{"total":96,"rows":[{"id":"2111.11591","title":"Efficient Video Transformers with Spatial-Temporal Token Selection","created":"2021-11-23","cited_by_count":59,"area":null},{"id":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59,"area":null},{"id":"2108.01959","title":"Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning","created":"2021-08-04","cited_by_count":58,"area":null},{"id":"2501.02341","title":"UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility","created":"2025-01-04","cited_by_count":49,"area":"agents"},{"id":"2303.08914","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","created":"2023-03-15","cited_by_count":43,"area":null},{"id":"2303.05675","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","created":"2023-03-10","cited_by_count":38,"area":null},{"id":"2404.00532","title":"LLMs are Good Action Recognizers","created":"2024-03-31","cited_by_count":37,"area":null},{"id":"2107.08580","title":"UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition","created":"2021-07-19","cited_by_count":35,"area":null},{"id":"2201.07425","title":"WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Tracking","created":"2022-01-19","cited_by_count":26,"area":null},{"id":"2210.00788","title":"Towards a Unified View on Visual Parameter-Efficient Transfer Learning","created":"2022-10-03","cited_by_count":25,"area":null},{"id":"2403.14513","title":"View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network","created":"2024-03-21","cited_by_count":23,"area":null},{"id":"2209.00065","title":"ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting","created":"2022-08-31","cited_by_count":22,"area":null},{"id":"2401.06960","title":"Transformer for Object Re-Identification: A Survey","created":"2024-01-13","cited_by_count":22,"area":null},{"id":"2401.02634","title":"AG-ReID.v2: Bridging Aerial and Ground Views for Person Re-identification","created":"2024-01-05","cited_by_count":20,"area":null},{"id":"2303.08597","title":"Aerial-Ground Person Re-ID","created":"2023-03-15","cited_by_count":19,"area":null},{"id":"2304.07574","title":"Exploring Incompatible Knowledge Transfer in Few-shot Image Generation","created":"2023-04-15","cited_by_count":19,"area":null},{"id":"2307.00067","title":"Transformers in Healthcare: A Survey","created":"2023-06-30","cited_by_count":17,"area":null},{"id":"2303.10280","title":"Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances","created":"2023-03-17","cited_by_count":16,"area":null},{"id":"2503.06965","title":"SeCap: Self-Calibrating and Adaptive Prompts for Cross-view Person Re-Identification in Aerial-Ground Networks","created":"2025-03-10","cited_by_count":16,"area":null},{"id":"2407.12322","title":"Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer","created":"2024-07-17","cited_by_count":15,"area":null},{"id":"2409.13366","title":"RingMo-Aerial: An Aerial Remote Sensing Foundation Model With Affine Transformation Contrastive Learning","created":"2024-09-20","cited_by_count":15,"area":null},{"id":"2303.13505","title":"A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition","created":"2023-03-23","cited_by_count":14,"area":null},{"id":"2410.13790","title":"MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2110.14994","title":"Skeleton-Based Mutually Assisted Interacted Object Localization and Human Action Recognition","created":"2021-10-28","cited_by_count":13,"area":null},{"id":"2312.01640","title":"SequencePAR: Understanding Pedestrian Attributes via A Sequence Generation Paradigm","created":"2023-12-04","cited_by_count":13,"area":null},{"id":"2506.08045","title":"UAVs Meet Agentic AI: A Multidomain Survey of Autonomous Aerial Intelligence and Agentic UAVs","created":"2025-06-08","cited_by_count":13,"area":"agents"},{"id":"2206.15085","title":"Skeleton-based Action Recognition via Adaptive Cross-Form Learning","created":"2022-06-30","cited_by_count":12,"area":null},{"id":"2305.06437","title":"Self-Supervised Video Representation Learning via Latent Time Navigation","created":"2023-05-10","cited_by_count":11,"area":null},{"id":"2311.02559","title":"Rotation Invariant Transformer for Recognizing Object in UAVs","created":"2023-11-05","cited_by_count":11,"area":null},{"id":"2508.12586","title":"Foundation Model for Skeleton-Based Human Action Understanding","created":"2025-08-18","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":"2210.08423","title":"TransVisDrone: Spatio-Temporal Transformer for Vision-based Drone-to-Drone Detection in Aerial Videos","created":"2022-10-16","cited_by_count":10,"area":null},{"id":"2308.07050","title":"Survey on video anomaly detection in dynamic scenes with moving cameras","created":"2023-08-14","cited_by_count":10,"area":null},{"id":"2208.10930","title":"FS-BAN: Born-Again Networks for Domain Generalization Few-Shot Classification","created":"2022-08-23","cited_by_count":9,"area":null},{"id":"2209.00128","title":"Archangel: A Hybrid UAV-based Human Detection Benchmark with Position and Pose