{"total":104,"rows":[{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456,"area":null},{"id":"2208.03987","title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","created":"2022-08-08","cited_by_count":149,"area":null},{"id":"2108.12617","title":"AP-10K: A Benchmark for Animal Pose Estimation in the Wild","created":"2021-08-28","cited_by_count":123,"area":null},{"id":"2204.02825","title":"An Empirical Study of Remote Sensing Pretraining","created":"2022-04-06","cited_by_count":105,"area":null},{"id":"2308.08746","title":"SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation","created":"2023-08-17","cited_by_count":104,"area":null},{"id":"2107.08918","title":"Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning","created":"2021-07-19","cited_by_count":96,"area":null},{"id":"2201.08135","title":"Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges","created":"2022-01-20","cited_by_count":84,"area":null},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82,"area":null},{"id":"2211.10772","title":"DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting","created":"2022-11-19","cited_by_count":74,"area":null},{"id":"2212.04246","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","created":"2022-12-07","cited_by_count":65,"area":null},{"id":"2112.01148","title":"FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis","created":"2021-12-02","cited_by_count":61,"area":null},{"id":"2104.14222","title":"Privacy-Preserving Portrait Matting","created":"2021-04-29","cited_by_count":60,"area":null},{"id":"2107.07235","title":"Deep Automatic Natural Image Matting","created":"2021-07-15","cited_by_count":59,"area":null},{"id":"2103.12366","title":"Group-aware Label Transfer for Domain Adaptive Person Re-identification","created":"2021-03-23","cited_by_count":58,"area":null},{"id":"2206.05683","title":"APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking","created":"2022-06-12","cited_by_count":56,"area":null},{"id":"2201.01976","title":"SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection","created":"2022-01-06","cited_by_count":52,"area":null},{"id":"2207.04491","title":"DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer","created":"2022-07-10","cited_by_count":50,"area":null},{"id":"2107.12636","title":"Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers","created":"2021-07-27","cited_by_count":49,"area":null},{"id":"2407.07520","title":"IRSAM: Advancing Segment Anything Model for Infrared Small Target Detection","created":"2024-07-10","cited_by_count":46,"area":null},{"id":"2107.09600","title":"DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation","created":"2021-07-20","cited_by_count":45,"area":null},{"id":"2112.14889","title":"Few-shot Backdoor Defense Using Shapley Estimation","created":"2021-12-30","cited_by_count":41,"area":null},{"id":"2108.03658","title":"One-Shot Object Affordance Detection in the Wild","created":"2021-08-08","cited_by_count":40,"area":null},{"id":"2206.05514","title":"Toward Real-world Single Image Deraining: A New Benchmark and Beyond","created":"2022-06-11","cited_by_count":40,"area":null},{"id":"2203.14533","title":"Robust Unlearnable Examples: Protecting Data Against Adversarial Learning","created":"2022-03-28","cited_by_count":35,"area":null},{"id":"2106.14747","title":"One-Shot Affordance Detection","created":"2021-06-28","cited_by_count":32,"area":null},{"id":"2312.16602","title":"Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey","created":"2023-12-27","cited_by_count":29,"area":null},{"id":"2205.01297","title":"RU-Net: Regularized Unrolling Network for Scene Graph Generation","created":"2022-05-03","cited_by_count":28,"area":null},{"id":"2106.10598","title":"TGRNet: A Table Graph Reconstruction Network for Table Structure Recognition","created":"2021-06-20","cited_by_count":27,"area":null},{"id":"2108.05675","title":"Learning Visual Affordance