{"total":94,"rows":[{"id":"2310.01412","title":"DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model","created":"2023-10-02","cited_by_count":461,"area":"mllm"},{"id":"2404.09990","title":"HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing","created":"2024-04-15","cited_by_count":193,"area":null},{"id":"2411.18279","title":"Large Language Model-Brained GUI Agents: A Survey","created":"2024-11-27","cited_by_count":162,"area":"agents"},{"id":"2402.01105","title":"A Survey for Foundation Models in Autonomous Driving","created":"2024-02-02","cited_by_count":52,"area":"driving"},{"id":"2504.14603","title":"UFO2: The Desktop AgentOS","created":"2025-04-20","cited_by_count":41,"area":null},{"id":"2410.18963","title":"OSCAR: Operating System Control via State-Aware Reasoning and Re-Planning","created":"2024-10-24","cited_by_count":38,"area":"lr"},{"id":"2412.04244","title":"GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities","created":"2024-12-05","cited_by_count":33,"area":null},{"id":"2412.14172","title":"Learning from Massive Human Videos for Universal Humanoid Pose Control","created":"2024-12-18","cited_by_count":29,"area":null},{"id":"2510.19488","title":"VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos","created":"2025-10-22","cited_by_count":22,"area":"agents"},{"id":"2403.11821","title":"A Survey on Quality Metrics for Text-to-Image Generation","created":"2024-03-18","cited_by_count":18,"area":null},{"id":"2408.14819","title":"Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image Generation","created":"2024-08-27","cited_by_count":18,"area":"diffusion"},{"id":"2403.02640","title":"HoloVIC: Large-scale Dataset and Benchmark for Multi-Sensor Holographic Intersection and Vehicle-Infrastructure Cooperative","created":"2024-03-05","cited_by_count":14,"area":null},{"id":"2502.19842","title":"CLIP Under the Microscope: A Fine-Grained Analysis of Multi-Object Representation","created":"2025-02-27","cited_by_count":14,"area":null},{"id":"2507.12956","title":"FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers","created":"2025-07-17","cited_by_count":13,"area":"diffusion"},{"id":"2409.20283","title":"Match Stereo Videos via Bidirectional Alignment","created":"2024-09-30","cited_by_count":11,"area":null},{"id":"2509.10345","title":"Towards Understanding Visual Grounding in Visual Language Models","created":"2025-09-12","cited_by_count":10,"area":"mllm"},{"id":"2501.16679","title":"Polyp-Gen: Realistic and Diverse Polyp Image Generation for Endoscopic Dataset Expansion","created":"2025-01-28","cited_by_count":9,"area":null},{"id":"2407.16541","title":"QPT V2: Masked Image Modeling Advances Visual Scoring","created":"2024-07-23","cited_by_count":8,"area":null},{"id":"2408.06970","title":"Prompt-Based Segmentation at Multiple Resolutions and Lighting Conditions using Segment Anything Model 2","created":"2024-08-13","cited_by_count":8,"area":null},{"id":"2511.06457","title":"Inpaint360GS: Efficient Object-Aware 3D Inpainting via Gaussian Splatting for 360{\\deg} Scenes","created":"2025-11-09","cited_by_count":8,"area":null},{"id":"2411.19292","title":"UrbanCAD: Towards Highly Controllable and Photorealistic 3D Vehicles for Urban Scene Simulation","created":"2024-11-28","cited_by_count":7,"area":null},{"id":"2402.08875","title":"Advancing Human Action Recognition with Foundation Models trained on Unlabeled Public Videos","created":"2024-02-14","cited_by_count":6,"area":null},{"id":"2408.10499","title":"ProgramAlly: Creating Custom Visual Access Programs via Multi-Modal End-User Programming","created":"2024-08-20","cited_by_count":6,"area":null},{"id":"2504.03438","title":"ZFusion: An Effective Fuser of Camera and 4D Radar for 3D Object Perception in Autonomous Driving","created":"2025-04-04","cited_by_count":6,"area":null},{"id":"2505.00737","title":"A Survey on 3D Reconstruction Techniques in Plant Phenotyping: From Classical Methods to Neural Radiance Fields (NeRF), 3D Gaussian Splatting (3DGS), and Beyond","created":"2025-04-30","cited_by_count":6,"area":null},{"id":"2512.05412","title":"YOLO and SGBM Integration for Autonomous Tree Branch Detection and Depth Estimation in Radiata Pine Pruning Applications","created":"2025-12-05","cited_by_count":6,"area":null},{"id":"2407.17847","title":"Move and Act: Enhanced Object Manipulation and Background Integrity for Image Editing","created":"2024-07-25","cited_by_count":4,"area":null},{"id":"2501.05631","title":"HFMF: Hierarchical Fusion Meets Multi-Stream Models for Deepfake Detection","created":"2025-01-10","cited_by_count":4,"area":null},{"id":"2507.04667","title":"What's Making That Sound Right Now? Video-centric Audio-Visual Localization","created":"2025-07-07","cited_by_count":4,"area":null},{"id":"2407.01558","title":"Visual Grounding Methods for Efficient Interaction with Desktop Graphical User Interfaces","created":"2024-05-05","cited_by_count":3,"area":null},{"id":"2408.04786","title":"SOD-YOLOv8 -- Enhancing YOLOv8 for Small Object Detection in Traffic Scenes","created":"2024-08-08","cited_by_count":3,"area":null},{"id":"2409.17526","title":"Drone Stereo Vision for Radiata Pine