{"total":41,"rows":[{"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":"2603.07022","title":"OV-DEIM: Real-time DETR-Style Open-Vocabulary Object Detection with GridSynthetic Augmentation","created":"2026-03-07","cited_by_count":3,"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":"2509.20318","title":"A Comprehensive Evaluation of YOLO-based Deer Detection Performance on Edge Devices","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2512.12101","title":"AI-Augmented Pollen Recognition in Optical and Holographic Microscopy for Veterinary Imaging","created":"2025-12-13","cited_by_count":1,"area":null},{"id":"2601.00344","title":"Intelligent Traffic Surveillance for Real-Time Vehicle Detection, License Plate Recognition, and Speed Estimation","created":"2026-01-01","cited_by_count":1,"area":null},{"id":"2603.22841","title":"UAV-DETR: DETR for Anti-Drone Target Detection","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2609.05049","title":"Efficient Multi-Timescale Event Representations for Feed-Forward Object Detection","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2412.14965","title":"Movie2Story: A framework for understanding videos and telling stories in the form of novel text","created":"2024-12-19","cited_by_count":0,"area":null},{"id":"2502.16541","title":"EDocNet: Efficient Datasheet Layout Analysis Based on Focus and Global Knowledge Distillation","created":"2025-02-23","cited_by_count":0,"area":null},{"id":"2505.17364","title":"Optimizing YOLOv8 for Parking Space Detection: Comparative Analysis of Custom YOLOv8 Architecture","created":"2025-05-23","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":"2507.23225","title":"YOLO-ROC: A High-Precision and Ultra-Lightweight Model for Real-Time Road Damage Detection","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2509.19166","title":"YOLO-LAN: Precise Polyp Detection via Optimized Loss, Augmentations and Negatives","created":"2025-09-23","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":"2510.20381","title":"VLSP 2025 MLQA-TSR Challenge: Vietnamese Multimodal Legal Question Answering on Traffic Sign Regulation","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2510.23278","title":"hYOLO Model: Enhancing Object Classification with Hierarchical Context in YOLOv8","created":"2025-10-27","cited_by_count":0,"area":null},{"id":"2510.25032","title":"Efficient License Plate Recognition via Pseudo-Labeled Supervision with Grounding DINO and YOLOv8","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2511.13378","title":"Moving Pictures of Thought: Extracting Visual Knowledge in Charles S. Peirce's Manuscripts with Vision-Language Models","created":"2025-11-17","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":"2512.10975","title":"Agent-Based Modular Learning for Multimodal Emotion Recognition in Human-Agent Systems","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2601.16874","title":"Model-Centric Diagnostics: A Framework for Internal State Readouts","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2602.09446","title":"A Scoping Review of Deep Learning for Urban Visual Pollution and Proposal of a Real-Time Monitoring Framework with a Visual Pollution Index","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2603.01036","title":"SMR-Net:Robot Snap Detection Based on Multi-Scale Features and Self-Attention Network","created":"2026-03-01","cited_by_count":0,"area":null},{"id":"2603.03604","title":"Tracking Feral Horses in Aerial Video Using Oriented Bounding Boxes","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2604.04127","title":"SARES-DEIM: Sparse Mixture-of-Experts Meets DETR for Robust SAR Ship Detection","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2604.10077","title":"DocRevive: A Unified Pipeline for Document Text Restoration","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2604.16500","title":"Semantically Stable Image Composition Analysis via Saliency and Gradient Vector Flow Fusion","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.17530","title":"Real-Time Cellist Postural Evaluation With On-Device Computer Vision","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2604.23788","title":"MIRAGE: A Micro-Interaction Relational Architecture for Grounded Exploration in Multi-Figure Artworks","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2605.14773","title":"Beyond What to Select: A Plug-and-play Oscillatory Data-Volume Scheduling for Efficient Model Training","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.15423","title":"MR2-ByteTrack: CNN and Transformer-based Video Object Detection for AI-augmented Embedded Vision Sensor Nodes","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.16397","title":"Trajectory-Aware Adaptive Inference in Object Detection Models","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.03508","title":"Structure-Guided Mixed Masked Pretraining and Spatial Continuity Regularization for Printed Circuit Board Defect Detection","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.13509","title":"Measurement-Calibrated Multi-Camera Fusion for Vision-Based Indoor Localization","created":"2026-06-11","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":"2606.31007","title":"Dense Structural Priors for Sparse Functional Landmark Localization in Surgical Videos","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":"2608.04061","title":"Advancing Utility Pole and Sign Detection Through Deep Learning","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.11595","title":"ProtoHGF-Net: Prototype HyperGraph Fusion with Intra-modal Calibration for RGBT Object Detection","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.14770","title":"Artificial Intelligence as a Tool for Combating Child Labour: A Real-Time Edge Vision Pipeline for Child Detection and Age Estimation","created":"2026-08-14","cited_by_count":0,"area":null}],"next_cursor":null}