Metadata","created":"2022-08-31","cited_by_count":9,"area":null},{"id":"2308.12712","title":"Ground-to-Aerial Person Search: Benchmark Dataset and Approach","created":"2023-08-24","cited_by_count":9,"area":null},{"id":"2303.01589","title":"AZTR: Aerial Video Action Recognition with Auto Zoom and Temporal Reasoning","created":"2023-03-02","cited_by_count":8,"area":null},{"id":"2503.23722","title":"LATex: Leveraging Attribute-based Text Knowledge for Aerial-Ground Person Re-Identification","created":"2025-03-31","cited_by_count":8,"area":null},{"id":"2211.11312","title":"Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack","created":"2022-11-21","cited_by_count":7,"area":null},{"id":"2304.06866","title":"PMI Sampler: Patch Similarity Guided Frame Selection for Aerial Action Recognition","created":"2023-04-14","cited_by_count":7,"area":null},{"id":"2504.09549","title":"SD-ReID: View-aware Stable Diffusion for Aerial-Ground Person Re-Identification","created":"2025-04-13","cited_by_count":7,"area":null},{"id":"2503.17096","title":"Multi-modal Multi-platform Person Re-Identification: Benchmark and Method","created":"2025-03-21","cited_by_count":6,"area":null},{"id":"2506.00915","title":"3D Skeleton-Based Action Recognition: A Review","created":"2025-06-01","cited_by_count":6,"area":null},{"id":"2311.06231","title":"Learning Human Action Recognition Representations Without Real Humans","created":"2023-11-10","cited_by_count":5,"area":null},{"id":"2406.02978","title":"Self-Supervised Skeleton-Based Action Representation Learning: A Benchmark and Beyond","created":"2024-06-05","cited_by_count":5,"area":null},{"id":"2408.00096","title":"From Attributes to Natural Language: A Survey and Foresight on Text-based Person Re-identification","created":"2024-07-31","cited_by_count":5,"area":null},{"id":"2510.22268","title":"GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identification","created":"2025-10-25","cited_by_count":5,"area":null},{"id":"2209.09194","title":"Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition","created":"2022-09-15","cited_by_count":4,"area":null},{"id":"2303.02575","title":"MITFAS: Mutual Information based Temporal Feature Alignment and Sampling for Aerial Video Action Recognition","created":"2023-03-05","cited_by_count":4,"area":null},{"id":"2303.11444","title":"Aerial Diffusion: Text Guided Ground-to-Aerial View Translation from a Single Image using Diffusion Models","created":"2023-03-15","cited_by_count":4,"area":"diffusion"},{"id":"2309.09518","title":"NOMAD: A Natural, Occluded, Multi-scale Aerial Dataset, for Emergency Response Scenarios","created":"2023-09-18","cited_by_count":4,"area":null},{"id":"2311.16738","title":"Riemannian Self-Attention Mechanism for SPD Networks","created":"2023-11-28","cited_by_count":4,"area":null},{"id":"2404.15719","title":"HDBN: A Novel Hybrid Dual-branch Network for Robust Skeleton-based Action Recognition","created":"2024-04-24","cited_by_count":4,"area":null},{"id":"2410.17149","title":"Are Visual-Language Models Effective in Action Recognition? A Comparative Study","created":"2024-10-22","cited_by_count":4,"area":"mllm"},{"id":"2502.15934","title":"Dissecting Human Body Representations in Deep Networks Trained for Person Identification","created":"2025-02-21","cited_by_count":4,"area":null},{"id":"2405.02762","title":"TK-Planes: Tiered K-Planes with High Dimensional Feature Vectors for Dynamic UAV-based Scenes","created":"2024-05-04","cited_by_count":3,"area":null},{"id":"2607.04352","title":"Last-Meter Precision Navigation for UAVs: A Diffusion-Refined Aerial Visual Servoing Approach","created":"2026-07-05","cited_by_count":3,"area":null},{"id":"2108.08344","title":"The Multi-Modal Video Reasoning and Analyzing Competition","created":"2021-08-18","cited_by_count":2,"area":null},{"id":"2409.03245","title":"UAV (Unmanned Aerial Vehicles): Diverse Applications of UAV Datasets in Segmentation, Classification, Detection, and Tracking","created":"2024-09-05","cited_by_count":2,"area":null},{"id":"2409.06665","title":"Data Collection-free Masked Video Modeling","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2502.07130","title":"Unconstrained Body Recognition at Altitude and Range: Comparing Four Approaches","created":"2025-02-10","cited_by_count":2,"area":null},{"id":"2503.23266","title":"OwlSight: A Robust Illumination Adaptation Framework for Dark Video Human Action Recognition","created":"2025-03-30","cited_by_count":2,"area":null},{"id":"2505.10888","title":"PoseBench3D: A Cross-Dataset Analysis Framework for 3D Human Pose Estimation via Pose Lifting Networks","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2506.22843","title":"AG-VPReID 2025: Aerial-Ground Video-based Person Re-identification Challenge Results","created":"2025-06-28","cited_by_count":2,"area":null},{"id":"2511.04042","title":"An LLM-based Framework for Human-Swarm Teaming Cognition in Disaster Search and Rescue","created":"2025-11-06","cited_by_count":2,"area":null},{"id":"2601.01416","title":"AirSpatialBot: A Spatially-Aware Aerial Agent for