{"total":33,"rows":[{"id":"2410.17725","title":"YOLOv11: An Overview of the Key Architectural Enhancements","created":"2024-10-23","cited_by_count":425,"area":null},{"id":"2408.15857","title":"What is YOLOv8: An In-Depth Exploration of the Internal Features of the Next-Generation Object Detector","created":"2024-08-28","cited_by_count":45,"area":null},{"id":"2604.27621","title":"Robot Learning from Human Videos: A Survey","created":"2026-04-30","cited_by_count":5,"area":null},{"id":"2409.07813","title":"What is YOLOv9: An In-Depth Exploration of the Internal Features of the Next-Generation Object Detector","created":"2024-09-12","cited_by_count":4,"area":null},{"id":"2503.10986","title":"Image-Goal Navigation Using Refined Feature Guidance and Scene Graph Enhancement","created":"2025-03-14","cited_by_count":3,"area":null},{"id":"2603.15497","title":"Real-Time Oriented Object Detection Transformer in Remote Sensing Images","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2604.10397","title":"Rethinking Video Human-Object Interaction: Set Prediction over Time for Unified Detection and Anticipation","created":"2026-04-12","cited_by_count":2,"area":null},{"id":"2502.03829","title":"Frequency Domain Enhanced U-Net for Low-Frequency Information-Rich Image Segmentation in Surgical and Deep-Sea Exploration Robots","created":"2025-02-06","cited_by_count":1,"area":null},{"id":"2507.00825","title":"High-Frequency Semantics and Geometric Priors for End-to-End Detection Transformers in Challenging UAV Imagery","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2509.18451","title":"An Analysis of Kalman Filter based Object Tracking Methods for Fast-Moving Tiny Objects","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2512.03837","title":"Heatmap Pooling Network for Action Recognition from RGB Videos","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2605.25538","title":"Tetris: Tile-level Sampling for Efficient and High-Fidelity Video Object Tracking","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2607.05177","title":"CP-WSP: A Declarative CP-SAT Framework for Configurable Multi-Constraint Workforce Scheduling","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2607.09888","title":"Bridging the Catalog-to-Real Gap: Scalable Product Recognition via Multi-Stage Contrastive Learning","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2607.22731","title":"Calibration-Free 3D Multi-Camera People Tracking for Indoor Environment","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2504.11995","title":"A Review of YOLOv12: Attention-Based Enhancements vs. Previous Versions","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2504.18046","title":"DMS-Net:Dual-Modal Multi-Scale Siamese Network for Binocular Fundus Image Classification","created":"2025-04-25","cited_by_count":0,"area":null},{"id":"2505.10770","title":"Geofenced Unmanned Aerial Robotic Defender for Deer Detection and Deterrence (GUARD)","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2507.05376","title":"YOLO-APD: Enhancing YOLOv8 for Robust Pedestrian Detection on Complex Road Geometries","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2507.11301","title":"Detecci\\'on y Cuantificaci\\'on de Erosi\\'on Fluvial con Visi\\'on Artificial","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2509.02957","title":"Ensemble YOLO Framework for Multi-Domain Mitotic Figure Detection in Histopathology Images","created":"2025-09-03","cited_by_count":0,"area":null},{"id":"2510.19574","title":"Can You Trust What You See? Alpha Channel No-Box Attacks on Video Object Detection","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2510.20126","title":"Physics-Guided Fusion for Robust 3D Tracking of Fast Moving Small Objects","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2512.04734","title":"MT-Depth: Multi-task Instance feature analysis for the Depth Completion","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2603.08208","title":"Alignment-Aware and Reliability-Gated Multimodal Fusion for Unmanned Aerial Vehicle Detection Across Heterogeneous Thermal-Visual Sensors","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.19625","title":"IUP-Pose: Decoupled Iterative Uncertainty Propagation for Real-time Relative Pose Regression via Implicit Dense Alignment v1","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2605.07388","title":"A Marine Debris Detection Framework for Ocean Robots via Self-Attention Enhancement and Feature Interaction Optimization","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.18523","title":"DART: A design-aware microfluidic chip paradigm for real-time live-cell image analysis","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.25312","title":"LEVIRDet: A Million-Scale 159-Category Dataset and Foundation Model for Universal Remote Sensing Object Detection","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.31456","title":"Zero-Shot Quantization for Object Detectors using Off-the-Shelf Generative Models","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.02005","title":"A Stereo Visual SLAM System Using Object-Level Motion Estimation and Geometric Filtering Based on Cross Disparity","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.07554","title":"Impact of Dataset Composition on Embedded Real-Time UAV Wildfire Detection Using Compact YOLO Models","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2609.39467","title":"DensePed-Lite: Quality-Aware Adaptive Detection for Dense Pedestrians under Occlusion","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}