","title":"Robust Event Detection based on Spatio-Temporal Latent Action Unit using Skeletal Information","created":"2021-09-06","cited_by_count":6,"area":null},{"id":"2201.05739","title":"Real-World Graph Convolution Networks (RW-GCNs) for Action Recognition in Smart Video Surveillance","created":"2022-01-15","cited_by_count":6,"area":null},{"id":"2202.02212","title":"Video Violence Recognition and Localization Using a Semi-Supervised Hard Attention Model","created":"2022-02-04","cited_by_count":6,"area":null},{"id":"2211.15107","title":"A Light Touch Approach to Teaching Transformers Multi-view Geometry","created":"2022-11-28","cited_by_count":6,"area":null},{"id":"2310.13039","title":"Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2312.06718","title":"Large Scale Foundation Models for Intelligent Manufacturing Applications: A Survey","created":"2023-12-11","cited_by_count":6,"area":null},{"id":"2410.11650","title":"Efficient Partitioning Vision Transformer on Edge Devices for Distributed Inference","created":"2024-10-15","cited_by_count":6,"area":null},{"id":"2304.10073","title":"Video-based Contrastive Learning on Decision Trees: from Action Recognition to Autism Diagnosis","created":"2023-04-20","cited_by_count":5,"area":null},{"id":"2501.09411","title":"Towards Robust and Realistic Human Pose Estimation via WiFi Signals","created":"2025-01-16","cited_by_count":5,"area":null},{"id":"2202.02314","title":"Towards To-a-T Spatio-Temporal Focus for Skeleton-Based Action Recognition","created":"2022-02-04","cited_by_count":4,"area":null},{"id":"2303.01685","title":"Multi-Scale Control Signal-Aware Transformer for Motion Synthesis without Phase","created":"2023-03-03","cited_by_count":4,"area":null},{"id":"2309.00794","title":"FastPoseGait: A Toolbox and Benchmark for Efficient Pose-based Gait Recognition","created":"2023-09-02","cited_by_count":4,"area":null},{"id":"2411.05692","title":"Autoregressive Adaptive Hypergraph Transformer for Skeleton-based Activity Recognition","created":"2024-11-08","cited_by_count":4,"area":null},{"id":"2503.11004","title":"VA-AR: Learning Velocity-Aware Action Representations with Mixture of Window Attention","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2507.00566","title":"Zero-Shot Skeleton-Based Action Recognition With Prototype-Guided Feature Alignment","created":"2025-07-01","cited_by_count":4,"area":null},{"id":"2111.11433","title":"Towards Tokenized Human Dynamics Representation","created":"2021-11-22","cited_by_count":3,"area":null},{"id":"2302.01921","title":"Transformers in Action Recognition: A Review on Temporal Modeling","created":"2022-12-29","cited_by_count":3,"area":null},{"id":"2411.00128","title":"Muscles in Time: Learning to Understand Human Motion by Simulating Muscle Activations","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2503.23214","title":"Action Recognition in Real-World Ambient Assisted Living Environment","created":"2025-03-29","cited_by_count":2,"area":null},{"id":"2507.14885","title":"BeatFormer: Efficient motion-robust remote heart rate estimation through unsupervised spectral zoomed attention filters","created":"2025-07-20","cited_by_count":2,"area":null},{"id":"2508.10522","title":"EgoMusic-driven Human Dance Motion Estimation with Skeleton Mamba","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2104.13051","title":"Three-stream network for enriched Action Recognition","created":"2021-04-27","cited_by_count":1,"area":null},{"id":"2207.02027","title":"CNN-based Local Vision Transformer for COVID-19 Diagnosis","created":"2022-07-05","cited_by_count":1,"area":null},{"id":"2301.10492","title":"Flow-guided Semi-supervised Video Object Segmentation","created":"2023-01-25","cited_by_count":1,"area":null},{"id":"2407.21525","title":"Skeleton-Based Action Recognition with Spatial-Structural Graph Convolution","created":"2024-07-31","cited_by_count":1,"area":null},{"id":"2411.19544","title":"SkelMamba: A State Space Model for Efficient Skeleton Action Recognition of Neurological Disorders","created":"2024-11-29","cited_by_count":1,"area":null},{"id":"2501.07039","title":"IoT-Based Real-Time Medical-Related Human Activity Recognition Using Skeletons and Multi-Stage Deep Learning for Healthcare","created":"2025-01-13","cited_by_count":1,"area":null},{"id":"2512.22214","title":"Signal-SGN++: Topology-Enhanced Time-Frequency Spiking Graph Network for Skeleton-Based Action Recognition","created":"2025-12-22","cited_by_count":1,"area":null},{"id":"2304.01672","title":"Motion-R3: Fast and Accurate Motion Annotation via Representation-based Representativeness Ranking","created":"2023-04-04","cited_by_count":0,"area":null},{"id":"2308.12914","title":"3D Pose Nowcasting: Forecast the Future to Improve the Present","created":"2023-08-24","cited_by_count":0,"area":null},{"id":"2310.10453","title":"On the Relevance of Temporal Features for Medical Ultrasound Video Recognition","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2409.00330","title":"GMFL-Net: A Global Multi-geometric Feature Learning Network for Repetitive Action Counting","created":"2024-08-31","cited_by_count":0,"area":null},{"id":"2501.01689","title":"Quantitative Gait Analysis from Single RGB Videos Using a Dual-Input Transformer-Based Network","created":"2025-01-03","cited_by_count":0,"area":null},{"id":"2509.16623","title":"CGTGait: Collaborative Graph and Transformer for Gait Emotion Recognition","created":"2025-09-20","cited_by_count":0,"area":null},{"id":"2512.11654","title":"Kinetic Mining in Context: Few-Shot Action Synthesis via Text-to-Motion Distillation","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2610.18176","title":"Neuro-Symbolic Graph Transformers for Hierarchical Intention Recognition from Multimodal Human Activity Sequences","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}