Grounding from Demonstration Videos","created":"2021-08-12","cited_by_count":25,"area":null},{"id":"2112.12916","title":"Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition","created":"2021-12-24","cited_by_count":25,"area":null},{"id":"2203.16828","title":"Rethinking Portrait Matting with Privacy Preserving","created":"2022-03-31","cited_by_count":25,"area":null},{"id":"2307.00997","title":"RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation","created":"2023-07-03","cited_by_count":25,"area":null},{"id":"2110.06475","title":"SAR-Net: A Scenario-Aware Ranking Network for Personalized Fair Recommendation in Hundreds of Travel Scenarios","created":"2021-10-13","cited_by_count":23,"area":null},{"id":"2211.10927","title":"GLT-T: Global-Local Transformer Voting for 3D Single Object Tracking in Point Clouds","created":"2022-11-20","cited_by_count":23,"area":null},{"id":"2206.05149","title":"Referring Image Matting","created":"2022-06-10","cited_by_count":22,"area":null},{"id":"2208.13196","title":"Grounded Affordance from Exocentric View","created":"2022-08-28","cited_by_count":22,"area":null},{"id":"2104.09713","title":"Hierarchically Modeling Micro and Macro Behaviors via Multi-Task Learning for Conversion Rate Prediction","created":"2021-04-20","cited_by_count":21,"area":null},{"id":"2108.12611","title":"Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Images","created":"2021-08-28","cited_by_count":20,"area":null},{"id":"2207.04680","title":"Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamics","created":"2022-07-11","cited_by_count":20,"area":null},{"id":"2304.09793","title":"Event-based Simultaneous Localization and Mapping: A Comprehensive Survey","created":"2023-04-19","cited_by_count":17,"area":null},{"id":"2304.11584","title":"OSP2B: One-Stage Point-to-Box Network for 3D Siamese Tracking","created":"2023-04-23","cited_by_count":16,"area":null},{"id":"2108.01343","title":"I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection","created":"2021-08-03","cited_by_count":14,"area":null},{"id":"2305.01443","title":"Scalable Mask Annotation for Video Text Spotting","created":"2023-05-02","cited_by_count":13,"area":null},{"id":"2401.11204","title":"Towards Category Unification of 3D Single Object Tracking on Point Clouds","created":"2024-01-20","cited_by_count":13,"area":null},{"id":"2304.04672","title":"Deep Image Matting: A Comprehensive Survey","created":"2023-04-10","cited_by_count":12,"area":null},{"id":"2304.09915","title":"DCN-T: Dual Context Network with Transformer for Hyperspectral Image Classification","created":"2023-04-19","cited_by_count":12,"area":null},{"id":"2410.19998","title":"Artificial Intelligence of Things: A Survey","created":"2024-10-25","cited_by_count":12,"area":null},{"id":"2503.10078","title":"Image Quality Assessment: From Human to Machine Preference","created":"2025-03-13","cited_by_count":12,"area":null},{"id":"2107.11572","title":"The USYD-JD Speech Translation System for IWSLT 2021","created":"2021-07-24","cited_by_count":11,"area":null},{"id":"2110.09241","title":"Video Coding for Machine: Compact Visual Representation Compression for Intelligent Collaborative Analytics","created":"2021-10-18","cited_by_count":11,"area":null},{"id":"2112.13983","title":"Siamese Network with Interactive Transformer for Video Object Segmentation","created":"2021-12-28","cited_by_count":11,"area":null},{"id":"2204.09931","title":"Learning to Purification for Unsupervised Person Re-identification","created":"2022-04-21","cited_by_count":11,"area":null},{"id":"2303.16818","title":"SimDistill: Simulated Multi-modal Distillation for BEV 3D Object Detection","created":"2023-03-29","cited_by_count":10,"area":null},{"id":"2306.17170","title":"An Overview on Generative AI at Scale with Edge-Cloud Computing","created":"2023-06-02","cited_by_count":9,"area":null},{"id":"2203.05712","title":"Towards Scale