Branch Detection and Distance Measurement: Integrating SGBM and Segmentation Models","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2502.15737","title":"A Performance Analysis of You Only Look Once Models for Deployment on Constrained Computational Edge Devices in Drone Applications","created":"2025-02-06","cited_by_count":3,"area":null},{"id":"2507.13359","title":"Open-Vocabulary Object Detection in UAV Imagery: A Review and Future Perspectives","created":"2025-07-04","cited_by_count":3,"area":null},{"id":"2508.15038","title":"Decentralized Vision-Based Autonomous Aerial Wildlife Monitoring","created":"2025-08-20","cited_by_count":3,"area":null},{"id":"2309.01055","title":"Integration of Vision-based Object Detection and Grasping for Articulated Manipulator in Lunar Conditions","created":"2023-09-03","cited_by_count":2,"area":null},{"id":"2402.13918","title":"BenchCloudVision: A Benchmark Analysis of Deep Learning Approaches for Cloud Detection and Segmentation in Remote Sensing Imagery","created":"2024-02-21","cited_by_count":2,"area":null},{"id":"2404.10985","title":"Pixel-Wise Symbol Spotting via Progressive Points Location for Parsing CAD Images","created":"2024-04-17","cited_by_count":2,"area":null},{"id":"2405.03039","title":"Performance Evaluation of Real-Time Object Detection for Electric Scooters","created":"2024-05-05","cited_by_count":2,"area":null},{"id":"2408.12747","title":"CatFree3D: Category-agnostic 3D Object Detection with Diffusion","created":"2024-08-22","cited_by_count":2,"area":null},{"id":"2411.00818","title":"On the Black-box Explainability of Object Detection Models for Safe and Trustworthy Industrial Applications","created":"2024-10-28","cited_by_count":2,"area":null},{"id":"2412.16039","title":"SafeCFG: Controlling Harmful Features with Dynamic Safe Guidance for Safe Generation","created":"2024-12-20","cited_by_count":2,"area":"diffusion"},{"id":"2502.08189","title":"AnyCharV: Bootstrap Controllable Character Video Generation with Fine-to-Coarse Guidance","created":"2025-02-12","cited_by_count":2,"area":null},{"id":"2505.06118","title":"The Application of Deep Learning for Lymph Node Segmentation: A Systematic Review","created":"2025-05-09","cited_by_count":2,"area":null},{"id":"2507.20976","title":"Adapting Vehicle Detectors for Aerial Imagery to Unseen Domains with Weak Supervision","created":"2025-07-28","cited_by_count":2,"area":null},{"id":"2510.09092","title":"GL-DT: Multi-UAV Detection and Tracking with Global-Local Integration","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2601.14056","title":"POCI-Diff: 3D-Layout Guided Diffusion for Controllable Synthetic Surveillance Data Generation","created":"2026-01-20","cited_by_count":2,"area":"diffusion"},{"id":"2402.07059","title":"Domain Adaptable Fine-Tune Distillation Framework For Advancing Farm Surveillance","created":"2024-02-10","cited_by_count":1,"area":"distill"},{"id":"2408.10532","title":"NutrifyAI: An AI-Powered System for Real-Time Food Detection, Nutritional Analysis, and Personalized Meal Recommendations","created":"2024-08-20","cited_by_count":1,"area":null},{"id":"2409.00873","title":"Equitable Skin Disease Prediction Using Transfer Learning and Domain Adaptation","created":"2024-09-01","cited_by_count":1,"area":null},{"id":"2410.00503","title":"Drone Stereo Vision for Radiata Pine Branch Detection and Distance Measurement: Utilizing Deep Learning and YOLO Integration","created":"2024-10-01","cited_by_count":1,"area":null},{"id":"2503.10356","title":"Object detection characteristics in a learning factory environment using YOLOv8","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2503.10586","title":"Unlock the Power of Unlabeled Data in Language Driving Model","created":"2025-03-13","cited_by_count":1,"area":"driving"},{"id":"2503.22171","title":"An Empirical Study of Validating Synthetic Data for Text-Based Person Retrieval","created":"2025-03-28","cited_by_count":1,"area":null},{"id":"2504.09129","title":"A Constrained Optimization Approach for Gaussian Splatting from Coarsely-posed Images and Noisy Lidar Point Clouds","created":"2025-04-12","cited_by_count":1,"area":null},{"id":"2505.13633","title":"IPENS:Interactive Unsupervised Framework for Rapid Plant Phenotyping Extraction via NeRF-SAM2 Fusion","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2505.15868","title":"An Inclusive Foundation Model for Generalizable Cytogenetics in Precision Oncology","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2507.02217","title":"Understanding Trade offs When Conditioning Synthetic Data","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2510.01914","title":"Automated Defect Detection for Mass-Produced Electronic Components Based on YOLO Object Detection Models","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2510.24885","title":"FruitProm: Probabilistic Maturity Estimation and Detection of Fruits and Vegetables","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2602.13440","title":"Learning on the Fly: Replay-Based Continual Object Perception for Indoor Drones","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2309.05652","title":"An