Fine-Grained Vehicle Attribute Recognization and Retrieval","created":"2026-01-04","cited_by_count":2,"area":"mllm"},{"id":"2604.26520","title":"3D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identification","created":"2026-04-29","cited_by_count":2,"area":null},{"id":"2206.07967","title":"DreamNet: A Deep Riemannian Network based on SPD Manifold Learning for Visual Classification","created":"2022-06-16","cited_by_count":1,"area":null},{"id":"2311.15478","title":"HawkI: Homography & Mutual Information Guidance for 3D-free Single Image to Aerial View","created":"2023-11-27","cited_by_count":1,"area":null},{"id":"2504.02158","title":"UAVTwin: Neural Digital Twins for UAVs using Gaussian Splatting","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2505.01743","title":"An LLM-Empowered Low-Resolution Vision System for On-Device Human Behavior Understanding","created":"2025-05-03","cited_by_count":1,"area":"mllm"},{"id":"2511.22433","title":"SkeletonAgent: An Agentic Interaction Framework for Skeleton-based Action Recognition","created":"2025-11-27","cited_by_count":1,"area":"agents"},{"id":"2512.03837","title":"Heatmap Pooling Network for Action Recognition from RGB Videos","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2601.01312","title":"VReID-XFD: Video-based Person Re-identification at Extreme Far Distance Challenge Results","created":"2026-01-04","cited_by_count":1,"area":null},{"id":"2605.26933","title":"Leveraging Text-to-Image Diffusion Models for Unsupervised Visual Object Tracking","created":"2026-05-26","cited_by_count":1,"area":"diffusion"},{"id":"2207.13315","title":"Portrait Interpretation and a Benchmark","created":"2022-07-27","cited_by_count":0,"area":null},{"id":"2308.04535","title":"Estimation of Human Condition at Disaster Site Using Aerial Drone Images","created":"2023-08-08","cited_by_count":0,"area":null},{"id":"2409.18300","title":"FALCON: Future-Aware Learning with Contextual Object-Centric Pretraining for UAV Action Recognition","created":"2024-09-26","cited_by_count":0,"area":null},{"id":"2410.23806","title":"Human Action Recognition (HAR) Using Skeleton-based Spatial Temporal Relative Transformer Network: ST-RTR","created":"2024-10-31","cited_by_count":0,"area":null},{"id":"2501.05066","title":"Improving Skeleton-based Action Recognition with Interactive Object Information","created":"2025-01-09","cited_by_count":0,"area":null},{"id":"2505.04793","title":"DetReIDX: A Stress-Test Dataset for Real-World UAV-Based Person Recognition","created":"2025-05-07","cited_by_count":0,"area":null},{"id":"2508.06908","title":"Find Them All: Unveiling MLLMs for Versatile Person Re-identification","created":"2025-08-09","cited_by_count":0,"area":null},{"id":"2509.09151","title":"Video Understanding by Design: How Datasets Shape Video Models","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2510.15470","title":"MSAM: Multi-Semantic Adaptive Mining for Cross-Modal Drone Video-Text Retrieval","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2511.19846","title":"Face, Whole-Person, and Object Classification in a Unified Space Via The Interleaved Multi-Domain Identity Curriculum","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2512.11503","title":"TSkel-Mamba: Temporal Dynamic Modeling via State Space Model for Human Skeleton-based Action Recognition","created":"2025-12-12","cited_by_count":0,"area":"ssm"},{"id":"2512.16504","title":"Skeleton-Snippet Contrastive Learning with Multiscale Feature Fusion for Action Localization","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2601.05747","title":"FlyPose: Towards Robust Human Pose Estimation From Aerial Views","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2601.14101","title":"Curriculum-Based Strategies for Efficient Cross-Domain Action Recognition","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2601.21405","title":"Rectifying Geometry-Induced Similarity Distortions for Real-World Aerial-Ground Person Re-Identification","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2604.04183","title":"Scale-Aware Vision-Language Adaptation for Extreme Far-Distance Video Person Re-identification","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2605.19578","title":"Lens Privacy Sealing: A New Benchmark and Method for Physical Privacy-Preserving Action Recognition","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.25615","title":"UAV-OVO: Out-of-Viewpoint Generalization in UAV Action Recognition","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2607.18863","title":"Reliability-Aware 3D Geometric Injection for Universal Person Re-identification","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2610.01569","title":"Managing Context and Communication in Distributed Agentic UAV Swarms","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.19102","title":"The Gap Is in the Geometry: A Convergent Meta-Analysis of Multi-Facet Aerial and Remote Sensing Video Understanding","created":"2026-10-13","cited_by_count":0,"area":"mllm"}],"next_cursor":null}