Consistent Monocular Visual Odometry by Learning from the Virtual World","created":"2022-03-11","cited_by_count":8,"area":null},{"id":"2312.15612","title":"APTv2: Benchmarking Animal Pose Estimation and Tracking with a Large-scale Dataset and Beyond","created":"2023-12-25","cited_by_count":8,"area":null},{"id":"2507.09577","title":"Memory-Augmented SAM2 for Training-Free Surgical Video Segmentation","created":"2025-07-13","cited_by_count":8,"area":null},{"id":"2204.14093","title":"Learning Localization-aware Target Confidence for Siamese Visual Tracking","created":"2022-04-29","cited_by_count":7,"area":null},{"id":"2305.19957","title":"DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting","created":"2023-05-31","cited_by_count":7,"area":null},{"id":"2602.24133","title":"FocusTrack: One-Stage Focus-and-Suppress Framework for 3D Point Cloud Object Tracking","created":"2026-02-27","cited_by_count":7,"area":null},{"id":"2311.13163","title":"Have Your Cake and Eat It Too: Toward Efficient and Accurate Split Federated Learning","created":"2023-11-22","cited_by_count":6,"area":null},{"id":"2108.09041","title":"Out-of-boundary View Synthesis Towards Full-Frame Video Stabilization","created":"2021-08-20","cited_by_count":5,"area":null},{"id":"2203.05724","title":"Information-Theoretic Odometry Learning","created":"2022-03-11","cited_by_count":5,"area":null},{"id":"2411.06725","title":"GTA-Net: An IoT-Integrated 3D Human Pose Estimation System for Real-Time Adolescent Sports Posture Correction","created":"2024-11-11","cited_by_count":5,"area":null},{"id":"2506.12263","title":"A Survey of Foundation Models for IoT: Taxonomy and Criteria-Based Analysis","created":"2025-06-13","cited_by_count":5,"area":null},{"id":"2112.13753","title":"MetaCVR: Conversion Rate Prediction via Meta Learning in Small-Scale Recommendation Scenarios","created":"2021-12-27","cited_by_count":4,"area":null},{"id":"2304.00242","title":"GLT-T++: Global-Local Transformer for 3D Siamese Tracking with Ranking Loss","created":"2023-04-01","cited_by_count":4,"area":null},{"id":"2306.16736","title":"GraMMaR: Ground-aware Motion Model for 3D Human Motion Reconstruction","created":"2023-06-29","cited_by_count":4,"area":null},{"id":"2406.14367","title":"PoseBench: Benchmarking the Robustness of Pose Estimation Models under Corruptions","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2304.02089","title":"Hierarchically Fusing Long and Short-Term User Interests for Click-Through Rate Prediction in Product Search","created":"2023-04-04","cited_by_count":3,"area":null},{"id":"2311.04944","title":"Edge-assisted U-Shaped Split Federated Learning with Privacy-preserving for Internet of Things","created":"2023-11-08","cited_by_count":3,"area":null},{"id":"2409.04011","title":"Hybrid Mask Generation for Infrared Small Target Detection with Single-Point Supervision","created":"2024-09-06","cited_by_count":3,"area":null},{"id":"2507.12823","title":"FAR-Net: Multi-Stage Fusion Network with Enhanced Semantic Alignment and Adaptive Reconciliation for Composed Image Retrieval","created":"2025-07-17","cited_by_count":3,"area":null},{"id":"2508.18803","title":"A Survey on Cloud-Edge-Terminal Collaborative Intelligence in AIoT Networks","created":"2025-08-26","cited_by_count":3,"area":null},{"id":"2309.02820","title":"Roulette: A Semantic Privacy-Preserving Device-Edge Collaborative Inference Framework for Deep Learning Classification Tasks","created":"2023-09-06","cited_by_count":2,"area":null},{"id":"2405.04765","title":"When Foresight Pruning Meets Zeroth-Order Optimization: Efficient Federated Learning for Low-Memory Devices","created":"2024-05-08","cited_by_count":2,"area":null},{"id":"2409.08308","title":"DiReDi: Distillation and Reverse Distillation for AIoT Applications","created":"2024-09-12","cited_by_count":2,"area":null},{"id":"2505.23939","title":"Searching Neural Architectures for