Effective Two-stage Training Paradigm Detector for Small Dataset","created":"2023-09-11","cited_by_count":0,"area":null},{"id":"2309.10617","title":"Intelligent Debris Mass Estimation Model for Autonomous Underwater Vehicle","created":"2023-09-19","cited_by_count":0,"area":null},{"id":"2310.04566","title":"Knolling Bot: Teaching Robots the Human Notion of Tidiness","created":"2023-10-06","cited_by_count":0,"area":null},{"id":"2311.16357","title":"Cross Entropy in Deep Learning of Classifiers Is Unnecessary -- ISBE Error is All You Need","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2405.04943","title":"Unsupervised Skin Feature Tracking with Deep Neural Networks","created":"2024-05-08","cited_by_count":0,"area":null},{"id":"2406.13694","title":"An Embedded Intelligent System for Attendance Monitoring","created":"2024-06-19","cited_by_count":0,"area":null},{"id":"2406.17323","title":"XAMI -- A Benchmark Dataset for Artefact Detection in XMM-Newton Optical Images","created":"2024-06-25","cited_by_count":0,"area":null},{"id":"2409.08695","title":"Precision Aquaculture: An Integrated Computer Vision and IoT Approach for Optimized Tilapia Feeding","created":"2024-09-13","cited_by_count":0,"area":null},{"id":"2410.05721","title":"Mero Nagarikta: Advanced Nepali Citizenship Data Extractor with Deep Learning-Powered Text Detection and OCR","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2412.03633","title":"NBM: an Open Dataset for the Acoustic Monitoring of Nocturnal Migratory Birds in Europe","created":"2024-12-04","cited_by_count":0,"area":null},{"id":"2501.12239","title":"Investigating Market Strength Prediction with CNNs on Candlestick Chart Images","created":"2025-01-21","cited_by_count":0,"area":null},{"id":"2504.07441","title":"WS-DETR: Robust Water Surface Object Detection through Vision-Radar Fusion with Detection Transformer","created":"2025-04-10","cited_by_count":0,"area":null},{"id":"2505.02441","title":"MSFNet-CPD: Multi-Scale Cross-Modal Fusion Network for Crop Pest Detection","created":"2025-05-05","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":"2506.16563","title":"From Semantic To Instance: A Semi-Self-Supervised Learning Approach","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2506.20522","title":"AI-assisted radiographic analysis in detecting alveolar bone-loss severity and patterns","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2509.14985","title":"PRISM: Product Retrieval In Shopping Carts using Hybrid Matching","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2509.25659","title":"YOLO-Based Defect Detection for Metal Sheets","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2510.03501","title":"Real-Time Threaded Houbara Detection and Segmentation for Wildlife Conservation using Mobile Platforms","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2510.18405","title":"Automated Wicket-Taking Delivery Segmentation and Trajectory-Based Dismissal-Zone Analysis in Cricket Videos Using OCR-Guided YOLOv8","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2511.16712","title":"PairHuman: A High-Fidelity Photographic Dataset for Customized Dual-Person Generation","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2511.19367","title":"AnatomicalNets: A Multi-Structure Segmentation and Contour-Based Distance Estimation Pipeline for Clinically Grounded Lung Cancer T-Staging","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2512.05482","title":"Concept-based Explainable Data Mining with VLM for 3D Detection","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2602.17537","title":"IRIS: Learning-Driven Task-Specific Cinema Robot Arm for Visuomotor Motion Control","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.19456","title":"In-the-Wild Camouflage Attack on Vehicle Detectors through Controllable Image Editing","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2604.16480","title":"Positioning radiata pine branches requiring pruning by drone stereo vision","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2605.08213","title":"Low-Cost Stereo Vision for Robust 3D Positioning of Thin Radiata Pine Branches in Autonomous Drone Pruning","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.30544","title":"On-Device Generative AI for GDPR-Compliant Visual Monitoring: Natural Language Alerts from Local Object Detection","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2608.00111","title":"FDIR: Harmonizing Fidelity and Human-Machine Preference in Lossy Compression Image Restoration","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.01906","title":"Assessing the Benefits of Combining Advanced Deep Learning Techniques for Post-Disaster Building Damage Assessment from UAV Imagery","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.06712","title":"Suppress and Diversify: Refining Robust Pathways for Corruption Robustness","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2609.22108","title":"Correcting Learning-based Perception for Safety","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2610.19100","title":"GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}