Sensor Nodes on IoT Gateways","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2112.13747","title":"MOEF: Modeling Occasion Evolution in Frequency Domain for Promotion-Aware Click-Through Rate Prediction","created":"2021-12-27","cited_by_count":1,"area":null},{"id":"2302.03397","title":"AniPixel: Towards Animatable Pixel-Aligned Human Avatar","created":"2023-02-07","cited_by_count":1,"area":null},{"id":"2304.04529","title":"FAN: Fatigue-Aware Network for Click-Through Rate Prediction in E-commerce Recommendation","created":"2023-04-10","cited_by_count":1,"area":null},{"id":"2305.01899","title":"Empowering Agrifood System with Artificial Intelligence: A Survey of the Progress, Challenges and Opportunities","created":"2023-05-03","cited_by_count":1,"area":null},{"id":"2305.13839","title":"SAR-to-Optical Image Translation via Thermodynamics-inspired Network","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2306.04566","title":"Recent applications of machine learning, remote sensing, and iot approaches in yield prediction: a critical review","created":"2023-06-07","cited_by_count":1,"area":null},{"id":"2306.05358","title":"Trustworthy Sensor Fusion against Inaudible Command Attacks in Advanced Driver-Assistance System","created":"2023-05-30","cited_by_count":1,"area":null},{"id":"2404.09709","title":"Scenario-Adaptive Fine-Grained Personalization Network: Tailoring User Behavior Representation to the Scenario Context","created":"2024-04-15","cited_by_count":1,"area":null},{"id":"2412.03055","title":"Real-Time AIoT for AAV Antenna Interference Detection via Edge-Cloud Collaboration","created":"2024-12-04","cited_by_count":1,"area":null},{"id":"2506.20018","title":"Achieving Trustworthy Real-Time Decision Support Systems with Low-Latency Interpretable AI Models","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2107.09101","title":"Accelerating deep neural networks for efficient scene understanding in automotive cyber-physical systems","created":"2021-07-19","cited_by_count":0,"area":null},{"id":"2112.05534","title":"An Embarrassingly Pragmatic Introduction to Vision-based Autonomous Robots","created":"2021-11-15","cited_by_count":0,"area":null},{"id":"2204.07772","title":"SETTI: A Self-supervised Adversarial Malware Detection Architecture in an IoT Environment","created":"2022-04-16","cited_by_count":0,"area":null},{"id":"2212.09329","title":"SrTR: Self-reasoning Transformer with Visual-linguistic Knowledge for Scene Graph Generation","created":"2022-12-19","cited_by_count":0,"area":null},{"id":"2306.10858","title":"Multi-Granularity Hand Action Detection","created":"2023-06-19","cited_by_count":0,"area":null},{"id":"2405.08183","title":"Towards Energy-Aware Federated Learning via MARL: A Dual-Selection Approach for Model and Client","created":"2024-05-13","cited_by_count":0,"area":null},{"id":"2407.06485","title":"CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community","created":"2024-07-09","cited_by_count":0,"area":null},{"id":"2410.22079","title":"HRPVT: High-Resolution Pyramid Vision Transformer for medium and small-scale human pose estimation","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2502.11644","title":"InTec: integrated things-edge computing: a framework for distributing machine learning pipelines in edge AI systems","created":"2025-02-17","cited_by_count":0,"area":null},{"id":"2505.07980","title":"Task-Adaptive Semantic Communications with Controllable Diffusion-based Data Regeneration","created":"2025-05-12","cited_by_count":0,"area":null},{"id":"2510.08932","title":"MATT-CTR: Unleashing a Model-Agnostic Test-Time Paradigm for CTR Prediction with Confidence-Guided Inference Paths","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2512.14020","title":"Deep Learning Perspective of Scene Understanding in Autonomous Robots","created":"2025-12-16","cited_by_count":0,"area":null}],"next_cursor":"100"}